|
1
|
Zhai Y, Chen Z, Luo X, Zheng Z, Zhang H, Wang X, Yan X, Liu X, Yin J, Wang J, Zhang J. Generation of surgical reports for lymph node dissection during laparoscopic gastric cancer surgery based on artificial intelligence. Int J Comput Assist Radiol Surg 2025; 20:1025-1033. [PMID: 40167881 DOI: 10.1007/s11548-025-03345-w] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/07/2024] [Accepted: 02/27/2025] [Indexed: 04/02/2025]
Abstract
PURPOSE This study aimed to develop an artificial intelligence (AI) model for the surgical report output of laparoscopic lymph node dissection in the suprapancreatic region during gastric cancer surgery. METHODS Patients who underwent laparoscopic radical resection for gastric cancer were included in this study, and their surgical videos were analyzed. The videos were recorded from the opening of the gastropancreatic fold as the starting point to the transection of the left gastric artery as the endpoint, with the video frame rate set to 1 frame per second. All surgical procedures were recorded following the principle of tool-tissue interaction, with annotations completed by an experienced surgeon and reviewed by a senior surgeon. The final annotated surgical videos were used as inputs for the AI model to generate the surgical report output. RESULTS A total of 100 patients who underwent laparoscopic surgery for gastric cancer were included. A Surgical Concept Alignment Network was used as the model for surgical report output. The average number of frames in the videos was 728.71, with the grasping forceps being the most frequently used instrument. The AI model successfully generated a surgical video report output, achieving a BLEU-4 score of 0.7377, METEOR score of 0.4846, and ROUGE-L score of 0.7953. CONCLUSION The AI model demonstrates its capability in producing surgical report output for laparoscopic lymph node dissection in the suprapancreatic region during gastric cancer surgery. This model serves as a valuable tool in clinical diagnosis, treatment, and training.
Collapse
Affiliation(s)
- Yuhao Zhai
- Department of General Surgery, Beijing Friendship Hospital, Capital Medical University, 95 Yong'an Road, Xicheng District, Beijing, China
| | - Zhen Chen
- Centre for Artificial Intelligence and Robotics (CAIR), Hong Kong Institute of Science & Innovation, Chinese Academy of Sciences, Shantin, China
| | - Xingjian Luo
- Centre for Artificial Intelligence and Robotics (CAIR), Hong Kong Institute of Science & Innovation, Chinese Academy of Sciences, Shantin, China
| | - Zhi Zheng
- Department of General Surgery, Beijing Friendship Hospital, Capital Medical University, 95 Yong'an Road, Xicheng District, Beijing, China
| | - Haiqiao Zhang
- Department of General Surgery, Beijing Friendship Hospital, Capital Medical University, 95 Yong'an Road, Xicheng District, Beijing, China
| | - Xi Wang
- Department of General Surgery, Beijing Friendship Hospital, Capital Medical University, 95 Yong'an Road, Xicheng District, Beijing, China
| | - Xiaosheng Yan
- Department of General Surgery, Beijing Friendship Hospital, Capital Medical University, 95 Yong'an Road, Xicheng District, Beijing, China
| | - Xiaoye Liu
- Department of General Surgery, Beijing Friendship Hospital, Capital Medical University, 95 Yong'an Road, Xicheng District, Beijing, China
| | - Jie Yin
- Department of General Surgery, Beijing Friendship Hospital, Capital Medical University, 95 Yong'an Road, Xicheng District, Beijing, China
| | - Jinqiao Wang
- Foundation Model Research Center, Institute of Automation, Chinese Academy of Sciences, 95 Zhongguancun East Road, Haidian District, Beijing, China.
- School of artificial intelligence, University of Chinese Academy of Sciences, 19A Yuquan Road, Shijingshan District, Beijing, China.
- Wuhan AI Research, Wuhan, Hubei, China.
| | - Jun Zhang
- Department of General Surgery, Beijing Friendship Hospital, Capital Medical University, 95 Yong'an Road, Xicheng District, Beijing, China.
| |
Collapse
|
|
2
|
Liu C, Li Y, Xu Y, Hou H. The impact of preoperative skeletal muscle mass index-defined sarcopenia on postoperative complications and survival in gastric cancer: An updated meta-analysis. EUROPEAN JOURNAL OF SURGICAL ONCOLOGY 2025; 51:109569. [PMID: 39794171 DOI: 10.1016/j.ejso.2024.109569] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/11/2024] [Revised: 12/05/2024] [Accepted: 12/27/2024] [Indexed: 01/13/2025]
Abstract
BACKGROUND The impact of preoperative sarcopenia on postoperative outcomes in gastric cancer remains debated. This study aims to perform an in-depth meta-analysis and comprehensive review of the relationship between preoperative sarcopenia, as assessed by the Skeletal Muscle Mass Index (SMI), and postoperative complications and survival metrics in gastric cancer patients, to offer new insights into this issue. METHODS We conducted a systematic search of primary studies in databases such as Embase, PubMed, and Web of Science, up to July 2024. Our analysis focused on comparing postoperative readmission and mortality rates, overall and severe complication rates, incidence of specific complications, as well as overall survival (OS) and disease-free survival (DFS) between groups with and without preoperative sarcopenia. RESULTS Our review included 42 studies with a total of 11,981 patients. Findings revealed that patients with sarcopenia had significantly higher rates of overall postoperative complications, severe complications, mortality, and readmissions compared to those without sarcopenia (all P < 0.001). A detailed examination showed that sarcopenic patients had notably higher incidences of pulmonary complications, bowel obstruction, and pancreatic fistulas. Additionally, the OS (P < 0.001) and DFS (P = 0.003) rates were considerably lower in the sarcopenia group. CONCLUSIONS Preoperative sarcopenia is associated with an increased risk of postoperative complications and poorer survival outcomes in gastric cancer patients. Given these associations, it is recommended to incorporate routine screening for sarcopenia using SMI before surgery, where feasible, to enhance patient risk assessment and customize treatment approaches.
Collapse
Affiliation(s)
- Chengcong Liu
- Department of Gastrointestinal Surgery, Qingdao Central Hospital, University of Health and Rehabilitation Sciences(Qingdao Central Hospital), Qingdao, 266000, China
| | - Yueping Li
- Department of Gastrointestinal Surgery, Qingdao Central Hospital, University of Health and Rehabilitation Sciences(Qingdao Central Hospital), Qingdao, 266000, China
| | - Yongjing Xu
- Department of Gastrointestinal Surgery, Qingdao Central Hospital, University of Health and Rehabilitation Sciences(Qingdao Central Hospital), Qingdao, 266000, China
| | - Hong Hou
- Department of Breast Surgery, Qingdao Central Hospital, University of Health and Rehabilitation Sciences(Qingdao Central Hospital), Qingdao, 266000, China.
| |
Collapse
|
|
3
|
Adachi K, Ebisutani Y, Matsubara Y, Okimoto E, Ishimura N, Ishihara S. Effectiveness of Artificial Intelligence in Screening Esophagogastroduodenoscopy. Cureus 2025; 17:e79935. [PMID: 40177429 PMCID: PMC11962169 DOI: 10.7759/cureus.79935] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 03/01/2025] [Indexed: 04/05/2025] Open
Abstract
BACKGROUND This retrospective study investigated the usefulness of the EW10-EG01 artificial intelligence (AI) application for screening esophagogastroduodenoscopy (EGD). METHODOLOGY A total of 7,655 subjects (4,863 men, 2,792 women; mean age 54.9±10.1 years) who underwent EGD during a medical checkup were enrolled in the study. The number of diagnosed upper gastrointestinal tumors was compared between EGD examinations performed with and without the AI system. RESULTS EGD examinations with and without the AI system were performed on 3,841 and 3,814 subjects, respectively. Biopsy procedures were more frequently performed, and examination time was longer in EGD with AI applications than in those without. Upper gastrointestinal tumors diagnosed by EGD with and without AI were 39 (1.02%) and 24 (0.63%), respectively (P = 0.062). There was a significant difference in the detection rate of esophageal and gastric tumors between EGD with (30, 0.78%) and without (14, 0.37%) the AI system (P = 0.017). When endoscopists were divided into three groups based on their experience with the EW10-EG01 application, higher detection rates of esophageal and gastric tumors were observed in each group when using EGD with AI. CONCLUSIONS Usage of the EW10-EG01 AI system may be useful for screening EGD due to the increased esophageal and gastric tumor detection rate.
Collapse
Affiliation(s)
- Kyoichi Adachi
- Health Center, Shimane Environment and Health Public Corporation, Matsue, JPN
| | - Yuri Ebisutani
- Health Center, Shimane Environment and Health Public Corporation, Matsue, JPN
| | - Yuko Matsubara
- Health Center, Shimane Environment and Health Public Corporation, Matsue, JPN
| | - Eiko Okimoto
- Health Center, Shimane Environment and Health Public Corporation, Matsue, JPN
| | - Norihisa Ishimura
- Second Department of Internal Medicine, Faculty of Medicine, Shimane University, Izumo, JPN
| | - Shunji Ishihara
- Second Department of Internal Medicine, Faculty of Medicine, Shimane University, Izumo, JPN
| |
Collapse
|
|
4
|
Rencuzogullari A, Karahan SN, Selcukbiricik F, Lacin S, Taskin OC, Saka B, Karahacioglu D, Gurses B, Ozoran E, Uymaz DS, Ozata IH, Saglam S, Bugra D, Balik E. The New Era of Total Neoadjuvant FLOT Therapy for Locally Advanced, Resectable Gastric Cancer: A Propensity-Matched Comparison With Standard Perioperative Therapy. J Surg Oncol 2025; 131:417-426. [PMID: 39400342 PMCID: PMC12044282 DOI: 10.1002/jso.27934] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/07/2024] [Revised: 08/28/2024] [Accepted: 09/17/2024] [Indexed: 10/15/2024]
Abstract
BACKGROUND The FLOT 4-AIO trial established the docetaxel-based regimen's superiority over epirubicin-based triplet therapy in terms of survival rates and acceptable toxicity for locally advanced resectable gastric (LARGC). Yet, fewer than half of the patients achieved completion of eight prescribed FLOT cycles. We proposed that administering all FLOT cycles in the form of total neoadjuvant therapy may improve completion rates and downstaging. This study contrasted total neoadjuvant therapy (FLOT x8) with standard neoadjuvant therapy (FLOT 4+4) for patients LARGC adenocarcinoma who underwent curative resection with routine D2 lymphadenectomy, focusing on histopathological outcomes, toxicity, and survival outcomes. METHODS We reviewed patients with histologically confirmed advanced clinical stage cT2 or higher, nodal positive stage (cN+), or both, with resectable gastric tumors and no distant metastases (January 2017 to July 2023). We divided patients into two groups, FLOT 4+4 and FLOT x8; FLOT 4+4 patients underwent four preoperative and four postoperative bi-weekly cycles of docetaxel, oxaliplatin, leucovorin, and fluorouracil, while FLOT x8 patients received all eight cycles preoperatively after a gradual practice change starting from January 2020. Propensity score matching adjusted for age, clinical stage, tumor location, and histology. RESULTS Of the 77 patients in the FLOT x8 group, 37 were propensity-matched to an equal number in the FLOT 4+4 group. Demographics, duration of surgery, and hospital stay showed no significant differences between the groups. The FLOT x8 group exhibited a significantly higher all-cycle completion rate at 89.1% compared to FLOT 4+4's 67.6% (p < 0.01). Both groups demonstrated comparable hematological and non-hematological toxicity rates, Clavien-Dindo ≥ 3 complications, and CAP tumor regression grades. The mean number of harvested lymph nodes was 42.5 and 41.2 in the FLOT 4+4 and FLOT x8 groups, respectively. Similar rates of disease-free survival and overall survival were noted in both groups, despite a trend toward a higher pathological complete response rate, albeit not statistically significant (8.1% vs. 18.9%, p = 0.29), in the FLOT x8 group at a median follow-up of 36 months. CONCLUSION Total neoadjuvant therapy with the FLOT x8 protocol corresponds to higher treatment completion rates, a safety profile similar to standard perioperative therapy, and a twofold increase in complete pathological response. Further research on long-term oncological outcomes is needed to confirm the effectiveness of total neoadjuvant therapy.
Collapse
Affiliation(s)
| | - Salih Nafiz Karahan
- Department of General Surgery, School of MedicineKoç UniversityIstanbulTurkey
| | - Fatih Selcukbiricik
- Department of Medical Oncology, School of MedicineKoç UniversityIstanbulTurkey
| | - Sahin Lacin
- Department of Medical Oncology, School of MedicineKoç UniversityIstanbulTurkey
| | - Orhun Cig Taskin
- Department of Pathology, School of MedicineKoç UniversityIstanbulTurkey
| | - Burcu Saka
- Department of Pathology, School of MedicineKoç UniversityIstanbulTurkey
| | | | - Bengi Gurses
- Department of Radiology, School of MedicineKoç UniversityIstanbulTurkey
| | - Emre Ozoran
- Department of General Surgery, School of MedicineKoç UniversityIstanbulTurkey
| | - Derya Salim Uymaz
- Department of General Surgery, School of MedicineKoç UniversityIstanbulTurkey
| | - Ibrahim Halil Ozata
- Department of General Surgery, School of MedicineKoç UniversityIstanbulTurkey
| | - Sezer Saglam
- Department of Medical OncologyDemiroglu Bilim UniversityIstanbulTurkey
| | - Dursun Bugra
- Department of General Surgery, School of MedicineKoç UniversityIstanbulTurkey
- Department of General SurgeryAmerican HospitalIstanbulTurkey
| | - Emre Balik
- Department of General Surgery, School of MedicineKoç UniversityIstanbulTurkey
| |
Collapse
|
|
5
|
Ying Y, Ju R, Wang J, Li W, Ji Y, Shi Z, Chen J, Chen M. Accuracy of machine learning in diagnosing microsatellite instability in gastric cancer: A systematic review and meta-analysis. Int J Med Inform 2025; 193:105685. [PMID: 39515046 DOI: 10.1016/j.ijmedinf.2024.105685] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/24/2024] [Revised: 10/21/2024] [Accepted: 10/28/2024] [Indexed: 11/16/2024]
Abstract
BACKGROUND Significant challenges persist in the early identification of microsatellite instability (MSI) within current clinical practice. In recent years, with the growing utilization of machine learning (ML) in the diagnosis and management of gastric cancer (GC), numerous researchers have explored the effectiveness of ML methodologies in detecting MSI. Nevertheless, the predictive value of these approaches still lacks comprehensive evidence. Accordingly, this study was carried out to consolidate the accuracy of ML in the prompt detection of MSI in GC. METHODS PubMed, the Cochrane Library, the Web of Science, and Embase were retrieved up to March 20, 2024. The risk of bias in the encompassed studies was evaluated utilizing a risk assessment tool for predictive models. Models were then subjected to subgroup analysis based on the modeling variables. RESULTS A total of 12 studies, encompassing 11,912 patients with GC, satisfied the predefined inclusion criteria. ML models established in these studies were primarily based on pathological images, clinical features, and radiomics. The results suggested that in the validation sets, the pathological image-based models had a synthesized c-index of 0.86 [95 % CI (0.83-0.89)], with sensitivity and specificity being 0.86 [95 % CI (0.76-0.92)] and 0.83 [95 % CI (0.78-0.87)], respectively; radiomics feature-based models achieved respective values of 0.87 [95 % CI (0.81-0.92)], 0.77 [95 % CI (0.70-0.83)] and 0.81 [95 % CI (0.74-0.87)]; radiomics feature-based models + clinical feature-based models achieved respective values of 0.87 [95 % CI (0.81-0.93)], 0.78 [95 % CI (0.70-0.84)] and 0.79 [95 % CI (0.69-0.86)]. CONCLUSIONS ML has demonstrated optimal performance in detecting MSI in GC and could serve as a prospective early adjunctive detection tool for MSI in GC. Future research should contemplate minimally invasive or non-invasive, readily collectible, and efficient predictors to augment the predictive accuracy of ML.
Collapse
Affiliation(s)
- Yuou Ying
- The Second Affiliated College of Zhejiang Chinese Medical University, Hangzhou 310053, Zhejiang Province, China
| | - Ruyi Ju
- Zhejiang Chinese Medical University, Hangzhou 310053, Zhejiang Province, China
| | - Jieyi Wang
- The Basic Medical College of Zhejiang Chinese Medical University, Hangzhou 310053, Zhejiang Province, China
| | - Wenkai Li
- Zhejiang Chinese Medical University, Hangzhou 310053, Zhejiang Province, China
| | - Yuan Ji
- The Second Affiliated College of Zhejiang Chinese Medical University, Hangzhou 310053, Zhejiang Province, China
| | - Zhenyu Shi
- The Second Affiliated College of Zhejiang Chinese Medical University, Hangzhou 310053, Zhejiang Province, China
| | - Jinhan Chen
- The Second Affiliated College of Zhejiang Chinese Medical University, Hangzhou 310053, Zhejiang Province, China
| | - Mingxian Chen
- Department of Gastroenterology, Tongde Hospital of Zhejiang Province, Street Gucui No. 234, Region Xihu, Hangzhou 310012, Zhejiang Province, China.
| |
Collapse
|
|
6
|
Akbari A, Adabi M, Masoodi M, Namazi A, Mansouri F, Tabaeian SP, Shokati Eshkiki Z. Artificial intelligence: clinical applications and future advancement in gastrointestinal cancers. Front Artif Intell 2024; 7:1446693. [PMID: 39764458 PMCID: PMC11701808 DOI: 10.3389/frai.2024.1446693] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/10/2024] [Accepted: 12/02/2024] [Indexed: 04/01/2025] Open
Abstract
One of the foremost causes of global healthcare burden is cancer of the gastrointestinal tract. The medical records, lab results, radiographs, endoscopic images, tissue samples, and medical histories of patients with gastrointestinal malignancies provide an enormous amount of medical data. There are encouraging signs that the advent of artificial intelligence could enhance the treatment of gastrointestinal issues with this data. Deep learning algorithms can swiftly and effectively analyze unstructured, high-dimensional data, including texts, images, and waveforms, while advanced machine learning approaches could reveal new insights into disease risk factors and phenotypes. In summary, artificial intelligence has the potential to revolutionize various features of gastrointestinal cancer care, such as early detection, diagnosis, therapy, and prognosis. This paper highlights some of the many potential applications of artificial intelligence in this domain. Additionally, we discuss the present state of the discipline and its potential future developments.
Collapse
Affiliation(s)
- Abolfazl Akbari
- Colorectal Research Center, Iran University of Medical Sciences, Tehran, Iran
| | - Maryam Adabi
- Infectious Ophthalmologic Research Center, Ahvaz Jundishapur University of Medical Sciences, Ahvaz, Iran
| | - Mohsen Masoodi
- Colorectal Research Center, Iran University of Medical Sciences, Tehran, Iran
| | - Abolfazl Namazi
- Colorectal Research Center, Iran University of Medical Sciences, Tehran, Iran
- Department of Internal Medicine, School of Medicine, Iran University of Medical Sciences, Tehran, Iran
| | - Fatemeh Mansouri
- Department of Microbiology, Faculty of Sciences, Qom Branch, Islamic Azad University, Qom, Iran
| | - Seidamir Pasha Tabaeian
- Colorectal Research Center, Iran University of Medical Sciences, Tehran, Iran
- Department of Internal Medicine, School of Medicine, Iran University of Medical Sciences, Tehran, Iran
| | - Zahra Shokati Eshkiki
- Alimentary Tract Research Center, Clinical Sciences Research Institute, Imam Khomeini Hospital, Ahvaz Jundishapur University of Medical Sciences, Ahvaz, Iran
| |
Collapse
|
|
7
|
Ali A, Iqbal A, Khan S, Ahmad N, Shah S. A two-phase transfer learning framework for gastrointestinal diseases classification. PeerJ Comput Sci 2024; 10:e2587. [PMID: 39896396 PMCID: PMC11784777 DOI: 10.7717/peerj-cs.2587] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/24/2024] [Accepted: 11/17/2024] [Indexed: 02/04/2025]
Abstract
Gastrointestinal (GI) disorders are common and often debilitating health issues that affect a significant portion of the population. Recent advancements in artificial intelligence, particularly computer vision algorithms, have shown great potential in detecting and classifying medical images. These algorithms utilize deep convolutional neural network architectures to learn complex spatial features in images and make predictions for similar unseen images. The proposed study aims to assist gastroenterologists in making more efficient and accurate diagnoses of GI patients by utilizing its two-phase transfer learning framework to identify GI diseases from endoscopic images. Three pre-trained image classification models, namely Xception, InceptionResNetV2, and VGG16, are fine-tuned on publicly available datasets of annotated endoscopic images of the GI tract. Additionally, two custom convolutional neural networks are constructed and fully trained for comparative analysis of their performance. Four different classification tasks are examined based on the endoscopic image categories. The proposed architecture employing InceptionResNetV2 achieves the most consistent and generalized performance across most classification tasks, yielding accuracy scores of 85.7% for general classification of GI tract (eight-category classification), 97.6% for three-diseases classification, 99.5% for polyp identification (binary classification), and 74.2% for binary classification of esophagitis severity on unseen endoscopic images. The results indicate the effectiveness of the two-phase transfer learning framework for clinical use to enhance the identification of GI diseases, aiding in their early diagnosis and treatment.
Collapse
Affiliation(s)
- Ahmed Ali
- School of Computing Sciences, Pak-Austria Fachhochschule: Institute of Applied Sciences and Technology, Mang, Haripur, Khyber Pakhtunkhwa, Pakistan
| | - Arshad Iqbal
- School of Computing Sciences, Pak-Austria Fachhochschule: Institute of Applied Sciences and Technology, Mang, Haripur, Khyber Pakhtunkhwa, Pakistan
- Sino-Pak Center for Artificial Intelligence, Pak-Austria Fachhochschule Institute of Applied Sciences and Technology, Mang, Haripur, Khyber Pakhtunkhwa, Pakistan
| | - Sohail Khan
- Sino-Pak Center for Artificial Intelligence, Pak-Austria Fachhochschule Institute of Applied Sciences and Technology, Mang, Haripur, Khyber Pakhtunkhwa, Pakistan
| | - Naveed Ahmad
- College of Computer and Information Sciences, Prince Sultan University, Riyadh, Saudi Arabia
| | - Sajid Shah
- College of Computer and Information Sciences, Prince Sultan University, Riyadh, Saudi Arabia
| |
Collapse
|
|
8
|
Khosravi M, Jasemi SK, Hayati P, Javar HA, Izadi S, Izadi Z. Transformative artificial intelligence in gastric cancer: Advancements in diagnostic techniques. Comput Biol Med 2024; 183:109261. [PMID: 39488054 DOI: 10.1016/j.compbiomed.2024.109261] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/25/2024] [Revised: 09/30/2024] [Accepted: 10/07/2024] [Indexed: 11/04/2024]
Abstract
Gastric cancer represents a significant global health challenge with elevated incidence and mortality rates, highlighting the need for advancements in diagnostic and therapeutic strategies. This review paper addresses the critical need for a thorough synthesis of the role of artificial intelligence (AI) in the management of gastric cancer. It provides an in-depth analysis of current AI applications, focusing on their contributions to early diagnosis, treatment planning, and outcome prediction. The review identifies key gaps and limitations in the existing literature by examining recent studies and technological developments. It aims to clarify the evolution of AI-driven methods and their impact on enhancing diagnostic accuracy, personalizing treatment strategies, and improving patient outcomes. The paper emphasizes the transformative potential of AI in overcoming the challenges associated with gastric cancer management and proposes future research directions to further harness AI's capabilities. Through this synthesis, the review underscores the importance of integrating AI technologies into clinical practice to revolutionize gastric cancer management.
Collapse
Affiliation(s)
- Mobina Khosravi
- Student Research Committee, Kermanshah University of Medical Sciences, Kermanshah, Iran; USERN Office, Kermanshah University of Medical Sciences, Kermanshah, Iran.
| | - Seyedeh Kimia Jasemi
- Student Research Committee, Kermanshah University of Medical Sciences, Kermanshah, Iran; USERN Office, Kermanshah University of Medical Sciences, Kermanshah, Iran.
| | - Parsa Hayati
- Student Research Committee, Kermanshah University of Medical Sciences, Kermanshah, Iran; USERN Office, Kermanshah University of Medical Sciences, Kermanshah, Iran.
| | - Hamid Akbari Javar
- Department of Pharmaceutics, Faculty of Pharmacy, Tehran University of Medical Sciences, Tehran, Iran; USERN Office, Kermanshah University of Medical Sciences, Kermanshah, Iran.
| | - Saadat Izadi
- Department of Computer Engineering and Information Technology, Razi University, Kermanshah, Iran; USERN Office, Kermanshah University of Medical Sciences, Kermanshah, Iran.
| | - Zhila Izadi
- Pharmaceutical Sciences Research Center, Health Institute, Kermanshah University of Medical Sciences, Kermanshah, Iran; USERN Office, Kermanshah University of Medical Sciences, Kermanshah, Iran.
| |
Collapse
|
|
9
|
Liu Y, Shang X, Du W, Shen W, Zhu Y. Helicobacter Pylori Infection as the Predominant High-Risk Factor for Gastric Cancer Recurrence Post-Gastrectomy: An 8-Year Multicenter Retrospective Study. Int J Gen Med 2024; 17:4999-5014. [PMID: 39494357 PMCID: PMC11531290 DOI: 10.2147/ijgm.s485347] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/03/2024] [Accepted: 10/24/2024] [Indexed: 11/05/2024] Open
Abstract
Purpose The reappearance of gastric cancer, a frequent postoperative complication following radical gastric cancer surgery, substantially impacts the near-term and far-reaching medical outlook of patients. The objective of this research was to create a machine learning algorithm that could recognize high-risk factors for gastric cancer recurrence and anticipate the correlation between gastric cancer recurrence and Helicobacter pylori (H. pylori) infection. Patients and Methods This investigation comprised 1234 patients diagnosed with gastric cancer, and 37 characteristic variables were obtained. Four machine learning algorithms, namely, extreme gradient boosting (XGBoost), random forest (RF), k-nearest neighbor algorithm (KNN), and multilayer perceptron (MLP), were implemented to develop the models. The k-fold cross-validation technique was utilized to perform internal validation of the four models, while independent datasets were employed for external validation of the models. Results In contrast to the other machine learning models, the XGBoost algorithm demonstrated superior predictive ability regarding high-risk factors for gastric cancer recurrence. The outcomes of Shapley additive explanation (SHAP) analysis revealed that tumor invasion depth, tumor lymph node metastasis, H. pylori infection, postoperative carcinoembryonic antigen (CEA), tumor size, and tumor number were risk elements for gastric cancer recurrence in patients, with H. pylori infection being the primary high-risk factor. Conclusion Out of the four machine learning models, the XGBoost algorithm exhibited superior performance in predicting the recurrence of gastric cancer. In addition, machine learning models can help clinicians identify key prognostic factors that are clinically meaningful for the application of personalized patient monitoring and immunotherapy.
Collapse
Affiliation(s)
- Yuan Liu
- Department of General Surgery, Wuxi Medical Center of Nanjing Medical University, Wuxi, People’s Republic of China
- Department of General Surgery, Tengzhou Central People’s Hospital, Jining Medical College, Shandong, People’s Republic of China
| | - Xingchen Shang
- Department of General Surgery, Wuxi Medical Center of Nanjing Medical University, Wuxi, People’s Republic of China
| | - Wenyi Du
- Department of General Surgery, Wuxi Medical Center of Nanjing Medical University, Wuxi, People’s Republic of China
| | - Wei Shen
- Department of General Surgery, Wuxi Medical Center of Nanjing Medical University, Wuxi, People’s Republic of China
| | - Yanfei Zhu
- Department of General Surgery, Wuxi Medical Center of Nanjing Medical University, Wuxi, People’s Republic of China
| |
Collapse
|
|
10
|
Aznar-Gimeno R, García-González MA, Muñoz-Sierra R, Carrera-Lasfuentes P, Rodrigálvarez-Chamarro MDLV, González-Muñoz C, Meléndez-Estrada E, Lanas Á, Del Hoyo-Alonso R. GastricAITool: A Clinical Decision Support Tool for the Diagnosis and Prognosis of Gastric Cancer. Biomedicines 2024; 12:2162. [PMID: 39335675 PMCID: PMC11429470 DOI: 10.3390/biomedicines12092162] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/11/2024] [Revised: 09/10/2024] [Accepted: 09/19/2024] [Indexed: 09/30/2024] Open
Abstract
BACKGROUND/OBJECTIVE Gastric cancer (GC) is a complex disease representing a significant global health concern. Advanced tools for the early diagnosis and prediction of adverse outcomes are crucial. In this context, artificial intelligence (AI) plays a fundamental role. The aim of this work was to develop a diagnostic and prognostic tool for GC, providing support to clinicians in critical decision-making and enabling personalised strategies. METHODS Different machine learning and deep learning techniques were explored to build diagnostic and prognostic models, ensuring model interpretability and transparency through explainable AI methods. These models were developed and cross-validated using data from 590 Spanish Caucasian patients with primary GC and 633 cancer-free individuals. Up to 261 variables were analysed, including demographic, environmental, clinical, tumoral, and genetic data. Variables such as Helicobacter pylori infection, tobacco use, family history of GC, TNM staging, metastasis, tumour location, treatment received, gender, age, and genetic factors (single nucleotide polymorphisms) were selected as inputs due to their association with the risk and progression of the disease. RESULTS The XGBoost algorithm (version 1.7.4) achieved the best performance for diagnosis, with an AUC value of 0.68 using 5-fold cross-validation. As for prognosis, the Random Survival Forest algorithm achieved a C-index of 0.77. Of interest, the incorporation of genetic data into the clinical-demographics models significantly increased discriminatory ability in both diagnostic and prognostic models. CONCLUSIONS This article presents GastricAITool, a simple and intuitive decision support tool for the diagnosis and prognosis of GC.
Collapse
Affiliation(s)
- Rocío Aznar-Gimeno
- Department of Big Data and Cognitive Systems, Instituto Tecnológico de Aragón, ITA, María de Luna 7-8, 50018 Zaragoza, Spain
| | - María Asunción García-González
- Instituto de Investigación Sanitaria Aragón (IIS Aragón), 50009 Zaragoza, Spain
- Instituto Aragonés de Ciencias de la Salud (IACS), 50009 Zaragoza, Spain
- Centro de Investigación Biomédica en Red de Enfermedades Hepáticas y Digestivas (CIBERehd), 28029 Madrid, Spain
| | - Rubén Muñoz-Sierra
- Department of Big Data and Cognitive Systems, Instituto Tecnológico de Aragón, ITA, María de Luna 7-8, 50018 Zaragoza, Spain
| | - Patricia Carrera-Lasfuentes
- Instituto de Investigación Sanitaria Aragón (IIS Aragón), 50009 Zaragoza, Spain
- Facultad de Ciencias de la Salud, Universidad San Jorge, 50830 Zaragoza, Spain
| | | | - Carlos González-Muñoz
- Department of Big Data and Cognitive Systems, Instituto Tecnológico de Aragón, ITA, María de Luna 7-8, 50018 Zaragoza, Spain
| | - Enrique Meléndez-Estrada
- Department of Big Data and Cognitive Systems, Instituto Tecnológico de Aragón, ITA, María de Luna 7-8, 50018 Zaragoza, Spain
| | - Ángel Lanas
- Instituto de Investigación Sanitaria Aragón (IIS Aragón), 50009 Zaragoza, Spain
- Centro de Investigación Biomédica en Red de Enfermedades Hepáticas y Digestivas (CIBERehd), 28029 Madrid, Spain
- Department of Gastroenterology, Hospital Clínico Universitario Lozano Blesa, 50009 Zaragoza, Spain
- School of Medicine, University of Zaragoza, 50009 Zaragoza, Spain
| | - Rafael Del Hoyo-Alonso
- Department of Big Data and Cognitive Systems, Instituto Tecnológico de Aragón, ITA, María de Luna 7-8, 50018 Zaragoza, Spain
| |
Collapse
|
|
11
|
Bhardwaj P, Kim S, Koul A, Kumar Y, Changela A, Shafi J, Ijaz MF. Advanced CNN models in gastric cancer diagnosis: enhancing endoscopic image analysis with deep transfer learning. Front Oncol 2024; 14:1431912. [PMID: 39351364 PMCID: PMC11439627 DOI: 10.3389/fonc.2024.1431912] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/14/2024] [Accepted: 08/09/2024] [Indexed: 10/04/2024] Open
Abstract
Introduction The rapid advancement of science and technology has significantly expanded the capabilities of artificial intelligence, enhancing diagnostic accuracy for gastric cancer. Methods This research aims to utilize endoscopic images to identify various gastric disorders using an advanced Convolutional Neural Network (CNN) model. The Kvasir dataset, comprising images of normal Z-line, normal pylorus, ulcerative colitis, stool, and polyps, was used. Images were pre-processed and graphically analyzed to understand pixel intensity patterns, followed by feature extraction using adaptive thresholding and contour analysis for morphological values. Five deep transfer learning models-NASNetMobile, EfficientNetB5, EfficientNetB6, InceptionV3, DenseNet169-and a hybrid model combining EfficientNetB6 and DenseNet169 were evaluated using various performance metrics. Results & discussion For the complete images of gastric cancer, EfficientNetB6 computed the top performance with 99.88% accuracy on a loss of 0.049. Additionally, InceptionV3 achieved the highest testing accuracy of 97.94% for detecting normal pylorus, while EfficientNetB6 excelled in detecting ulcerative colitis and normal Z-line with accuracies of 98.8% and 97.85%, respectively. EfficientNetB5 performed best for polyps and stool with accuracies of 98.40% and 96.86%, respectively.The study demonstrates that deep transfer learning techniques can effectively predict and classify different types of gastric cancer at early stages, aiding experts in diagnosis and detection.
Collapse
Affiliation(s)
- Priya Bhardwaj
- Department of Computer Science and Engineering (CSE), Tula's Institute, Dehradun, India
| | - SeongKi Kim
- Department of Computer Science and Engineering (CSE), School of Technology, Pandit Deendayal Energy University, Gandhinagar, India
| | - Apeksha Koul
- School of Computer Science Engineering and Technology, Bennett University, Greater Noida, India
| | - Yogesh Kumar
- Department of Computer Science and Engineering (CSE), School of Technology, Pandit Deendayal Energy University, Gandhinagar, India
| | - Ankur Changela
- Department of Information and Communication Technology (ICT), School of Technology, Pandit Deendayal Energy University, Gandhinagar, India
| | - Jana Shafi
- Department of Computer Engineering and Information, College of Engineering in Wadi Alddawasir, Prince Sattam Bin Abdulaziz University, Wadi Alddawasir, Saudi Arabia
| | - Muhammad Fazal Ijaz
- School of Information Technology (IT) and Engineering, Melbourne Institute of Technology, Melbourne, VIC, Australia
| |
Collapse
|
|
12
|
Huang J, Saw SN, He T, Yang R, Qin Y, Chen Y, Kiong LC. DCNNLFS: A Dilated Convolutional Neural Network With Late Fusion Strategy for Intelligent Classification of Gastric Histopathology Images. IEEE J Biomed Health Inform 2024; 28:4534-4543. [PMID: 37983160 DOI: 10.1109/jbhi.2023.3334709] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/22/2023]
Abstract
Gastric cancer has a high incidence rate, significantly threatening patients' health. Gastric histopathology images can reliably diagnose related diseases. Still, the data volume of histopathology images is too large, making misdiagnosis or missed diagnosis easy. The classification model based on deep learning has made some progress on gastric histopathology images. However, traditional convolutional neural networks (CNNs) generally use pooling operations, which will reduce the spatial resolution of the image, resulting in poor prediction results. The image feature in previous CNN has a poor perception of details. Therefore, we design a dilated CNN with a late fusion strategy (DCNNLFS) for gastric histopathology image classification. The DCNNLFS model utilizes dilated convolutions, enabling it to expand the receptive field. The dilated convolutions can learn the different contextual information by adjusting the dilation rate. The DCNNLFS model uses a late fusion strategy to enhance the classification ability of DCNNLFS. We run related experiments on a gastric histopathology image dataset to verify the excellence of the DCNNLFS model, where the three metrics Precision, Accuracy, and F1-Score are 0.938, 0.935, and 0.959.
Collapse
|
|
13
|
Zhou X, Gao F, Xu G, Puyang Y, Rui H, Li J. SIAH1 facilitates the migration and invasion of gastric cancer cells through promoting the ubiquitination and degradation of RECK. Heliyon 2024; 10:e32676. [PMID: 38961977 PMCID: PMC11219971 DOI: 10.1016/j.heliyon.2024.e32676] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/07/2023] [Revised: 06/06/2024] [Accepted: 06/06/2024] [Indexed: 07/05/2024] Open
Abstract
Siah E3 ubiquitin protein ligase 1 (SIAH1) has been reported to participate in the development of several human cancers, including gastric cancer. However, the effect and mechanism of SIAH1 on the migration and invasion of gastric cancer cells need be further explored. Here, we first analyzed the clinical value of SIAH1 in gastric cancer, and found that SIAH1 was up-regulated in gastric cancer and associated with a poor prognosis. In addition, silencing of SIAH1 significantly inhibited the migration and invasion of gastric cancer cells through inhibiting the expression of matrix metalloproteinase-9 (MMP9), while overexpression of SIAH1 had the opposite effect. Molecularly, we provided the evidence that reversion-inducing cysteine-rich protein with Kazal motifs (RECK) was a potential substrate of SIAH1. We determined that SIAH1 could destabilize RECK through promoting its ubiquitination and degradation via proteasome pathway. We also found RECK was involved in SIAH1-regulated gastric cancer cell migration and invasion. In conclusion, SIAH1 is up-regulated in gastric cancer, which promotes the migration and invasion of gastric cancer cells through regulating RECK-MMP9 pathway.
Collapse
Affiliation(s)
- Xiaohua Zhou
- School of Medicine, Southeast University, China
- Department of General Surgery, Nanjing Gaochun People's Hospital, China
| | - Fuping Gao
- Department of Pathology, Nanjing Gaochun People's Hospital, China
| | - Guangqi Xu
- Department of General Surgery, Nanjing Gaochun People's Hospital, China
| | - Yongqiang Puyang
- Department of General Surgery, Nanjing Gaochun People's Hospital, China
| | - Hongqing Rui
- Department of General Surgery, Nanjing Gaochun People's Hospital, China
| | - Junsheng Li
- School of Medicine, Southeast University, China
- Department of General Surgery, Affiliated Zhongda Hospital of Southeast University, China
| |
Collapse
|
|
14
|
Xie Y, Sang Q, Da Q, Niu G, Deng S, Feng H, Chen Y, Li YY, Liu B, Yang Y, Dai W. Improving diagnosis and outcome prediction of gastric cancer via multimodal learning using whole slide pathological images and gene expression. Artif Intell Med 2024; 152:102871. [PMID: 38685169 DOI: 10.1016/j.artmed.2024.102871] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/25/2023] [Revised: 03/08/2024] [Accepted: 04/15/2024] [Indexed: 05/02/2024]
Abstract
For the diagnosis and outcome prediction of gastric cancer (GC), machine learning methods based on whole slide pathological images (WSIs) have shown promising performance and reduced the cost of manual analysis. Nevertheless, accurate prediction of GC outcome may rely on multiple modalities with complementary information, particularly gene expression data. Thus, there is a need to develop multimodal learning methods to enhance prediction performance. In this paper, we collect a dataset from Ruijin Hospital and propose a multimodal learning method for GC diagnosis and outcome prediction, called GaCaMML, which is featured by a cross-modal attention mechanism and Per-Slide training scheme. Additionally, we perform feature attribution analysis via integrated gradient (IG) to identify important input features. The proposed method improves prediction accuracy over the single-modal learning method on three tasks, i.e., survival prediction (by 4.9% on C-index), pathological stage classification (by 11.6% on accuracy), and lymph node classification (by 12.0% on accuracy). Especially, the Per-Slide strategy addresses the issue of a high WSI-to-patient ratio and leads to much better results compared with the Per-Person training scheme. For the interpretable analysis, we find that although WSIs dominate the prediction for most samples, there is still a substantial portion of samples whose prediction highly relies on gene expression information. This study demonstrates the great potential of multimodal learning in GC-related prediction tasks and investigates the contribution of WSIs and gene expression, respectively, which not only shows how the model makes a decision but also provides insights into the association between macroscopic pathological phenotypes and microscopic molecular features.
Collapse
Affiliation(s)
- Yuzhang Xie
- Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, 200240, China
| | - Qingqing Sang
- Department of General Surgery, Shanghai Key Laboratory of Gastric Neoplasm, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, 200025, China
| | - Qian Da
- Department of Pathology, Ruijin Hospital, Shanghai Jiaotong University School of Medicine, Shanghai, 200025, China
| | - Guoshuai Niu
- Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, 200240, China
| | - Shijie Deng
- Department of Pathology, Ruijin Hospital, Shanghai Jiaotong University School of Medicine, Shanghai, 200025, China
| | - Haoran Feng
- Department of General Surgery, Shanghai Key Laboratory of Gastric Neoplasm, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, 200025, China
| | - Yunqin Chen
- Shanghai-MOST Key Laboratory of Health and Disease Genomics, Shanghai Institute for Biomedical and Pharmaceutical Technologies, Shanghai 200237, China; Shanghai Engineering Research Center of Pharmaceutical Translation, Shanghai, 201203, China
| | - Yuan-Yuan Li
- Shanghai-MOST Key Laboratory of Health and Disease Genomics, Shanghai Institute for Biomedical and Pharmaceutical Technologies, Shanghai 200237, China; Shanghai Engineering Research Center of Pharmaceutical Translation, Shanghai, 201203, China
| | - Bingya Liu
- Department of General Surgery, Shanghai Key Laboratory of Gastric Neoplasm, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, 200025, China.
| | - Yang Yang
- Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, 200240, China.
| | - Wentao Dai
- Department of General Surgery, Shanghai Key Laboratory of Gastric Neoplasm, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, 200025, China; Shanghai-MOST Key Laboratory of Health and Disease Genomics, Shanghai Institute for Biomedical and Pharmaceutical Technologies, Shanghai 200237, China; Shanghai Engineering Research Center of Pharmaceutical Translation, Shanghai, 201203, China.
| |
Collapse
|
|
15
|
Qi JH, Huang SL, Jin SZ. Novel milestones for early esophageal carcinoma: From bench to bed. World J Gastrointest Oncol 2024; 16:1104-1118. [PMID: 38660637 PMCID: PMC11037034 DOI: 10.4251/wjgo.v16.i4.1104] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 12/15/2023] [Revised: 01/28/2024] [Accepted: 02/26/2024] [Indexed: 04/10/2024] Open
Abstract
Esophageal cancer (EC) is the seventh most common cancer worldwide, and esophageal squamous cell carcinoma (ESCC) accounts for the majority of cases of EC. To effectively diagnose and treat ESCC and improve patient prognosis, timely diagnosis in the initial phase of the illness is necessary. This article offers a detailed summary of the latest advancements and emerging technologies in the timely identification of ECs. Molecular biology and epigenetics approaches involve the use of molecular mechanisms combined with fluorescence quantitative polymerase chain reaction (qPCR), high-throughput sequencing technology (next-generation sequencing), and digital PCR technology to study endogenous or exogenous biomolecular changes in the human body and provide a decision-making basis for the diagnosis, treatment, and prognosis of diseases. The investigation of the microbiome is a swiftly progressing area in human cancer research, and microorganisms with complex functions are potential components of the tumor microenvironment. The intratumoral microbiota was also found to be connected to tumor progression. The application of endoscopy as a crucial technique for the early identification of ESCC has been essential, and with ongoing advancements in technology, endoscopy has continuously improved. With the advancement of artificial intelligence (AI) technology, the utilization of AI in the detection of gastrointestinal tumors has become increasingly prevalent. The implementation of AI can effectively resolve the discrepancies among observers, improve the detection rate, assist in predicting the depth of invasion and differentiation status, guide the pericancerous margins, and aid in a more accurate diagnosis of ESCC.
Collapse
Affiliation(s)
- Ji-Han Qi
- Department of Gastroenterology and Hepatology, The Second Affiliated Hospital of Harbin Medical University, Harbin 150086, Heilongjiang Province, China
| | - Shi-Ling Huang
- Department of Gastroenterology and Hepatology, The Second Affiliated Hospital of Harbin Medical University, Harbin 150086, Heilongjiang Province, China
| | - Shi-Zhu Jin
- Department of Gastroenterology and Hepatology, The Second Affiliated Hospital of Harbin Medical University, Harbin 150086, Heilongjiang Province, China
| |
Collapse
|
|
16
|
Ma H, Huang H, Li C, Li S, Gan J, Lian C, Ling Y. The antidepressive mechanism of Longya Lilium combined with Fluoxetine in mice with depression-like behaviors. NPJ Syst Biol Appl 2024; 10:5. [PMID: 38218856 PMCID: PMC10787738 DOI: 10.1038/s41540-024-00329-5] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/05/2023] [Accepted: 01/02/2024] [Indexed: 01/15/2024] Open
Abstract
Traditional Chinese medicine is one of the most commonly used complementary and alternative medicine therapies for depression. Integrated Chinese-western therapies have been extensively applied in numerous diseases due to their superior efficiency in individual treatment. We used the meta-analysis, network pharmacology, and bioinformatics studies to identify the putative role of Longya Lilium combined with Fluoxetine in depression. Depression-like behaviors were mimicked in mice after exposure to the chronic unpredictable mild stress (CUMS). The underlying potential mechanism of this combination therapy was further explored based on in vitro and in vivo experiments to analyze the expression of COX-2, PGE2, and IL-22, activation of microglial cells, and neuron viability and apoptosis in the hippocampus. The antidepressant effect was noted for the combination of Longya Lilium with Fluoxetine in mice compared to a single treatment. COX-2 was mainly expressed in hippocampal CA1 areas. Longya Lilium combined with Fluoxetine reduced the expression of COX-2 and thus alleviated depression-like behavior and neuroinflammation in mice. A decrease of COX-2 curtailed BV-2 microglial cell activation, inflammation, and neuron apoptosis by blunting the PGE2/IL-22 axis. Therefore, a combination of Longya Lilium with Fluoxetine inactivates the COX-2/PGE2/IL-22 axis, consequently relieving the neuroinflammatory response and the resultant depression.
Collapse
Affiliation(s)
- Huina Ma
- Department of Health, Youjiang Medical University for Nationalities, Baise, 533000, P. R. China
| | - Hehua Huang
- Department of Human Anatomy, Youjiang Medical University for Nationalities, Baise, 533000, P. R. China
| | - Chenyu Li
- Department of Human Anatomy, Youjiang Medical University for Nationalities, Baise, 533000, P. R. China
| | - Shasha Li
- Department of Human Anatomy, Youjiang Medical University for Nationalities, Baise, 533000, P. R. China
| | - Juefang Gan
- Department of Human Anatomy, Youjiang Medical University for Nationalities, Baise, 533000, P. R. China
| | - Chunrong Lian
- Department of Human Anatomy, Youjiang Medical University for Nationalities, Baise, 533000, P. R. China
| | - Yanwu Ling
- Department of Human Anatomy, Youjiang Medical University for Nationalities, Baise, 533000, P. R. China.
| |
Collapse
|
|
17
|
Evans H, Snead D. Why do errors arise in artificial intelligence diagnostic tools in histopathology and how can we minimize them? Histopathology 2024; 84:279-287. [PMID: 37921030 DOI: 10.1111/his.15071] [Citation(s) in RCA: 11] [Impact Index Per Article: 11.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/15/2023] [Revised: 09/22/2023] [Accepted: 09/27/2023] [Indexed: 11/04/2023]
Abstract
Artificial intelligence (AI)-based diagnostic tools can offer numerous benefits to the field of histopathology, including improved diagnostic accuracy, efficiency and productivity. As a result, such tools are likely to have an increasing role in routine practice. However, all AI tools are prone to errors, and these AI-associated errors have been identified as a major risk in the introduction of AI into healthcare. The errors made by AI tools are different, in terms of both cause and nature, to the errors made by human pathologists. As highlighted by the National Institute for Health and Care Excellence, it is imperative that practising pathologists understand the potential limitations of AI tools, including the errors made. Pathologists are in a unique position to be gatekeepers of AI tool use, maximizing patient benefit while minimizing harm. Furthermore, their pathological knowledge is essential to understanding when, and why, errors have occurred and so to developing safer future algorithms. This paper summarises the literature on errors made by AI diagnostic tools in histopathology. These include erroneous errors, data concerns (data bias, hidden stratification, data imbalances, distributional shift, and lack of generalisability), reinforcement of outdated practices, unsafe failure mode, automation bias, and insensitivity to impact. Methods to reduce errors in both tool design and clinical use are discussed, and the practical roles for pathologists in error minimisation are highlighted. This aims to inform and empower pathologists to move safely through this seismic change in practice and help ensure that novel AI tools are adopted safely.
Collapse
Affiliation(s)
- Harriet Evans
- Histopathology Department, University Hospitals Coventry and Warwickshire NHS Trust, Coventry, UK
- Warwick Medical School, University of Warwick, Coventry, UK
| | - David Snead
- Histopathology Department, University Hospitals Coventry and Warwickshire NHS Trust, Coventry, UK
- Warwick Medical School, University of Warwick, Coventry, UK
| |
Collapse
|
|
18
|
Orășeanu A, Brisc MC, Maghiar OA, Popa H, Brisc CM, Șolea SF, Maghiar TA, Brisc C. Landscape of Innovative Methods for Early Diagnosis of Gastric Cancer: A Systematic Review. Diagnostics (Basel) 2023; 13:3608. [PMID: 38132192 PMCID: PMC10742893 DOI: 10.3390/diagnostics13243608] [Citation(s) in RCA: 8] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/31/2023] [Revised: 11/28/2023] [Accepted: 12/01/2023] [Indexed: 12/23/2023] Open
Abstract
From a global perspective, gastric cancer (GC) persists as a significant healthcare issue. In the Western world, the majority of cases are discovered at late stages, when the treatment is generally unsuccessful. There are no organized screening programs outside of Asia (Japan and Republic of Korea). Traditional diagnosis techniques (such as upper endoscopy), conventional tumor markers (CEA, CA19-9, and CA72-4), radiographic imaging, and CT scanning all have drawbacks. The gold standard for the earliest detection of cancer and related premalignant lesions is still endoscopy with a proper biopsy follow-up. Since there are currently no clinically approved biomarkers for the early diagnosis of GC, the identification of non-invasive biomarkers is expected to help improve the prognosis and survival rate of these patients. The search for new screening biomarkers is currently underway. These include genetic biomarkers, such as circulating tumor cells, microRNAs, and exosomes, as well as metabolic biomarkers obtained from biofluids. Meanwhile, cutting-edge high-resolution endoscopic technologies are demonstrating promising outcomes in the visual diagnosis of mucosal lesions with the aid of linked color imaging and machine learning models. Following the PRISMA guidelines, this study examined the articles in databases such as PubMed, resulting in 167 included articles. This review discusses the currently available and emerging methods for diagnosing GC early on, as well as new developments in the endoscopic detection of early lesions of the stomach.
Collapse
Affiliation(s)
- Alexandra Orășeanu
- Clinic of Gastroenterology, Bihor Clinical County Emergency Hospital, 410169 Oradea, Romania; (A.O.); (S.F.Ș.)
- Doctoral School of Biomedical Sciences, University of Oradea, 410087 Oradea, Romania; (O.A.M.); (T.A.M.); (C.B.)
| | | | - Octavian Adrian Maghiar
- Doctoral School of Biomedical Sciences, University of Oradea, 410087 Oradea, Romania; (O.A.M.); (T.A.M.); (C.B.)
- Faculty of Medicine and Pharmacy, University of Oradea, 410068 Oradea, Romania;
| | - Horia Popa
- Clinical Emergency Hospital “Prof. Dr. Agrippa Ionescu”, 011356 Bucharest, Romania;
| | - Ciprian Mihai Brisc
- Faculty of Medicine and Pharmacy, University of Oradea, 410068 Oradea, Romania;
| | - Sabina Florina Șolea
- Clinic of Gastroenterology, Bihor Clinical County Emergency Hospital, 410169 Oradea, Romania; (A.O.); (S.F.Ș.)
- Doctoral School of Biomedical Sciences, University of Oradea, 410087 Oradea, Romania; (O.A.M.); (T.A.M.); (C.B.)
| | - Teodor Andrei Maghiar
- Doctoral School of Biomedical Sciences, University of Oradea, 410087 Oradea, Romania; (O.A.M.); (T.A.M.); (C.B.)
- Faculty of Medicine and Pharmacy, University of Oradea, 410068 Oradea, Romania;
| | - Ciprian Brisc
- Doctoral School of Biomedical Sciences, University of Oradea, 410087 Oradea, Romania; (O.A.M.); (T.A.M.); (C.B.)
- Faculty of Medicine and Pharmacy, University of Oradea, 410068 Oradea, Romania;
| |
Collapse
|
|
19
|
Su Y, Li Y, Chen W, Yang W, Qin J, Liu L. Automated machine learning-based model for predicting benign anastomotic strictures in patients with rectal cancer who have received anterior resection. EUROPEAN JOURNAL OF SURGICAL ONCOLOGY 2023; 49:107113. [PMID: 37857102 DOI: 10.1016/j.ejso.2023.107113] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/24/2023] [Revised: 09/26/2023] [Accepted: 10/08/2023] [Indexed: 10/21/2023]
Abstract
BACKGROUND Benign anastomotic strictures (BAS) significantly impact patients' quality of life and long-term prognosis. However, the current clinical practice lacks accurate tools for predicting BAS. This study aimed to develop a machine-learning model to predict BAS in patients with rectal cancer who have undergone anterior resection. METHODS Data from 1973 patients who underwent anterior resection for rectal cancer were collected. Multiple machine learning classification models were integrated to analyze the data and identify the optimal model. Model performance was evaluated using receiver operator characteristic (ROC) curves, decision curve analysis (DCA), and calibration curves. The Shapley Additive exPlanation (SHAP) algorithm was utilized to assess the impact of various clinical characteristics on the optimal model to enhance the interpretability of the model results. RESULTS A total of 10 clinical features were considered in constructing the machine learning model. The model evaluation results indicated that the random forest (RF)model was optimal, with the area under the test set curve (AUC: 0.888, 95% CI: 0.810-0.965), accuracy: 0.792, sensitivity: 0.846, specificity: 0.791. The SHAP algorithm analysis identified prophylactic ileostomy, operative time, and anastomotic leakage as significant contributing factors influencing the predictions of the RF model. CONCLUSION We developed a robust machine-learning model and user-friendly online prediction tool for predicting BAS following anterior resection of rectal cancer. This tool offers a potential foundation for BAS prevention and aids clinical practice by enabling more efficient disease management and precise medical interventions.
Collapse
Affiliation(s)
- Yang Su
- Department of Gastrointestinal Surgery Center, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, 430030, China; Molecular Medicine Center, Tongi Hospita, Tongi Medical College, Huazhong University of Science and Technology, 430030, Wuhan, China.
| | - Yanqi Li
- Department of Gastrointestinal Surgery Center, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, 430030, China; Molecular Medicine Center, Tongi Hospita, Tongi Medical College, Huazhong University of Science and Technology, 430030, Wuhan, China.
| | - Wenshu Chen
- School of Computer Science(National Pilot Software Engineering School), Beijing University of Posts and Telecommunication, 100876, Beijing, China.
| | - Wangshuo Yang
- Department of Gastrointestinal Surgery Center, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, 430030, China; Molecular Medicine Center, Tongi Hospita, Tongi Medical College, Huazhong University of Science and Technology, 430030, Wuhan, China.
| | - Jichao Qin
- Department of Gastrointestinal Surgery Center, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, 430030, China; Molecular Medicine Center, Tongi Hospita, Tongi Medical College, Huazhong University of Science and Technology, 430030, Wuhan, China.
| | - Lu Liu
- Department of Gastrointestinal Surgery Center, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, 430030, China; Molecular Medicine Center, Tongi Hospita, Tongi Medical College, Huazhong University of Science and Technology, 430030, Wuhan, China.
| |
Collapse
|
|
20
|
Hayashi T, Takasawa K, Yoshikawa T, Hashimoto T, Sekine S, Wada T, Yamagata Y, Suzuki H, Abe S, Yoshinaga S, Saito Y, Kouno N, Hamamoto R. A discrimination model by machine learning to avoid gastrectomy for early gastric cancer. Ann Gastroenterol Surg 2023; 7:913-921. [PMID: 37927931 PMCID: PMC10623978 DOI: 10.1002/ags3.12714] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 03/19/2023] [Revised: 06/21/2023] [Accepted: 06/27/2023] [Indexed: 11/07/2023] Open
Abstract
Aim Gastrectomy is recommended for patients with early gastric cancer (EGC) because the possibility of lymph node metastasis (LNM) cannot be completely denied. The aim of this study was to develop a discrimination model to select patients who do not require surgery using machine learning. Methods Data from 382 patients who received gastrectomy for gastric cancer and who were diagnosed with pT1b were extracted for developing a discrimination model. For the validation of this discrimination model, data from 140 consecutive patients who underwent endoscopic resection followed by gastrectomy, with a diagnosis of pT1b EGC, were extracted. We applied XGBoost to develop a discrimination model for clinical and pathological variables. The performance of the discrimination model was evaluated based on the number of cases classified as true negatives for LNM, with no false negatives for LNM allowed. Results Lymph node metastasis was observed in 95 patients (25%) in the development cohort and 11 patients (8%) in the validation cohort. The discrimination model was developed to identify 27 (7%) patients with no indications for additional surgery due to the prediction of an LNM-negative status with no false negatives. In the validation cohort, 13 (9%) patients were identified as having no indications for additional surgery and no patients with LNM were classified into this group. Conclusion The discrimination model using XGBoost algorithms could select patients with no risk of LNM from patients with pT1b EGC. This discrimination model was considered promising for clinical decision-making in relation to patients with EGC.
Collapse
Affiliation(s)
- Tsutomu Hayashi
- Department of Gastric SurgeryNational Cancer Center HospitalTokyoJapan
| | - Ken Takasawa
- Division of Medical AI Research and DevelopmentNational Cancer Center Research InstituteTokyoJapan
- Cancer Translational Research Team, RIKEN Center for Advanced Intelligence ProjectTokyoJapan
| | - Takaki Yoshikawa
- Department of Gastric SurgeryNational Cancer Center HospitalTokyoJapan
| | - Taiki Hashimoto
- Department of Diagnostic PathologyNational Cancer Center HospitalTokyoJapan
| | - Shigeki Sekine
- Department of Diagnostic PathologyNational Cancer Center HospitalTokyoJapan
| | - Takeyuki Wada
- Department of Gastric SurgeryNational Cancer Center HospitalTokyoJapan
| | - Yukinori Yamagata
- Department of Gastric SurgeryNational Cancer Center HospitalTokyoJapan
| | | | - Seiichirou Abe
- Endoscopy DivisionNational Cancer Center HospitalTokyoJapan
| | | | - Yutaka Saito
- Endoscopy DivisionNational Cancer Center HospitalTokyoJapan
| | - Nobuji Kouno
- Division of Medical AI Research and DevelopmentNational Cancer Center Research InstituteTokyoJapan
| | - Ryuji Hamamoto
- Division of Medical AI Research and DevelopmentNational Cancer Center Research InstituteTokyoJapan
- Cancer Translational Research Team, RIKEN Center for Advanced Intelligence ProjectTokyoJapan
| |
Collapse
|
|
21
|
Popovic D, Glisic T, Milosavljevic T, Panic N, Marjanovic-Haljilji M, Mijac D, Stojkovic Lalosevic M, Nestorov J, Dragasevic S, Savic P, Filipovic B. The Importance of Artificial Intelligence in Upper Gastrointestinal Endoscopy. Diagnostics (Basel) 2023; 13:2862. [PMID: 37761229 PMCID: PMC10528171 DOI: 10.3390/diagnostics13182862] [Citation(s) in RCA: 6] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/30/2023] [Revised: 08/28/2023] [Accepted: 09/01/2023] [Indexed: 09/16/2023] Open
Abstract
Recently, there has been a growing interest in the application of artificial intelligence (AI) in medicine, especially in specialties where visualization methods are applied. AI is defined as a computer's ability to achieve human cognitive performance, which is accomplished through enabling computer "learning". This can be conducted in two ways, as machine learning and deep learning. Deep learning is a complex learning system involving the application of artificial neural networks, whose algorithms imitate the human form of learning. Upper gastrointestinal endoscopy allows examination of the esophagus, stomach and duodenum. In addition to the quality of endoscopic equipment and patient preparation, the performance of upper endoscopy depends on the experience and knowledge of the endoscopist. The application of artificial intelligence in endoscopy refers to computer-aided detection and the more complex computer-aided diagnosis. The application of AI in upper endoscopy is aimed at improving the detection of premalignant and malignant lesions, with special attention on the early detection of dysplasia in Barrett's esophagus, the early detection of esophageal and stomach cancer and the detection of H. pylori infection. Artificial intelligence reduces the workload of endoscopists, is not influenced by human factors and increases the diagnostic accuracy and quality of endoscopic methods.
Collapse
Affiliation(s)
- Dusan Popovic
- Faculty of Medicine Belgrade, University of Belgrade, 11000 Belgrade, Serbia; (T.G.); (D.M.); (M.S.L.); (J.N.); (S.D.); (P.S.); (B.F.)
- Department of Gastroenterology, Clinical Hospital Center “Dr Dragisa Misovic-Dedinje”, 11000 Belgrade, Serbia; (N.P.); (M.M.-H.)
| | - Tijana Glisic
- Faculty of Medicine Belgrade, University of Belgrade, 11000 Belgrade, Serbia; (T.G.); (D.M.); (M.S.L.); (J.N.); (S.D.); (P.S.); (B.F.)
- Clinic for Gastroenterohepatology, University Clinical Centre of Serbia, 11000 Belgrade, Serbia
| | | | - Natasa Panic
- Department of Gastroenterology, Clinical Hospital Center “Dr Dragisa Misovic-Dedinje”, 11000 Belgrade, Serbia; (N.P.); (M.M.-H.)
| | - Marija Marjanovic-Haljilji
- Department of Gastroenterology, Clinical Hospital Center “Dr Dragisa Misovic-Dedinje”, 11000 Belgrade, Serbia; (N.P.); (M.M.-H.)
| | - Dragana Mijac
- Faculty of Medicine Belgrade, University of Belgrade, 11000 Belgrade, Serbia; (T.G.); (D.M.); (M.S.L.); (J.N.); (S.D.); (P.S.); (B.F.)
- Clinic for Gastroenterohepatology, University Clinical Centre of Serbia, 11000 Belgrade, Serbia
| | - Milica Stojkovic Lalosevic
- Faculty of Medicine Belgrade, University of Belgrade, 11000 Belgrade, Serbia; (T.G.); (D.M.); (M.S.L.); (J.N.); (S.D.); (P.S.); (B.F.)
- Clinic for Gastroenterohepatology, University Clinical Centre of Serbia, 11000 Belgrade, Serbia
| | - Jelena Nestorov
- Faculty of Medicine Belgrade, University of Belgrade, 11000 Belgrade, Serbia; (T.G.); (D.M.); (M.S.L.); (J.N.); (S.D.); (P.S.); (B.F.)
- Clinic for Gastroenterohepatology, University Clinical Centre of Serbia, 11000 Belgrade, Serbia
| | - Sanja Dragasevic
- Faculty of Medicine Belgrade, University of Belgrade, 11000 Belgrade, Serbia; (T.G.); (D.M.); (M.S.L.); (J.N.); (S.D.); (P.S.); (B.F.)
- Clinic for Gastroenterohepatology, University Clinical Centre of Serbia, 11000 Belgrade, Serbia
| | - Predrag Savic
- Faculty of Medicine Belgrade, University of Belgrade, 11000 Belgrade, Serbia; (T.G.); (D.M.); (M.S.L.); (J.N.); (S.D.); (P.S.); (B.F.)
- Clinic for Surgery, Clinical Hospital Center “Dr Dragisa Misovic-Dedinje”, 11000 Belgrade, Serbia
| | - Branka Filipovic
- Faculty of Medicine Belgrade, University of Belgrade, 11000 Belgrade, Serbia; (T.G.); (D.M.); (M.S.L.); (J.N.); (S.D.); (P.S.); (B.F.)
- Department of Gastroenterology, Clinical Hospital Center “Dr Dragisa Misovic-Dedinje”, 11000 Belgrade, Serbia; (N.P.); (M.M.-H.)
| |
Collapse
|
|
22
|
Ruiz-Fresneda MA, Gijón A, Morales-Álvarez P. Bibliometric analysis of the global scientific production on machine learning applied to different cancer types. ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH INTERNATIONAL 2023; 30:96125-96137. [PMID: 37566331 PMCID: PMC10482761 DOI: 10.1007/s11356-023-28576-9] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 01/27/2023] [Accepted: 06/29/2023] [Indexed: 08/12/2023]
Abstract
Cancer disease is one of the main causes of death in the world, with million annual cases in the last decades. The need to find a cure has stimulated the search for efficient treatments and diagnostic procedures. One of the most promising tools that has emerged against cancer in recent years is machine learning (ML), which has raised a huge number of scientific papers published in a relatively short period of time. The present study analyzes global scientific production on ML applied to the most relevant cancer types through various bibliometric indicators. We find that over 30,000 studies have been published so far and observe that cancers with the highest number of published studies using ML (breast, lung, and colon cancer) are those with the highest incidence, being the USA and China the main scientific producers on the subject. Interestingly, the role of China and Japan in stomach cancer is correlated with the number of cases of this cancer type in Asia (78% of the worldwide cases). Knowing the countries and institutions that most study each area can be of great help for improving international collaborations between research groups and countries. Our analysis shows that medical and computer science journals lead the number of publications on the subject and could be useful for researchers in the field. Finally, keyword co-occurrence analysis suggests that ML-cancer research trends are focused not only on the use of ML as an effective diagnostic method, but also for the improvement of radiotherapy- and chemotherapy-based treatments.
Collapse
Affiliation(s)
| | - Alfonso Gijón
- Department of Computer Science and Artificial Intelligence, University of Granada, Granada, Spain
- Research Centre for Information and Communication Technologies (CITIC-UGR), University of Granada, Granada, Spain
| | - Pablo Morales-Álvarez
- Research Centre for Information and Communication Technologies (CITIC-UGR), University of Granada, Granada, Spain
- Department of Statistics and Operations Research, University of Granada, Granada, Spain
| |
Collapse
|
|
23
|
Kiran N, Sapna F, Kiran F, Kumar D, Raja F, Shiwlani S, Paladini A, Sonam F, Bendari A, Perkash RS, Anjali F, Varrassi G. Digital Pathology: Transforming Diagnosis in the Digital Age. Cureus 2023; 15:e44620. [PMID: 37799211 PMCID: PMC10547926 DOI: 10.7759/cureus.44620] [Citation(s) in RCA: 8] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/18/2023] [Accepted: 09/03/2023] [Indexed: 10/07/2023] Open
Abstract
In the context of rapid technological advancements, the narrative review titled "Digital Pathology: Transforming Diagnosis in the Digital Age" explores the significant impact of digital pathology in reshaping diagnostic approaches. This review delves into the various effects of the field, including remote consultations and artificial intelligence (AI)-assisted analysis, revealing the ongoing transformation taking place. The investigation explores the process of digitizing traditional glass slides, which aims to improve accessibility and facilitate sharing. Additionally, it addresses the complexities associated with data security and standardization challenges. Incorporating AI enhances pathologists' diagnostic capabilities and accelerates analytical procedures. Furthermore, the review highlights the growing importance of collaborative networks facilitating global knowledge sharing. It also emphasizes the significant impact of this technology on medical education and patient care. This narrative review aims to provide an overview of digital pathology's transformative and innovative potential, highlighting its disruptive nature in reshaping diagnostic practices.
Collapse
Affiliation(s)
- Nfn Kiran
- Pathology and Laboratory Medicine, Staten Island University Hospital, New York, USA
| | - Fnu Sapna
- Pathology and Laboratory Medicine, Albert Einstein College of Medicine, New York, USA
| | - Fnu Kiran
- Pathology and Laboratory Medicine, University of Missouri School of Medicine, Columbia, USA
| | - Deepak Kumar
- Pathology and Laboratory Medicine, University of Missouri, Columbia, USA
| | - Fnu Raja
- Pathology and Laboratory Medicine, MetroHealth Medical Center, Cleveland, USA
| | - Sheena Shiwlani
- Pathology and Laboratory Medicine, Isra University, Karachi, PAK
- Pathology, Mount Sinai Hospital, New York, USA
| | - Antonella Paladini
- Clinical Medicine, Public Health and Life Science (MESVA), University of L'Aquila, L'Aquila, ITA
| | - Fnu Sonam
- Pathology and Laboratory Medicine, Liaquat University of Medical and Health Sciences, Sukkur, PAK
- Medicine, Mustafai Trust Central Hospital, Sukkur, PAK
| | - Ahmed Bendari
- Pathology and Laboratory Medicine, Lenox Hill Hospital, New York, USA
| | | | - Fnu Anjali
- Internal Medicine, Sakhi Baba General Hospital, Sukkur, PAK
| | | |
Collapse
|
|
24
|
Martos O, Hoque MZ, Keskinarkaus A, Kemi N, Näpänkangas J, Eskuri M, Pohjanen VM, Kauppila JH, Seppänen T. Optimized detection and segmentation of nuclei in gastric cancer images using stain normalization and blurred artifact removal. Pathol Res Pract 2023; 248:154694. [PMID: 37494804 DOI: 10.1016/j.prp.2023.154694] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 02/04/2023] [Revised: 07/03/2023] [Accepted: 07/13/2023] [Indexed: 07/28/2023]
Abstract
Histological analysis with microscopy is the gold standard to diagnose and stage cancer, where slides or whole slide images are analyzed for cell morphological and spatial features by pathologists. The nuclei of cancerous cells are characterized by nonuniform chromatin distribution, irregular shapes, and varying size. As nucleus area and shape alone carry prognostic value, detection and segmentation of nuclei are among the most important steps in disease grading. However, evaluation of nuclei is a laborious, time-consuming, and subjective process with large variation among pathologists. Recent advances in digital pathology have allowed significant applications in nuclei detection, segmentation, and classification, but automated image analysis is greatly affected by staining factors, scanner variability, and imaging artifacts, requiring robust image preprocessing, normalization, and segmentation methods for clinically satisfactory results. In this paper, we aimed to evaluate and compare the digital image analysis techniques used in clinical pathology and research in the setting of gastric cancer. A literature review was conducted to evaluate potential methods of improving nuclei detection. Digitized images of 35 patients from a retrospective cohort of gastric adenocarcinoma at Oulu University Hospital in 1987-2016 were annotated for nuclei (n = 9085) by expert pathologists and 14 images of different cancer types from public TCGA dataset with annotated nuclei (n = 7000) were used as a comparison to evaluate applicability in other cancer types. The detection and segmentation accuracy with the selected color normalization and stain separation techniques were compared between the methods. The extracted information can be supplemented by patient's medical data and fed to the existing statistical clinical tools or subjected to subsequent AI-assisted classification and prediction models. The performance of each method is evaluated by several metrics against the annotations done by expert pathologists. The F1-measure of 0.854 ± 0.068 is achieved with color normalization for the gastric cancer dataset, and 0.907 ± 0.044 with color deconvolution for the public dataset, showing comparable results to the earlier state-of-the-art works. The developed techniques serve as a basis for further research on application and interpretability of AI-assisted tools for gastric cancer diagnosis.
Collapse
Affiliation(s)
- Oleg Martos
- Center for Machine Vision and Signal Analysis, Faculty of Information Technology and Electrical Engineering, University of Oulu, Finland
| | - Md Ziaul Hoque
- Center for Machine Vision and Signal Analysis, Faculty of Information Technology and Electrical Engineering, University of Oulu, Finland.
| | - Anja Keskinarkaus
- Center for Machine Vision and Signal Analysis, Faculty of Information Technology and Electrical Engineering, University of Oulu, Finland
| | - Niko Kemi
- Department of Pathology, Oulu University Hospital, Finland, and University of Oulu, Finland
| | - Juha Näpänkangas
- Department of Pathology, Oulu University Hospital, Finland, and University of Oulu, Finland
| | - Maarit Eskuri
- Department of Pathology, Oulu University Hospital, Finland, and University of Oulu, Finland
| | - Vesa-Matti Pohjanen
- Department of Pathology, Oulu University Hospital, Finland, and University of Oulu, Finland
| | - Joonas H Kauppila
- Department of Surgery, Oulu University Hospital, Finland, and University of Oulu, Finland
| | - Tapio Seppänen
- Center for Machine Vision and Signal Analysis, Faculty of Information Technology and Electrical Engineering, University of Oulu, Finland
| |
Collapse
|
|
25
|
SenthilKumar G, Madhusudhana S, Flitcroft M, Sheriff S, Thalji S, Merrill J, Clarke CN, Maduekwe UN, Tsai S, Christians KK, Gamblin TC, Kothari AN. Automated machine learning (AutoML) can predict 90-day mortality after gastrectomy for cancer. Sci Rep 2023; 13:11051. [PMID: 37422500 PMCID: PMC10329647 DOI: 10.1038/s41598-023-37396-3] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/30/2022] [Accepted: 06/21/2023] [Indexed: 07/10/2023] Open
Abstract
Early postoperative mortality risk prediction is crucial for clinical management of gastric cancer. This study aims to predict 90-day mortality in gastric cancer patients undergoing gastrectomy using automated machine learning (AutoML), optimize models for preoperative prediction, and identify factors influential in prediction. National Cancer Database was used to identify stage I-III gastric cancer patients undergoing gastrectomy between 2004 and 2016. 26 features were used to train predictive models using H2O.ai AutoML. Performance on validation cohort was measured. In 39,108 patients, 90-day mortality rate was 8.8%. The highest performing model was an ensemble (AUC = 0.77); older age, nodal ratio, and length of inpatient stay (LOS) following surgery were most influential for prediction. Removing the latter two parameters decreased model performance (AUC 0.71). For optimizing models for preoperative use, models were developed to first predict node ratio or LOS, and these predicted values were inputted for 90-day mortality prediction (AUC of 0.73-0.74). AutoML performed well in predicting 90-day mortality in a larger cohort of gastric cancer patients that underwent gastrectomy. These models can be implemented preoperatively to inform prognostication and patient selection for surgery. Our study supports broader evaluation and application of AutoML to guide surgical oncologic care.
Collapse
Affiliation(s)
- Gopika SenthilKumar
- Medical Scientist Training Program, Medical College of Wisconsin, Milwaukee, USA
- Division of Surgical Oncology, Department of Surgery, Medical College of Wisconsin, 8701 Watertown Plank Road, Milwaukee, WI, 53226, USA
| | - Sharadhi Madhusudhana
- Division of Surgical Oncology, Department of Surgery, Medical College of Wisconsin, 8701 Watertown Plank Road, Milwaukee, WI, 53226, USA
| | - Madelyn Flitcroft
- Division of Surgical Oncology, Department of Surgery, Medical College of Wisconsin, 8701 Watertown Plank Road, Milwaukee, WI, 53226, USA
| | - Salma Sheriff
- Division of Surgical Oncology, Department of Surgery, Medical College of Wisconsin, 8701 Watertown Plank Road, Milwaukee, WI, 53226, USA
| | - Samih Thalji
- Division of Surgical Oncology, Department of Surgery, Medical College of Wisconsin, 8701 Watertown Plank Road, Milwaukee, WI, 53226, USA
| | - Jennifer Merrill
- Division of Surgical Oncology, Department of Surgery, Medical College of Wisconsin, 8701 Watertown Plank Road, Milwaukee, WI, 53226, USA
| | - Callisia N Clarke
- Division of Surgical Oncology, Department of Surgery, Medical College of Wisconsin, 8701 Watertown Plank Road, Milwaukee, WI, 53226, USA
| | - Ugwuji N Maduekwe
- Division of Surgical Oncology, Department of Surgery, Medical College of Wisconsin, 8701 Watertown Plank Road, Milwaukee, WI, 53226, USA
| | - Susan Tsai
- Division of Surgical Oncology, Department of Surgery, Medical College of Wisconsin, 8701 Watertown Plank Road, Milwaukee, WI, 53226, USA
| | - Kathleen K Christians
- Division of Surgical Oncology, Department of Surgery, Medical College of Wisconsin, 8701 Watertown Plank Road, Milwaukee, WI, 53226, USA
| | - T Clark Gamblin
- Division of Surgical Oncology, Department of Surgery, Medical College of Wisconsin, 8701 Watertown Plank Road, Milwaukee, WI, 53226, USA
| | - Anai N Kothari
- Division of Surgical Oncology, Department of Surgery, Medical College of Wisconsin, 8701 Watertown Plank Road, Milwaukee, WI, 53226, USA.
| |
Collapse
|
|
26
|
Kim KW, Huh J, Urooj B, Lee J, Lee J, Lee IS, Park H, Na S, Ko Y. Artificial Intelligence in Gastric Cancer Imaging With Emphasis on Diagnostic Imaging and Body Morphometry. J Gastric Cancer 2023; 23:388-399. [PMID: 37553127 PMCID: PMC10412978 DOI: 10.5230/jgc.2023.23.e30] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 07/20/2023] [Revised: 07/28/2023] [Accepted: 07/28/2023] [Indexed: 08/10/2023] Open
Abstract
Gastric cancer remains a significant global health concern, coercing the need for advancements in imaging techniques for ensuring accurate diagnosis and effective treatment planning. Artificial intelligence (AI) has emerged as a potent tool for gastric-cancer imaging, particularly for diagnostic imaging and body morphometry. This review article offers a comprehensive overview of the recent developments and applications of AI in gastric cancer imaging. We investigated the role of AI imaging in gastric cancer diagnosis and staging, showcasing its potential to enhance the accuracy and efficiency of these crucial aspects of patient management. Additionally, we explored the application of AI body morphometry specifically for assessing the clinical impact of gastrectomy. This aspect of AI utilization holds significant promise for understanding postoperative changes and optimizing patient outcomes. Furthermore, we examine the current state of AI techniques for the prognosis of patients with gastric cancer. These prognostic models leverage AI algorithms to predict long-term survival outcomes and assist clinicians in making informed treatment decisions. However, the implementation of AI techniques for gastric cancer imaging has several limitations. As AI continues to evolve, we hope to witness the translation of cutting-edge technologies into routine clinical practice, ultimately improving patient care and outcomes in the fight against gastric cancer.
Collapse
Affiliation(s)
- Kyung Won Kim
- Department of Radiology and Research Institute of Radiology, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Korea
| | - Jimi Huh
- Department of Radiology, Ajou University School of Medicine, Suwon, Korea
| | - Bushra Urooj
- Biomedical Research Center, Asan Institute for Life Sciences, Asan Medical Center, Seoul, Korea
| | - Jeongjin Lee
- School of Computer Science and Engineering, Soongsil University, Seoul, Korea
| | - Jinseok Lee
- Department of Biomedical Engineering, College of Electronics and Information, Kyung Hee University, Yongin, Korea
| | - In-Seob Lee
- Department of Surgery, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Korea
| | - Hyesun Park
- Body Imaging Department of Radiology, Lahey Hospital and Medical Center, Burlington, MA, USA
| | - Seongwon Na
- Biomedical Research Center, Asan Institute for Life Sciences, Asan Medical Center, Seoul, Korea
| | - Yousun Ko
- Department of Radiology and Research Institute of Radiology, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Korea
- Biomedical Research Center, Asan Institute for Life Sciences, Asan Medical Center, Seoul, Korea.
| |
Collapse
|
|
27
|
Liang P, Lv D, Ren XC, Cheng M, Hu ZW, Yong LL, Zhu BB, Liu MR, Gao JB. The 'double‑track sign': A novel CT finding suggestive of the diagnosis of T1a gastric cancer. Oncol Lett 2023; 26:286. [PMID: 37274467 PMCID: PMC10236118 DOI: 10.3892/ol.2023.13872] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/10/2022] [Accepted: 04/12/2023] [Indexed: 06/06/2023] Open
Abstract
Effective identification of T1a stage cancer is crucial for planning endoscopic resection for early gastric cancers. The present study aimed to determine the diagnostic value of the double-track sign in patients with T1a gastric cancer using computed tomography (CT) imaging. A total of 152 patients diagnosed with pathologically proven T1a gastric cancer at The First Affiliated Hospital of Zhengzhou University (Zhengzhou, China) between July 2011 and August 2021 were retrospectively reviewed. The control group consisted of 2,926 patients with gastritis. Clinical data, including patient characteristics and preoperative CT imaging findings with gastric morphological features, were reviewed and analyzed. Out of 51 patients with T1a gastric cancer finally included, 31 (60.8%) exhibited local double-track enhancement changes of the stomach, referred to as the 'double-track sign', on CT images. In addition, four patients (7.8%) had well-enhanced mucosal thickening of the gastric wall. Of the 2,926 control subjects, none had any double-track sign and six patients (0.2%) had local gastric wall thickening with abnormally strengthened enhancement. In conclusion, a double-track sign on CT images is beneficial in the diagnostic differentiation of T1a gastric cancer.
Collapse
Affiliation(s)
- Pan Liang
- Department of Radiology, The First Affiliated Hospital, Zhengzhou University, Zhengzhou, Henan 450052, P.R. China
| | - Dongbo Lv
- Department of Radiology, The First Affiliated Hospital, Zhengzhou University, Zhengzhou, Henan 450052, P.R. China
| | - Xiu-Chun Ren
- Department of Radiology, The First Affiliated Hospital, Zhengzhou University, Zhengzhou, Henan 450052, P.R. China
| | - Ming Cheng
- Department of Radiology, The First Affiliated Hospital, Zhengzhou University, Zhengzhou, Henan 450052, P.R. China
| | - Zhi-Wei Hu
- Department of Radiology, The First Affiliated Hospital, Zhengzhou University, Zhengzhou, Henan 450052, P.R. China
| | - Liu-Liang Yong
- Department of Radiology, The First Affiliated Hospital, Zhengzhou University, Zhengzhou, Henan 450052, P.R. China
| | - Bing-Bing Zhu
- Department of Radiology, The First Affiliated Hospital, Zhengzhou University, Zhengzhou, Henan 450052, P.R. China
| | - Meng-Ru Liu
- Department of Radiology, The First Affiliated Hospital, Zhengzhou University, Zhengzhou, Henan 450052, P.R. China
| | - Jian-Bo Gao
- Department of Radiology, The First Affiliated Hospital, Zhengzhou University, Zhengzhou, Henan 450052, P.R. China
| |
Collapse
|
|
28
|
Aziz S, König S, Umer M, Akhter TS, Iqbal S, Ibrar M, Ur-Rehman T, Ahmad T, Hanafiah A, Zahra R, Rasheed F. Risk factor profiles for gastric cancer prediction with respect to Helicobacter pylori: A study of a tertiary care hospital in Pakistan. Artif Intell Gastroenterol 2023; 4:10-27. [DOI: 10.35712/aig.v4.i1.10] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 12/14/2022] [Revised: 04/01/2023] [Accepted: 04/20/2023] [Indexed: 06/08/2023] Open
Abstract
BACKGROUND Gastric cancer (GC) is the fourth leading cause of cancer-related deaths worldwide. Diagnosis relies on histopathology and the number of endoscopies is increasing. Helicobacter pylori (H. pylori) infection is a major risk factor.
AIM To develop an in-silico GC prediction model to reduce the number of diagnostic surgical procedures. The meta-data of patients with gastroduodenal symptoms, risk factors associated with GC, and H. pylori infection status from Holy Family Hospital Rawalpindi, Pakistan, were used with machine learning.
METHODS A cohort of 341 patients was divided into three groups [normal gastric mucosa (NGM), gastroduodenal diseases (GDD), and GC]. Information associated with socioeconomic and demographic conditions and GC risk factors was collected using a questionnaire. H. pylori infection status was determined based on urea breath test. The association of these factors and histopathological grades was assessed statistically. K-Nearest Neighbors and Random Forest (RF) machine learning models were tested.
RESULTS This study reported an overall frequency of 64.2% (219/341) of H. pylori infection among enrolled subjects. It was higher in GC (74.2%, 23/31) as compared to NGM and GDD and higher in males (54.3%, 119/219) as compared to females. More abdominal pain (72.4%, 247/341) was observed than other clinical symptoms including vomiting, bloating, acid reflux and heartburn. The majority of the GC patients experienced symptoms of vomiting (91%, 20/22) with abdominal pain (100%, 22/22). The multinomial logistic regression model was statistically significant and correctly classified 80% of the GDD/GC cases. Age, income level, vomiting, bloating and medication had significant association with GDD and GC. A dynamic RF GC-predictive model was developed, which achieved > 80% test accuracy.
CONCLUSION GC risk factors were incorporated into a computer model to predict the likelihood of developing GC with high sensitivity and specificity. The model is dynamic and will be further improved and validated by including new data in future research studies. Its use may reduce unnecessary endoscopic procedures. It is freely available.
Collapse
Affiliation(s)
- Shahid Aziz
- Patients Diagnostic Lab, Isotope Application Division, Pakistan Institute of Nuclear Science and Technology, Islamabad 44000, Pakistan
- Department of Microbiology, Quaid-i-Azam University, Islamabad 45320, Pakistan
- Interdisciplinary Center for Clinical Research, Core Unit Proteomics, University of Münster, Münster 48149, Germany
| | - Simone König
- Interdisciplinary Center for Clinical Research, Core Unit Proteomics, University of Münster, Münster 48149, Germany
| | - Muhammad Umer
- Management Information System Division, Pakistan Institute of Nuclear Science and Technology, Islamabad 44000, Pakistan
| | - Tayyab Saeed Akhter
- Centre for Liver and Digestive Diseases, Holy Family Hospital, Rawalpindi 46300, Pakistan
| | - Shafqat Iqbal
- Centre for Liver and Digestive Diseases, Holy Family Hospital, Rawalpindi 46300, Pakistan
| | - Maryum Ibrar
- Pakistan Scientific and Technological Information Centre, Quaid-i-Azam University, Islamabad 45320, Pakistan
| | - Tofeeq Ur-Rehman
- Department of Pharmacy, Quaid-i-Azam University, Islamabad 45320, Pakistan
| | - Tanvir Ahmad
- Patients Diagnostic Lab, Isotope Application Division, Pakistan Institute of Nuclear Science and Technology, Islamabad 44000, Pakistan
| | - Alfizah Hanafiah
- Faculty of Medicine, Department of Medical Microbiology and Immunology, Universiti Kebangsan Malaysia, Cheras, Kuala Lumpur 56000, Malaysia
| | - Rabaab Zahra
- Department of Microbiology, Quaid-i-Azam University, Islamabad 45320, Pakistan
| | - Faisal Rasheed
- Patients Diagnostic Lab, Isotope Application Division, Pakistan Institute of Nuclear Science and Technology, Islamabad 44000, Pakistan
| |
Collapse
|
|
29
|
Liu Y, Wang L, Du W, Huang Y, Guo Y, Song C, Tian Z, Niu S, Xie J, Liu J, Cheng C, Shen W. Identification of high-risk factors associated with mortality at 1-, 3-, and 5-year intervals in gastric cancer patients undergoing radical surgery and immunotherapy: an 8-year multicenter retrospective analysis. Front Cell Infect Microbiol 2023; 13:1207235. [PMID: 37325512 PMCID: PMC10264693 DOI: 10.3389/fcimb.2023.1207235] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/17/2023] [Accepted: 05/10/2023] [Indexed: 06/17/2023] Open
Abstract
Background Combining immunotherapy with surgical intervention is a prevailing and radical therapeutic strategy for individuals afflicted with gastric carcinoma; nonetheless, certain patients exhibit unfavorable prognoses even subsequent to this treatment regimen. This research endeavors to devise a machine learning algorithm to recognize risk factors with a high probability of inducing mortality among patients diagnosed with gastric cancer, both prior to and during their course of treatment. Methods Within the purview of this investigation, a cohort of 1015 individuals with gastric cancer were incorporated, and 39 variables encompassing diverse features were recorded. To construct the models, we employed three distinct machine learning algorithms, specifically extreme gradient boosting (XGBoost), random forest (RF), and k-nearest neighbor algorithm (KNN). The models were subjected to internal validation through employment of the k-fold cross-validation technique, and subsequently, an external dataset was utilized to externally validate the models. Results In comparison to other machine learning algorithms employed, the XGBoost algorithm demonstrated superior predictive capacity regarding the risk factors that affect mortality after combination therapy in gastric cancer patients for a duration of one year, three years, and five years posttreatment. The common risk factors that significantly impacted patient survival during the aforementioned time intervals were identified as advanced age, tumor invasion, tumor lymph node metastasis, tumor peripheral nerve invasion (PNI), multiple tumors, tumor size, carcinoembryonic antigen (CEA) level, carbohydrate antigen 125 (CA125) level, carbohydrate antigen 72-4 (CA72-4) level, and H. pylori infection. Conclusion The XGBoost algorithm can assist clinicians in identifying pivotal prognostic factors that are of clinical significance and can contribute toward individualized patient monitoring and management.
Collapse
Affiliation(s)
- Yuan Liu
- Department of General Surgery, Wuxi People’s Hospital Affiliated to Nanjing Medical University, Wuxi, China
| | - Lanyu Wang
- Department of Urology, Wuxi People’s Hospital Affiliated to Nanjing Medical University, Wuxi, China
| | - Wenyi Du
- Department of General Surgery, Wuxi People’s Hospital Affiliated to Nanjing Medical University, Wuxi, China
| | - Yukang Huang
- Department of General Surgery, Wuxi People’s Hospital Affiliated to Nanjing Medical University, Wuxi, China
| | - Yi Guo
- Department of General Practice, Shandong Provincial Hospital Affiliated to Shandong First Medical University, Jinan, Shandong, China
| | - Chen Song
- Department of General Surgery, Wuxi People’s Hospital Affiliated to Nanjing Medical University, Wuxi, China
| | - Zhiqiang Tian
- Department of General Surgery, Wuxi People’s Hospital Affiliated to Nanjing Medical University, Wuxi, China
| | - Sen Niu
- Department of General Surgery, Wuxi People’s Hospital Affiliated to Nanjing Medical University, Wuxi, China
| | - Jiaheng Xie
- The First Affiliated Hospital of Nanjing Medical University, Nanjing, China
| | - Jinhui Liu
- The First Affiliated Hospital of Nanjing Medical University, Nanjing, China
| | - Chao Cheng
- Department of Neurosurgery, Wuxi People’s Hospital Affiliated to Nanjing Medical University, Wuxi, China
| | - Wei Shen
- Department of General Surgery, Wuxi People’s Hospital Affiliated to Nanjing Medical University, Wuxi, China
| |
Collapse
|
|
30
|
Cheema HI, Tharian B, Inamdar S, Garcia-Saenz-de-Sicilia M, Cengiz C. Recent advances in endoscopic management of gastric neoplasms. World J Gastrointest Endosc 2023; 15:319-337. [PMID: 37274561 PMCID: PMC10236974 DOI: 10.4253/wjge.v15.i5.319] [Citation(s) in RCA: 7] [Impact Index Per Article: 3.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 09/20/2022] [Revised: 01/12/2023] [Accepted: 04/06/2023] [Indexed: 05/16/2023] Open
Abstract
The development and clinical application of new diagnostic endoscopic technologies such as endoscopic ultrasonography with biopsy, magnification endoscopy, and narrow-band imaging, more recently supplemented by artificial intelligence, have enabled wider recognition and detection of various gastric neoplasms including early gastric cancer (EGC) and subepithelial tumors, such as gastrointestinal stromal tumors and neuroendocrine tumors. Over the last decade, the evolution of novel advanced therapeutic endoscopic techniques, such as endoscopic mucosal resection, endoscopic submucosal dissection, endoscopic full-thickness resection, and submucosal tunneling endoscopic resection, along with the advent of a broad array of endoscopic accessories, has provided a promising and yet less invasive strategy for treating gastric neoplasms with the advantage of a reduced need for gastric surgery. Thus, the management algorithms of various gastric tumors in a defined subset of the patient population at low risk of lymph node metastasis and amenable to endoscopic resection, may require revision considering upcoming data given the high success rate of en bloc resection by experienced endoscopists. Moreover, endoscopic surveillance protocols for precancerous gastric lesions will continue to be refined by systematic reviews and meta-analyses of further research. However, the lack of familiarity with subtle endoscopic changes associated with EGC, as well as longer procedural time, evolving resection techniques and tools, a steep learning curve of such high-risk procedures, and lack of coding are issues that do not appeal to many gastroenterologists in the field. This review summarizes recent advances in the endoscopic management of gastric neoplasms, with special emphasis on diagnostic and therapeutic methods and their future prospects.
Collapse
Affiliation(s)
- Hira Imad Cheema
- Department of Internal Medicine, Baptist Health Medical Center, Little Rock, AR 72205, United States
| | - Benjamin Tharian
- Department of Interventional Endoscopy/Gastroenterology, Bayfront Health, Digestive Health Institute, St. Petersberg, FL 33701, United States
| | - Sumant Inamdar
- Division of Gastroenterology and Hepatology, Department of Internal Medicine, University of Arkansas for Medical Sciences, Little Rock, AR 72205, United States
| | - Mauricio Garcia-Saenz-de-Sicilia
- Division of Gastroenterology and Hepatology, Department of Internal Medicine, University of Arkansas for Medical Sciences, Little Rock, AR 72205, United States
| | - Cem Cengiz
- Division of Gastroenterology and Hepatology, Department of Internal Medicine, University of Arkansas for Medical Sciences, Little Rock, AR 72205, United States
- Division of Gastroenterology and Hepatology, Department of Internal Medicine, John L. McClellan Memorial Veterans Hospital, Little Rock, AR 72205, United States
- Division of Gastroenterology and Hepatology, Department of Internal Medicine, TOBB University of Economics and Technology, Ankara 06510, Turkey
| |
Collapse
|
|
31
|
Chung H, Ko Y, Lee I, Hur H, Huh J, Han S, Kim KW, Lee J. Prognostic artificial intelligence model to predict 5 year survival at 1 year after gastric cancer surgery based on nutrition and body morphometry. J Cachexia Sarcopenia Muscle 2023; 14:847-859. [PMID: 36775841 PMCID: PMC10067496 DOI: 10.1002/jcsm.13176] [Citation(s) in RCA: 18] [Impact Index Per Article: 9.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 08/17/2022] [Revised: 10/31/2022] [Accepted: 01/02/2023] [Indexed: 02/14/2023] Open
Abstract
BACKGROUND Personalized survival prediction is important in gastric cancer patients after gastrectomy based on large datasets with many variables including time-varying factors in nutrition and body morphometry. One year after gastrectomy might be the optimal timing to predict long-term survival because most patients experience significant nutritional change, muscle loss, and postoperative changes in the first year after gastrectomy. We aimed to develop a personalized prognostic artificial intelligence (AI) model to predict 5 year survival at 1 year after gastrectomy. METHODS From a prospectively built gastric surgery registry from a tertiary hospital, 4025 gastric cancer patients (mean age 56.1 ± 10.9, 36.2% females) treated gastrectomy and survived more than a year were selected. Eighty-nine variables including clinical and derived time-varying variables were used as input variables. We proposed a multi-tree extreme gradient boosting (XGBoost) algorithm, an ensemble AI algorithm based on 100 datasets derived from repeated five-fold cross-validation. Internal validation was performed in split datasets (n = 1121) by comparing our proposed model and six other AI algorithms. External validation was performed in 590 patients from other hospitals (mean age 55.9 ± 11.2, 37.3% females). We performed a sensitivity analysis to analyse the effect of the nutritional and fat/muscle indices using a leave-one-out method. RESULTS In the internal validation, our proposed model showed AUROC of 0.8237, which outperformed the other AI algorithms (0.7988-0.8165), 80.00% sensitivity, 72.34% specificity, and 76.17% balanced accuracy. In the external validation, our model showed AUROC of 0.8903, 86.96% sensitivity, 74.60% specificity, and 80.78% balanced accuracy. Sensitivity analysis demonstrated that the nutritional and fat/muscle indices influenced the balanced accuracy by 0.31% and 6.29% in the internal and external validation set, respectively. Our developed AI model was published on a website for personalized survival prediction. CONCLUSIONS Our proposed AI model provides substantially good performance in predicting 5 year survival at 1 year after gastric cancer surgery. The nutritional and fat/muscle indices contributed to increase the prediction performance of our AI model.
Collapse
Affiliation(s)
- Heewon Chung
- Department of Biomedical Engineering, College of Electronics and InformationKyung Hee UniversityYongin‐siGyeonggi‐doRepublic of Korea
| | - Yousun Ko
- Department of Radiology, Asan Medical CenterUniversity of Ulsan College of MedicineSeoulRepublic of Korea
| | - In‐Seob Lee
- Department of Surgery, Asan Medical CenterUniversity of Ulsan College of MedicineSeoulRepublic of Korea
| | - Hoon Hur
- Department of SurgeryAjou University School of MedicineSuwonRepublic of Korea
| | - Jimi Huh
- Department of RadiologyAjou University School of MedicineSuwonRepublic of Korea
| | - Sang‐Uk Han
- Department of SurgeryAjou University School of MedicineSuwonRepublic of Korea
| | - Kyung Won Kim
- Department of Radiology, Asan Medical CenterUniversity of Ulsan College of MedicineSeoulRepublic of Korea
| | - Jinseok Lee
- Department of Biomedical Engineering, College of Electronics and InformationKyung Hee UniversityYongin‐siGyeonggi‐doRepublic of Korea
| |
Collapse
|
|
32
|
Talebi A, Celis-Morales CA, Borumandnia N, Abbasi S, Pourhoseingholi MA, Akbari A, Yousefi J. Predicting metastasis in gastric cancer patients: machine learning-based approaches. Sci Rep 2023; 13:4163. [PMID: 36914697 PMCID: PMC10011363 DOI: 10.1038/s41598-023-31272-w] [Citation(s) in RCA: 11] [Impact Index Per Article: 5.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/17/2022] [Accepted: 03/09/2023] [Indexed: 03/16/2023] Open
Abstract
Gastric cancer (GC), with a 5-year survival rate of less than 40%, is known as the fourth principal reason of cancer-related mortality over the world. This study aims to develop predictive models using different machine learning (ML) classifiers based on both demographic and clinical variables to predict metastasis status of patients with GC. The data applied in this study including 733 of GC patients, divided into a train and test groups at a ratio of 8:2, diagnosed at Taleghani tertiary hospital. In order to predict metastasis in GC, ML-based algorithms, including Naive Bayes (NB), Random Forest (RF), Support Vector Machine (SVM), Neural Network (NN), Decision Tree (RT) and Logistic Regression (LR), with 5-fold cross validation were performed. To assess the model performance, F1 score, precision, sensitivity, specificity, area under the curve (AUC) of receiver operating characteristic (ROC) curve and precision-recall AUC (PR-AUC) were obtained. 262 (36%) experienced metastasis among 733 patients with GC. Although all models have optimal performance, the indices of SVM model seems to be more appropiate (training set: AUC: 0.94, Sensitivity: 0.94; testing set: AUC: 0.85, Sensitivity: 0.92). Then, NN has the higher AUC among ML approaches (training set: AUC: 0.98; testing set: AUC: 0.86). The RF of ML-based models, which determine size of tumor and age as two essential variables, is considered as the third efficient model, because of higher specificity and AUC (84% and 87%). Based on the demographic and clinical characteristics, ML approaches can predict the metastasis status in GC patients. According to AUC, sensitivity and specificity in both SVM and NN can be regarded as better algorithms among 6 applied ML-based methods.
Collapse
Affiliation(s)
- Atefeh Talebi
- Colorectal Research Center, Iran University of Medical Sciences, Tehran, Iran
- British Heart Foundation Cardiovascular Research Centre, University of Glasgow, Glasgow, UK
| | - Carlos A Celis-Morales
- British Heart Foundation Cardiovascular Research Centre, University of Glasgow, Glasgow, UK
- Institute of Cardiovascular and Medical Sciences, University of Glasgow, Glasgow, UK
| | - Nasrin Borumandnia
- Urology and Nephrology Research Center, Shahid Beheshti University of Medical Sciences, Tehran, Iran.
| | - Somayeh Abbasi
- Department of Mathematics, Isfahan (Khorasgan) Branch, Islamic Azad University, Isfahan, Iran
| | - Mohamad Amin Pourhoseingholi
- Gastroenterology and Liver Diseases Research Center, Research Institute for Gastroenterology and Liver Diseases, Shahid Beheshti University of Medical Sciences, Tehran, Iran
| | - Abolfazl Akbari
- Colorectal Research Center, Iran University of Medical Sciences, Tehran, Iran
| | - Javad Yousefi
- Department of Internal Medicine, School of Medicine, Iran University of Medical Sciences, Tehran, Iran
| |
Collapse
|
|
33
|
A deep-learning based system using multi-modal data for diagnosing gastric neoplasms in real-time (with video). Gastric Cancer 2023; 26:275-285. [PMID: 36520317 DOI: 10.1007/s10120-022-01358-x] [Citation(s) in RCA: 5] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 10/24/2022] [Accepted: 11/25/2022] [Indexed: 12/23/2022]
Abstract
BACKGROUND White light (WL) and weak-magnifying (WM) endoscopy are both important methods for diagnosing gastric neoplasms. This study constructed a deep-learning system named ENDOANGEL-MM (multi-modal) aimed at real-time diagnosing gastric neoplasms using WL and WM data. METHODS WL and WM images of a same lesion were combined into image-pairs. A total of 4201 images, 7436 image-pairs, and 162 videos were used for model construction and validation. Models 1-5 including two single-modal models (WL, WM) and three multi-modal models (data fusion on task-level, feature-level, and input-level) were constructed. The models were tested on three levels including images, videos, and prospective patients. The best model was selected for constructing ENDOANGEL-MM. We compared the performance between the models and endoscopists and conducted a diagnostic study to explore the ENDOANGEL-MM's assistance ability. RESULTS Model 4 (ENDOANGEL-MM) showed the best performance among five models. Model 2 performed better in single-modal models. The accuracy of ENDOANGEL-MM was higher than that of Model 2 in still images, real-time videos, and prospective patients. (86.54 vs 78.85%, P = 0.134; 90.00 vs 85.00%, P = 0.179; 93.55 vs 70.97%, P < 0.001). Model 2 and ENDOANGEL-MM outperformed endoscopists on WM data (85.00 vs 71.67%, P = 0.002) and multi-modal data (90.00 vs 76.17%, P = 0.002), significantly. With the assistance of ENDOANGEL-MM, the accuracy of non-experts improved significantly (85.75 vs 70.75%, P = 0.020), and performed no significant difference from experts (85.75 vs 89.00%, P = 0.159). CONCLUSIONS The multi-modal model constructed by feature-level fusion showed the best performance. ENDOANGEL-MM identified gastric neoplasms with good accuracy and has a potential role in real-clinic.
Collapse
|
|
34
|
Liang Y, Rao Z, Du D, Wang Y, Fang T. Butyrate prevents the migration and invasion, and aerobic glycolysis in gastric cancer via inhibiting Wnt/β-catenin/c-Myc signaling. Drug Dev Res 2023; 84:532-541. [PMID: 36782390 DOI: 10.1002/ddr.22043] [Citation(s) in RCA: 14] [Impact Index Per Article: 7.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/20/2022] [Revised: 01/10/2023] [Accepted: 01/19/2023] [Indexed: 02/15/2023]
Abstract
Gastric cancer (GC) remains a common cause of cancer death worldwide. Evidence has found that butyrate exhibited antitumor effects on GC cells. However, the mechanism by which butyrate regulate GC cell proliferation, migration, invasion, and aerobic glycolysis remains largely unknown. The proliferation, migration, and invasion of GC cells were tested by EdU staining, transwell assays. Additionally, protein expressions were determined by western blot assay. Next, glucose uptake, lactate production, and cellular ATP levels in GC cells were detected. Furthermore, the antitumor effects of butyrate in tumor-bearing nude mice were evaluated. We found, butyrate significantly prevented GC cell proliferation, migration, and invasion (p < .01). Additionally, butyrate markedly inhibited GC cell aerobic glycolysis, as shown by the reduced expressions of GLUT1, HK2, and LDHA (p < .01). Moreover, butyrate notably decreased nuclear β-catenin and c-Myc levels in GC cells (p < .01). Remarkably, through activating Wnt/β-catenin signaling with LiCl, the inhibitory effects of butyrate on the growth and aerobic glycolysis of GC cells were diminished (p < .01). Moreover, butyrate notably suppressed tumor volume and weight in GC cell xenograft nude mice in vivo (p < .01). Meanwhile, butyrate obviously reduced nuclear β-catenin, c-Myc, GLUT1, HK2 and LDHA levels in tumor tissues in GC cell xenograft mice (p < .01). Collectively, butyrate could suppress the growth and aerobic glycolysis of GC cells in vitro and in vivo via downregulating wnt/β-catenin/c-Myc signaling. These findings are likely to prove useful in better understanding the role of butyrate in GC.
Collapse
Affiliation(s)
- Yizhi Liang
- Department of Gastroenterology, The Second Affiliated Clinical Medical College of Fujian Medical University, The Second Affiliated Hospital of Fujian Medical University, Fujian, China
| | - Zilan Rao
- Department of Gastroenterology, The Second Affiliated Clinical Medical College of Fujian Medical University, The Second Affiliated Hospital of Fujian Medical University, Fujian, China
| | - Dongwei Du
- Department of Gastroenterology, The Second Affiliated Clinical Medical College of Fujian Medical University, The Second Affiliated Hospital of Fujian Medical University, Fujian, China
| | - Yiwen Wang
- Department of Gastroenterology, The Second Affiliated Clinical Medical College of Fujian Medical University, The Second Affiliated Hospital of Fujian Medical University, Fujian, China
| | - Taiyong Fang
- Department of Gastroenterology, The Second Affiliated Clinical Medical College of Fujian Medical University, The Second Affiliated Hospital of Fujian Medical University, Fujian, China
| |
Collapse
|
|
35
|
Afrash MR, Shafiee M, Kazemi-Arpanahi H. Establishing machine learning models to predict the early risk of gastric cancer based on lifestyle factors. BMC Gastroenterol 2023; 23:6. [PMID: 36627564 PMCID: PMC9832798 DOI: 10.1186/s12876-022-02626-x] [Citation(s) in RCA: 14] [Impact Index Per Article: 7.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 05/14/2022] [Accepted: 12/19/2022] [Indexed: 01/12/2023] Open
Abstract
BACKGROUND Gastric cancer is one of the leading causes of death worldwide. Screening for gastric cancer greatly relies on endoscopy and pathology biopsy, which are invasive and pose financial burdens. Thus, the prevention of the disease by modifying lifestyle-related behaviors and dietary habits or even the prevention of risk factor formation is of great importance. This study aimed to construct an inexpensive, non-invasive, fast, and high-precision diagnostic model using six machine learning (ML) algorithms to classify patients at high or low risk of developing gastric cancer by analyzing individual lifestyle factors. METHODS This retrospective study used the data of 2029 individuals from the gastric cancer database of Ayatollah Taleghani Hospital in Abadan City, Iran. The data were randomly separated into training and test sets (ratio 0.7:0.3). Six ML methods, including multilayer perceptron (MLP), support vector machine (SVM) (linear kernel), SVM (RBF kernel), k-nearest neighbors (KNN) (K = 1, 3, 7, 9), random forest (RF), and eXtreme Gradient Boosting (XGBoost), were trained to construct prognostic models before and after performing the relief feature selection method. Finally, to evaluate the models' performance, the metrics derived from the confusion matrix were calculated via a test split and cross-validation. RESULTS This study found 11 important influence factors for the risk of gastric cancer, such as Helicobacter pylori infection, high salt intake, and chronic atrophic gastritis, among other factors. Comparisons indicated that the XGBoost had the best performance for the risk prediction of gastric cancer. CONCLUSIONS The results suggest that based on simple baseline patient data, the ML techniques have the potential to start the prescreening of gastric cancer and identify high-risk individuals who should proceed with invasive examinations. Our model could also considerably lessen the number of cases that need endoscopic surveillance. Future studies are required to validate the efficacy of the models in a larger and multicenter population.
Collapse
Affiliation(s)
- Mohammad Reza Afrash
- grid.411705.60000 0001 0166 0922Department of Artificial Intelligence, Smart University of Medical Sciences, Tehran, Iran
| | - Mohsen Shafiee
- Department of Nursing, Abadan University of Medical Sciences, Abadan, Iran
| | - Hadi Kazemi-Arpanahi
- Department of Health Information Technology, Abadan University of Medical Sciences, Abadan, Iran
| |
Collapse
|
|
36
|
Ferreira I, Montenegro CS, Coelho D, Pereira M, da Mata S, Carvalho S, Araújo AC, Abrantes C, Ruivo JM, Garcia H, Oliveira RC. Digital pathology implementation in a private laboratory: The CEDAP experience. J Pathol Inform 2023; 14:100180. [PMID: 36687527 PMCID: PMC9853351 DOI: 10.1016/j.jpi.2022.100180] [Citation(s) in RCA: 5] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/28/2022] [Revised: 12/23/2022] [Accepted: 12/28/2022] [Indexed: 01/05/2023] Open
Abstract
Introduction The transition to digital pathology has been carried out by several laboratories across the globe, with some cases described in Portugal. In this article, we describe the transition to digital pathology in a high-volume private laboratory, considering the main challenges and opportunities. Material and methods Our process started in 2020, with laboratory workflow adaptation and we are currently using a high-capacity scanner (Aperio GT450DX) to digitize slides at 20×. The visualization system, Aperio eSlide Manager WebViewer, is integrated into the Laboratory System. The validation process followed the Royal College of Pathologists Guidelines. Results Regarding validation, the first phase detected an error rate of 6.8%, mostly due to digitization errors. Phase optimization and collaboration with technical services led to improvements in this process. In the second validation phase, most of the slides had the desired quality for evaluation, with only an error rate of 0.6%, corrected with a new scan. The interpathologist correlation had a total agreement rate of 96.87% and 3.13% partial agreement. Conclusion The implementation and validation of digital pathology was a success, being ready for prime time. The total integration of all laboratory systems and the acquisition of new equipment will maximize their use, especially with the application of artificial intelligence algorithms.
Collapse
Affiliation(s)
- Inês Ferreira
- Germano de Sousa - Centro de Diagnóstico Histopatológico CEDAP, Coimbra, Portugal
| | | | - Daniel Coelho
- Germano de Sousa - Centro de Diagnóstico Histopatológico CEDAP, Coimbra, Portugal
| | - Maria Pereira
- Germano de Sousa - Centro de Diagnóstico Histopatológico CEDAP, Coimbra, Portugal
| | - Sara da Mata
- Germano de Sousa - Centro de Diagnóstico Histopatológico CEDAP, Coimbra, Portugal
| | - Sofia Carvalho
- Germano de Sousa - Centro de Diagnóstico Histopatológico CEDAP, Coimbra, Portugal,Hospital de Santa Luzia de Viana do Castelo, ULSAM, EPE, Viana do castelo, Portugal
| | - Ana Catarina Araújo
- Germano de Sousa - Centro de Diagnóstico Histopatológico CEDAP, Coimbra, Portugal
| | - Carlos Abrantes
- Germano de Sousa - Centro de Diagnóstico Histopatológico CEDAP, Coimbra, Portugal
| | - José Mário Ruivo
- Germano de Sousa - Centro de Diagnóstico Histopatológico CEDAP, Coimbra, Portugal
| | - Helena Garcia
- Germano de Sousa - Centro de Diagnóstico Histopatológico CEDAP, Coimbra, Portugal
| | - Rui Caetano Oliveira
- Germano de Sousa - Centro de Diagnóstico Histopatológico CEDAP, Coimbra, Portugal,Institute for Clinical and Biomedical Research (iCBR), Faculty of Medicine, University of Coimbra, Coimbra, Portugal,Centre of Investigation on Genetics and Oncobiology (CIMAGO), Coimbra, Portugal,Clinical and Academic Centre of Coimbra (CACC), Coimbra, Portugal,Corresponding author.
| |
Collapse
|
|
37
|
Luvhengo T, Molefi T, Demetriou D, Hull R, Dlamini Z. Use of Artificial Intelligence in Implementing Mainstream Precision Medicine to Improve Traditional Symptom-driven Practice of Medicine: Allowing Early Interventions and Tailoring better-personalised Cancer Treatments. ARTIFICIAL INTELLIGENCE AND PRECISION ONCOLOGY 2023:49-72. [DOI: 10.1007/978-3-031-21506-3_3] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 01/04/2025]
|
|
38
|
Deng Y, Qin HY, Zhou YY, Liu HH, Jiang Y, Liu JP, Bao J. Artificial intelligence applications in pathological diagnosis of gastric cancer. Heliyon 2022; 8:e12431. [PMID: 36619448 PMCID: PMC9816967 DOI: 10.1016/j.heliyon.2022.e12431] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/24/2022] [Revised: 09/29/2022] [Accepted: 12/09/2022] [Indexed: 12/23/2022] Open
Abstract
Globally, gastric cancer is the third leading cause of death from tumors. Prevention and individualized treatment are considered to be the best options for reducing the mortality rate of gastric cancer. Artificial intelligence (AI) technology has been widely used in the field of gastric cancer, including diagnosis, prognosis, and image analysis. Eligible papers were identified from PubMed and IEEE up to April 13, 2022. Through the comparison of these articles, the application status of AI technology in the diagnosis of gastric cancer was summarized, including application types, application scenarios, advantages and limitations. This review presents the current state and role of AI in the diagnosis of gastric cancer based on four aspects: 1) accurate sampling from early diagnosis (endoscopy), 2) digital pathological diagnosis, 3) molecules and genes, and 4) clinical big data analysis and prognosis prediction. AI plays a very important role in facilitating the diagnosis of gastric cancer; however, it also has shortcomings such as interpretability. The purpose of this review is to provide assistance to researchers working in this domain.
Collapse
Affiliation(s)
- Yang Deng
- Institute of Clinical Pathology, West China Hospital, Sichuan University, Chengdu 610041, Sichuan Province, China
| | - Hang-Yu Qin
- Institute of Clinical Pathology, West China Hospital, Sichuan University, Chengdu 610041, Sichuan Province, China
| | - Yan-Yan Zhou
- Institute of Clinical Pathology, West China Hospital, Sichuan University, Chengdu 610041, Sichuan Province, China
| | - Hong-Hong Liu
- Institute of Clinical Pathology, West China Hospital, Sichuan University, Chengdu 610041, Sichuan Province, China
| | - Yong Jiang
- Department of Pathology, West China Hospital, Sichuan University, Chengdu 610041, Sichuan Province, China
| | - Jian-Ping Liu
- Department of Pathology, West China Hospital, Sichuan University, Chengdu 610041, Sichuan Province, China
| | - Ji Bao
- Institute of Clinical Pathology, West China Hospital, Sichuan University, Chengdu 610041, Sichuan Province, China,Corresponding author.
| |
Collapse
|
|
39
|
Dilaghi E, Lahner E, Annibale B, Esposito G. Systematic review and meta-analysis: Artificial intelligence for the diagnosis of gastric precancerous lesions and Helicobacter pylori infection. Dig Liver Dis 2022; 54:1630-1638. [PMID: 35382973 DOI: 10.1016/j.dld.2022.03.007] [Citation(s) in RCA: 13] [Impact Index Per Article: 4.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 01/29/2022] [Revised: 03/12/2022] [Accepted: 03/16/2022] [Indexed: 02/08/2023]
Abstract
BACKGROUND The endoscopic diagnosis of Helicobacter-pylori(H.pylori) infection and gastric precancerous lesions(GPL), namely atrophic-gastritis and intestinal-metaplasia, still remains challenging. Artificial intelligence(AI) may represent a powerful resource for the endoscopic recognition of these conditions. AIMS To explore the diagnostic performance(DP) of AI in the diagnosis of GPL and H.pylori infection. METHODS A systematic-review was performed by two independent authors up to September 2021. Inclusion criteria were studies focusing on the DP of AI-system in the diagnosis of GPL and H.pylori infection. The pooled accuracy of studies included was reported. RESULTS Overall, 128 studies were found (PubMed-Embase-Cochrane Library) and four and nine studies were finally included regarding GPL and H.pylori infection, respectively. The pooled-accuracy(random effects model) was 90.3%(95%CI 84.3-94.9) and 79.6%(95%CI 66.7-90.0) with a significant heterogeneity[I2=90.4%(95%CI 78.5-95.7);I2=97.9%(97.2-98.6)] for GPL and H.pylori infection, respectively. The Begg's-test showed a significant publication-bias(p = 0.0371) only among studies regarding H.pylori infection. The pooled-accuracy(random-effects-model) was similar considering only studies using CNN-model for the diagnosis of H.pylori infection: 74.1%[(95%CI 51.6-91.3);I2=98.9%(95%CI 98.5-99.3)], Begg's-test(p = 0.1416) did not show publication-bias. CONCLUSION AI-system seems to be a good resource for an easier diagnosis of GPL and H.pylori infection, showing a pooled-diagnostic-accuracy of 90% and 80%, respectively. However, considering the high heterogeneity, these promising data need an external validation by randomized control trials and prospective real-time studies.
Collapse
Affiliation(s)
- E Dilaghi
- Department of Medical-Surgical Sciences and Translational Medicine, Sant'Andrea Hospital, Sapienza University of Rome, Via di Grottarossa, Roma 1035 - 00189, Italy
| | - E Lahner
- Department of Medical-Surgical Sciences and Translational Medicine, Sant'Andrea Hospital, Sapienza University of Rome, Via di Grottarossa, Roma 1035 - 00189, Italy
| | - B Annibale
- Department of Medical-Surgical Sciences and Translational Medicine, Sant'Andrea Hospital, Sapienza University of Rome, Via di Grottarossa, Roma 1035 - 00189, Italy
| | - G Esposito
- Department of Medical-Surgical Sciences and Translational Medicine, Sant'Andrea Hospital, Sapienza University of Rome, Via di Grottarossa, Roma 1035 - 00189, Italy.
| |
Collapse
|
|
40
|
Briggs E, de Kamps M, Hamilton W, Johnson O, McInerney CD, Neal RD. Machine Learning for Risk Prediction of Oesophago-Gastric Cancer in Primary Care: Comparison with Existing Risk-Assessment Tools. Cancers (Basel) 2022; 14:cancers14205023. [PMID: 36291807 PMCID: PMC9600097 DOI: 10.3390/cancers14205023] [Citation(s) in RCA: 8] [Impact Index Per Article: 2.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/14/2022] [Revised: 10/12/2022] [Accepted: 10/12/2022] [Indexed: 11/18/2022] Open
Abstract
Simple Summary Oesophago-gastric cancer is one of the commonest cancers worldwide, yet it can be particularly difficult to diagnose given that initial symptoms are often non-specific and routine screening is not available. Cancer risk-assessment tools, which calculate cancer risk based on symptoms and other risk factors present in the primary care record, can aid decisions on referrals for cancer investigations, facilitating earlier diagnosis. Diagnosing common cancers earlier could help improve survival rates. Using UK primary care electronic health record data, we compared five different machine learning techniques for probabilistic classification of cancer patients against a current widely used UK primary care cancer risk-assessment tool. The machine learning algorithms outperformed the current risk-assessment tool, with a higher overall accuracy and an ability to reasonably identify 11–25% more cancer patients. We conclude that machine-learning-based risk-assessment tools could help better identify suitable patients for further investigation and support earlier diagnosis. Abstract Oesophago-gastric cancer is difficult to diagnose in the early stages given its typical non-specific initial manifestation. We hypothesise that machine learning can improve upon the diagnostic performance of current primary care risk-assessment tools by using advanced analytical techniques to exploit the wealth of evidence available in the electronic health record. We used a primary care electronic health record dataset derived from the UK General Practice Research Database (7471 cases; 32,877 controls) and developed five probabilistic machine learning classifiers: Support Vector Machine, Random Forest, Logistic Regression, Naïve Bayes, and Extreme Gradient Boosted Decision Trees. Features included basic demographics, symptoms, and lab test results. The Logistic Regression, Support Vector Machine, and Extreme Gradient Boosted Decision Tree models achieved the highest performance in terms of accuracy and AUROC (0.89 accuracy, 0.87 AUROC), outperforming a current UK oesophago-gastric cancer risk-assessment tool (ogRAT). Machine learning also identified more cancer patients than the ogRAT: 11.0% more with little to no effect on false positives, or up to 25.0% more with a slight increase in false positives (for Logistic Regression, results threshold-dependent). Feature contribution estimates and individual prediction explanations indicated clinical relevance. We conclude that machine learning could improve primary care cancer risk-assessment tools, potentially helping clinicians to identify additional cancer cases earlier. This could, in turn, improve survival outcomes.
Collapse
Affiliation(s)
- Emma Briggs
- School of Computing, University of Leeds, Leeds LS2 9JT, UK
- Correspondence:
| | - Marc de Kamps
- School of Computing, University of Leeds, Leeds LS2 9JT, UK
- Leeds Institute for Data Analytics, University of Leeds, Leeds LS2 9NL, UK
- The Alan Turing Institute, London NW1 2DB, UK
| | - Willie Hamilton
- Department of Health and Community Sciences, University of Exeter, Exeter EX1 2LU, UK
| | - Owen Johnson
- School of Computing, University of Leeds, Leeds LS2 9JT, UK
- Leeds Institute for Data Analytics, University of Leeds, Leeds LS2 9NL, UK
| | - Ciarán D. McInerney
- Academic Unit of Primary Medical Care, University of Sheffield, Sheffield S10 2TN, UK
| | - Richard D. Neal
- Department of Health and Community Sciences, University of Exeter, Exeter EX1 2LU, UK
| |
Collapse
|
|
41
|
Zhang H, Qian J, Jin M, Fan L, Fan S, Pan H, Li Y, Wang N, Jian B. Jolkinolide B induces cell cycle arrest and apoptosis in MKN45 gastric cancer cells and inhibits xenograft tumor growth in vivo. Biosci Rep 2022; 42:BSR20220341. [PMID: 35674158 PMCID: PMC9245080 DOI: 10.1042/bsr20220341] [Citation(s) in RCA: 6] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/05/2022] [Revised: 06/04/2022] [Accepted: 06/07/2022] [Indexed: 11/20/2022] Open
Abstract
Gastric cancer is one of the most common digestive carcinomas throughout the world and represents high mortality. There is an urgent quest for seeking a novel and efficient antigastric cancer drug. Euphorbia fischeriana Steud had long been used as a traditional Chinese medicine for the treatment of cancer. According to the basic theory of traditional Chinese medicine, its antitumor mechanism is 'to combat poison with poison'. However, its effective material foundation of it is still ambiguous. In our previous work, we studied the chemical constituents of E. fischeriana Steud. Jolkinolide B (JB) is an ent-abietane-type diterpenoid we isolated from it. The purpose of the present study was to investigate the antigastric effect and mechanism of JB. Results revealed that JB could suppress the proliferation of MKN45 cells in vitro and inhibit MKN45 xenograft tumor growth in nude mice in vivo. We further investigated its anticancer mechanism. On the one hand, JB caused DNA damage in gastric cancer MKN45 cells and induced the S cycle arrest by activating the ATR-CHK1-CDC25A-Cdk2 signaling pathway, On the other hand, JB induced MKN45 cells apoptosis through the mitochondrial pathway, and ultimately effectively inhibited the growth of gastric cancer cells. These results suggest that JB appears to be a promising candidate drug with antigastric cancer activity and warrants further research.
Collapse
Affiliation(s)
- Hao Zhang
- Research Institute of Medicine and Pharmacy, Qiqihar Medical University, Qiqihar 161000, P. R. China
| | - Jiayi Qian
- College of Pharmacy, Qiqihar Medical University, Qiqihar 161000, P. R. China
| | - Ming Jin
- Research Institute of Medicine and Pharmacy, Qiqihar Medical University, Qiqihar 161000, P. R. China
| | - Li Fan
- Research Institute of Medicine and Pharmacy, Qiqihar Medical University, Qiqihar 161000, P. R. China
| | - SongJie Fan
- Research Institute of Medicine and Pharmacy, Qiqihar Medical University, Qiqihar 161000, P. R. China
| | - Hong Pan
- College of Pharmacy, Qiqihar Medical University, Qiqihar 161000, P. R. China
| | - Yang Li
- Research Institute of Medicine and Pharmacy, Qiqihar Medical University, Qiqihar 161000, P. R. China
| | - Ningning Wang
- Research Institute of Medicine and Pharmacy, Qiqihar Medical University, Qiqihar 161000, P. R. China
| | - Baiyu Jian
- Research Institute of Medicine and Pharmacy, Qiqihar Medical University, Qiqihar 161000, P. R. China
| |
Collapse
|
|
42
|
Xiao Y, Song Z, Zou S, You Y, Cui J, Wang S, Ku C, Wu X, Xue X, Han W, Zhou W. Artificial Intelligence Assisted Topographic Mapping System for Endoscopic Submucosal Dissection Specimens. Front Med (Lausanne) 2022; 9:822731. [PMID: 35755069 PMCID: PMC9219602 DOI: 10.3389/fmed.2022.822731] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/08/2022] [Accepted: 05/16/2022] [Indexed: 11/13/2022] Open
Abstract
Background Endoscopic submucosal dissection (ESD), a minimally invasive surgery used to treat early gastrointestinal malignancies, has been widely embraced around the world. The gross reconstruction of ESD specimens can facilitate a more precise pathological diagnosis and allow endoscopists to explore lesions thoroughly. The traditional method of mapping is time-consuming and inaccurate. We aim to design a topographic mapping system via artificial intelligence to perform the job automatically. Methods The topographic mapping system was built using computer vision techniques. We enrolled 23 ESD cases at the Peking Union Medical College Hospital from September to November 2019. The reconstruction maps were created for each case using both the traditional approach and the system. Results Using the system, the time saved per case ranges from 34 to 3,336 s. Two approaches revealed no significant variations in the shape, size, or tumor area. Conclusion We developed an AI-assisted system that would help pathologists complete the ESD topographic mapping process rapidly and accurately.
Collapse
Affiliation(s)
- Yu Xiao
- Department of Pathology, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China
| | - Zhigang Song
- Department of Pathology, The Chinese PLA General Hospital, Beijing, China
| | - Shuangmei Zou
- Department of Pathology, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China
| | - Yan You
- Department of Pathology, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China
| | - Jie Cui
- Department of Pathology, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China
| | - Shuhao Wang
- Institute for Interdisciplinary Information Sciences, Tsinghua University, Beijing, China.,Thorough Images, Beijing, China
| | | | - Xi Wu
- Department of Gastroenterology, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China
| | - Xiaowei Xue
- Department of Pathology, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China
| | - Wenqi Han
- Department of Pathology, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China
| | - Weixun Zhou
- Department of Pathology, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China
| |
Collapse
|
|
43
|
Tonozuka R, Niikura R, Itoi T. Artificial intelligence for routine esophagogastroduodenoscopy quality monitoring: Is the future right before our eyes? Gastrointest Endosc 2022; 95:1147-1149. [PMID: 35410727 DOI: 10.1016/j.gie.2022.02.030] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 01/23/2022] [Accepted: 02/20/2022] [Indexed: 02/08/2023]
Affiliation(s)
- Ryosuke Tonozuka
- Department of Gastroenterology and Hepatology Tokyo Medical University, Tokyo, Japan
| | - Ryota Niikura
- Endoscopic Center Tokyo Medical University, Tokyo, Japan
| | - Takao Itoi
- Department of Gastroenterology and Hepatology, Tokyo Medical University, Tokyo, Japan
| |
Collapse
|
|
44
|
Minchenberg SB, Walradt T, Glissen Brown JR. Scoping out the future: The application of artificial intelligence to gastrointestinal endoscopy. World J Gastrointest Oncol 2022; 14:989-1001. [PMID: 35646286 PMCID: PMC9124983 DOI: 10.4251/wjgo.v14.i5.989] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 02/26/2021] [Revised: 06/21/2021] [Accepted: 04/21/2022] [Indexed: 02/06/2023] Open
Abstract
Artificial intelligence (AI) is a quickly expanding field in gastrointestinal endoscopy. Although there are a myriad of applications of AI ranging from identification of bleeding to predicting outcomes in patients with inflammatory bowel disease, a great deal of research has focused on the identification and classification of gastrointestinal malignancies. Several of the initial randomized, prospective trials utilizing AI in clinical medicine have centered on polyp detection during screening colonoscopy. In addition to work focused on colorectal cancer, AI systems have also been applied to gastric, esophageal, pancreatic, and liver cancers. Despite promising results in initial studies, the generalizability of most of these AI systems have not yet been evaluated. In this article we review recent developments in the field of AI applied to gastrointestinal oncology.
Collapse
Affiliation(s)
- Scott B Minchenberg
- Department of Internal Medicine, Beth Israel Deaconess Medical Center, Boston, MA 02130, United States
| | - Trent Walradt
- Department of Internal Medicine, Beth Israel Deaconess Medical Center, Boston, MA 02130, United States
| | - Jeremy R Glissen Brown
- Division of Gastroenterology, Beth Israel Deaconess Medical Center, Boston, MA 02130, United States
| |
Collapse
|
|
45
|
Koopaie M, Ghafourian M, Manifar S, Younespour S, Davoudi M, Kolahdooz S, Shirkhoda M. Evaluation of CSTB and DMBT1 expression in saliva of gastric cancer patients and controls. BMC Cancer 2022; 22:473. [PMID: 35488257 PMCID: PMC9055774 DOI: 10.1186/s12885-022-09570-9] [Citation(s) in RCA: 11] [Impact Index Per Article: 3.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/26/2021] [Accepted: 04/19/2022] [Indexed: 01/07/2023] Open
Abstract
Background Gastric cancer (GC) is the fifth most common cancer and the third cause of cancer deaths globally, with late diagnosis, low survival rate, and poor prognosis. This case-control study aimed to evaluate the expression of cystatin B (CSTB) and deleted in malignant brain tumor 1 (DMBT1) in the saliva of GC patients with healthy individuals to construct diagnostic algorithms using statistical analysis and machine learning methods. Methods Demographic data, clinical characteristics, and food intake habits of the case and control group were gathered through a standard checklist. Unstimulated whole saliva samples were taken from 31 healthy individuals and 31 GC patients. Through ELISA test and statistical analysis, the expression of salivary CSTB and DMBT1 proteins was evaluated. To construct diagnostic algorithms, we used the machine learning method. Results The mean salivary expression of CSTB in GC patients was significantly lower (115.55 ± 7.06, p = 0.001), and the mean salivary expression of DMBT1 in GC patients was significantly higher (171.88 ± 39.67, p = 0.002) than the control. Multiple linear regression analysis demonstrated that GC was significantly correlated with high levels of DMBT1 after controlling the effects of age of participants (R2 = 0.20, p < 0.001). Considering salivary CSTB greater than 119.06 ng/mL as an optimal cut-off value, the sensitivity and specificity of CSTB in the diagnosis of GC were 83.87 and 70.97%, respectively. The area under the ROC curve was calculated as 0.728. The optimal cut-off value of DMBT1 for differentiating GC patients from controls was greater than 146.33 ng/mL (sensitivity = 80.65% and specificity = 64.52%). The area under the ROC curve was up to 0.741. As a result of the machine learning method, the area under the receiver-operating characteristic curve for the diagnostic ability of CSTB, DMBT1, demographic data, clinical characteristics, and food intake habits was 0.95. The machine learning model’s sensitivity, specificity, and accuracy were 100, 70.8, and 80.5%, respectively. Conclusion Salivary levels of DMBT1 and CSTB may be accurate in diagnosing GCs. Machine learning analyses using salivary biomarkers, demographic, clinical, and nutrition habits data simultaneously could provide affordability models with acceptable accuracy for differentiation of GC by a cost-effective and non-invasive method.
Collapse
Affiliation(s)
- Maryam Koopaie
- Department of Oral Medicine, School of Dentistry, Tehran University of Medical Sciences, Tehran, Iran
| | - Marjan Ghafourian
- Department of Oral Medicine, School of Dentistry, Tehran University of Medical Sciences, Tehran, Iran
| | - Soheila Manifar
- Department of Oral Medicine, Imam Khomeini Hospital, Tehran University of Medical Sciences, North Kargar St, P.O.Box:14395-433, Tehran, 14399-55991, Iran.
| | - Shima Younespour
- Dentistry Research Institute, Tehran University of Medical Sciences, Tehran, Iran
| | - Mansour Davoudi
- Department of Computer Science and Engineering and IT, School of Electrical and Computer Engineering, Shiraz University, Shiraz, Iran
| | - Sajad Kolahdooz
- Universal Scientific Education and Research Network (USERN), Tehran, Iran
| | - Mohammad Shirkhoda
- Department of General Oncology, Cancer Research Center, Cancer Institute of Iran, Tehran University of Medical Sciences, Tehran, Iran
| |
Collapse
|
|
46
|
Ko Y, Shin H, Shin J, Hur H, Huh J, Park T, Kim KW, Lee IS. Artificial Intelligence Mortality Prediction Model for Gastric Cancer Surgery Based on Body Morphometry, Nutritional, and Surgical Information: Feasibility Study. APPLIED SCIENCES 2022; 12:3873. [DOI: 10.3390/app12083873] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 12/04/2022]
Abstract
The objective of this study is to develop a mortality prediction model for patients undergoing gastric cancer surgery based on body morphometry, nutritional, and surgical information. Using a prospectively built gastric surgery registry from the Asan Medical Center (AMC), 621 gastric cancer patients, who were treated with surgery with no recurrence of cancer, were selected for the development of the prediction model. Input features (i.e., body morphometry, nutritional, surgical, and clinicopathologic information) were selected in the collected data based on the XGBoost analysis results and experts’ opinions. A convolutional neural network (CNN) framework was developed to predict the mortality of patients undergoing gastric cancer surgery. Internal validation was performed in split datasets of the AMC, whereas external validation was performed in patients in the Ajou University Hospital. Fifteen features were selected for the prediction of survival probability based on the XGBoost analysis results and experts’ suggestions. Accuracy, F1 score, and area under the curve of our CNN model were 0.900, 0.909, and 0.900 in the internal validation set and 0.879, 0.882, and 0.881 in the external validation set, respectively. Our developed CNN model was published on a website where anyone could predict mortality using individual patients’ data. Our CNN model provides substantially good performance in predicting mortality in patients undergoing surgery for gastric cancer, mainly based on body morphometry, nutritional, and surgical information. Using the web application, clinicians and gastric cancer patients will be able to efficiently manage mortality risk factors.
Collapse
Affiliation(s)
- Yousun Ko
- Biomedical Research Center, Asan Institute for Life Sciences, Asan Medical Center, Seoul 05505, Korea
| | - Hooyoung Shin
- Department of Systems Management Engineering, Sengkyunkwan University, Suwon 16419, Korea
| | - Juneseuk Shin
- Department of Systems Management Engineering, Sengkyunkwan University, Suwon 16419, Korea
| | - Hoon Hur
- Department of Surgery, Ajou University School of Medicine, Suwon 16499, Korea
| | - Jimi Huh
- Department of Radiology, Ajou University School of Medicine, Suwon 16499, Korea
| | - Taeyong Park
- Department of Radiology and Research Institute of Radiology, Asan Medical Center, University of Ulsan College of Medicine, Seoul 05505, Korea
| | - Kyung Won Kim
- Department of Radiology and Research Institute of Radiology, Asan Medical Center, University of Ulsan College of Medicine, Seoul 05505, Korea
| | - In-Seob Lee
- Department of Surgery, Asan Medical Center, University of Ulsan College of Medicine, Seoul 05505, Korea
| |
Collapse
|
|
47
|
Buendgens L, Cifci D, Ghaffari Laleh N, van Treeck M, Koenen MT, Zimmermann HW, Herbold T, Lux TJ, Hann A, Trautwein C, Kather JN. Weakly supervised end-to-end artificial intelligence in gastrointestinal endoscopy. Sci Rep 2022; 12:4829. [PMID: 35318364 PMCID: PMC8941159 DOI: 10.1038/s41598-022-08773-1] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/26/2021] [Accepted: 03/03/2022] [Indexed: 12/16/2022] Open
Abstract
Artificial intelligence (AI) is widely used to analyze gastrointestinal (GI) endoscopy image data. AI has led to several clinically approved algorithms for polyp detection, but application of AI beyond this specific task is limited by the high cost of manual annotations. Here, we show that a weakly supervised AI can be trained on data from a clinical routine database to learn visual patterns of GI diseases without any manual labeling or annotation. We trained a deep neural network on a dataset of N = 29,506 gastroscopy and N = 18,942 colonoscopy examinations from a large endoscopy unit serving patients in Germany, the Netherlands and Belgium, using only routine diagnosis data for the 42 most common diseases. Despite a high data heterogeneity, the AI system reached a high performance for diagnosis of multiple diseases, including inflammatory, degenerative, infectious and neoplastic diseases. Specifically, a cross-validated area under the receiver operating curve (AUROC) of above 0.70 was reached for 13 diseases, and an AUROC of above 0.80 was reached for two diseases in the primary data set. In an external validation set including six disease categories, the AI system was able to significantly predict the presence of diverticulosis, candidiasis, colon and rectal cancer with AUROCs above 0.76. Reverse engineering the predictions demonstrated that plausible patterns were learned on the level of images and within images and potential confounders were identified. In summary, our study demonstrates the potential of weakly supervised AI to generate high-performing classifiers and identify clinically relevant visual patterns based on non-annotated routine image data in GI endoscopy and potentially other clinical imaging modalities.
Collapse
Affiliation(s)
- Lukas Buendgens
- Department of Medicine III, University Hospital RWTH Aachen, Pauwelsstrasse 30, 52074, Aachen, Germany
| | - Didem Cifci
- Department of Medicine III, University Hospital RWTH Aachen, Pauwelsstrasse 30, 52074, Aachen, Germany
| | - Narmin Ghaffari Laleh
- Department of Medicine III, University Hospital RWTH Aachen, Pauwelsstrasse 30, 52074, Aachen, Germany
| | - Marko van Treeck
- Department of Medicine III, University Hospital RWTH Aachen, Pauwelsstrasse 30, 52074, Aachen, Germany
| | - Maria T Koenen
- Department of Medicine III, University Hospital RWTH Aachen, Pauwelsstrasse 30, 52074, Aachen, Germany
- Department of Medicine, Rhein-Maas-Klinikum, Würselen, Germany
| | - Henning W Zimmermann
- Department of Medicine III, University Hospital RWTH Aachen, Pauwelsstrasse 30, 52074, Aachen, Germany
| | - Till Herbold
- Department of Visceral Surgery and Transplantation, University Hospital RWTH Aachen, Aachen, Germany
| | - Thomas Joachim Lux
- Interventional and Experimental Endoscopy (InExEn), Internal Medicine II, University Hospital Würzburg, Würzburg, Germany
| | - Alexander Hann
- Interventional and Experimental Endoscopy (InExEn), Internal Medicine II, University Hospital Würzburg, Würzburg, Germany
| | - Christian Trautwein
- Department of Medicine III, University Hospital RWTH Aachen, Pauwelsstrasse 30, 52074, Aachen, Germany
| | - Jakob Nikolas Kather
- Department of Medicine III, University Hospital RWTH Aachen, Pauwelsstrasse 30, 52074, Aachen, Germany.
- Division of Pathology and Data Analytics, Leeds Institute of Medical Research at St James's, University of Leeds, Leeds, UK.
- Medical Oncology, National Center for Tumor Diseases (NCT), University Hospital Heidelberg, Heidelberg, Germany.
| |
Collapse
|
|
48
|
Talebi A, Borumandnia N, Doosti H, Abbasi S, Pourhoseingholi MA, Agah S, Tabaeian SP. Development of web-based dynamic nomogram to predict survival in patients with gastric cancer: a population-based study. Sci Rep 2022; 12:4580. [PMID: 35301382 PMCID: PMC8931071 DOI: 10.1038/s41598-022-08465-w] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/14/2021] [Accepted: 03/07/2022] [Indexed: 12/26/2022] Open
Abstract
Gastric cancer (GC) is the fifth most frequent malignancy worldwide and the third leading cause of cancer-associated mortality. The study's goal was to construct a predictive model and nomograms to predict the survival of GC patients. This historical cohort study assessed 733 patients who underwent treatments for GC. The univariate and multivariable Cox proportional hazard (CPH) survival analyses were applied to identify the factors related to overall survival (OS). A dynamic nomogram was developed as a graphical representation of the CPH regression model. The internal validation of the nomogram was evaluated by Harrell's concordance index (C-index) and time-dependent AUC. The results of the multivariable Cox model revealed that the age of patients, body mass index (BMI), grade of tumor, and depth of tumor elevate the mortality hazard of gastric cancer patients (P < 0.05). The built nomogram had a discriminatory performance, with a C-index of 0.64 (CI 0.61, 0.67). We constructed and validated an original predictive nomogram for OS in patients with GC. Furthermore, nomograms may help predict the individual risk of OS in patients treated for GC.
Collapse
Affiliation(s)
- Atefeh Talebi
- Colorectal Research Center, Iran University of Medical Sciences, Tehran, Iran
| | - Nasrin Borumandnia
- Urology and Nephrology Research Center, Shahid Beheshti University of Medical Sciences, 1666663111, Tehran, Iran.
| | - Hassan Doosti
- Department of Mathematics and Statistics, Macquarie University, Sydney, Australia
| | - Somayeh Abbasi
- Department of Mathematics, Isfahan (khorasgan) Branch, Islamic Azad University, Isfahan, Iran
| | - Mohamad Amin Pourhoseingholi
- Gastroenterology and Liver Diseases Research Center, Research Institute for Gastroenterology and Liver Diseases, Shahid Beheshti University of Medical Sciences, Tehran, Iran
| | - Shahram Agah
- Internal Medicine and Gastroenterology, Colorectal Research Center, Iran University of Medical Sciences, Tehran, Iran
| | - Seidamir Pasha Tabaeian
- Colorectal Research Center, Iran University of Medical Sciences, Tehran, Iran.
- Gastroenterology and Hepatology, Iran University of Medical Sciences, Tehran, Iran.
| |
Collapse
|
|
49
|
Wei J, Wang R, Lu Y, He S, Ding Y. Flotillin-1 promotes progression and dampens chemosensitivity to cisplatin in gastric cancer via ERK and AKT signaling pathways. Eur J Pharmacol 2022; 916:174631. [PMID: 34774850 DOI: 10.1016/j.ejphar.2021.174631] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/11/2021] [Revised: 11/08/2021] [Accepted: 11/09/2021] [Indexed: 11/20/2022]
Abstract
BACKGROUND Several past studies have reported the overexpression of Flotillin-1 in a variety of cancer types. Cisplatin is a chemotherapeutic drug commonly used for cancer treatment. The present study investigated the role of Flotillin-1 in the progression of GC and assessed whether it assists in the chemical sensitization of GC cells toward cisplatin. METHOD The expression of Flotillin-1 was detected both in human gastric mucosal cells and GC cells. Next, siRNA and shRNA were used to construct a stable cell line expressing low levels of Flotillin-1. Furthermore, the Cell Counting Kit 8 (CCK-8), flow cytometry, and transwell assays were employed to detect the impact of Flotillin-1 on GC cells. In addition, a nude mouse model of human GC was used to verify the knockdown of Flotillin-1 to increase the sensitivity of GC cells to cisplatin. RESULTS Flotillin-1 was overexpressed in GC cells when compared to that in human gastric mucosal cells. The results for in vitro and vivo assays revealed that the knockdown of Flotillin-1 could significantly inhibit the proliferation of GC cells and increased the sensitivity of GC cells to cisplatin via the regulation of the protein kinase B (AKT) and extracellular signal-regulated kinase (ERK) signaling pathway. CONCLUSION Flotillin-1 might be used as a molecular marker for GC diagnosis and could be explored as a potential new target for the treatment of GC.
Collapse
Affiliation(s)
- Jiahui Wei
- Department of Laboratory Animals, College of Animal Sciences, Jilin University, Changchun, Jilin, 130062, PR China
| | - Ruiqing Wang
- The Eye Center in the Second Hospital of Jilin University, Ziqiang Street 218#, Nanguan District, Changchun City, Jilin, 130041, China
| | - Yiran Lu
- Department of Laboratory Animals, College of Animal Sciences, Jilin University, Changchun, Jilin, 130062, PR China
| | - Song He
- Department of Laboratory Animals, College of Animal Sciences, Jilin University, Changchun, Jilin, 130062, PR China
| | - Yu Ding
- Department of Laboratory Animals, College of Animal Sciences, Jilin University, Changchun, Jilin, 130062, PR China.
| |
Collapse
|
|
50
|
Kinami S, Saito H, Takamura H. Significance of Lymph Node Metastasis in the Treatment of Gastric Cancer and Current Challenges in Determining the Extent of Metastasis. Front Oncol 2022; 11:806162. [PMID: 35071010 PMCID: PMC8777129 DOI: 10.3389/fonc.2021.806162] [Citation(s) in RCA: 31] [Impact Index Per Article: 10.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/31/2021] [Accepted: 12/13/2021] [Indexed: 12/16/2022] Open
Abstract
The stomach exhibits abundant lymphatic flow, and metastasis to lymph nodes is common. In the case of gastric cancer, there is a regularity to the spread of lymph node metastasis, and it does not easily metastasize outside the regional nodes. Furthermore, when its extent is limited, nodal metastasis of gastric cancer can be cured by appropriate lymph node dissection. Therefore, identifying and determining the extent of lymph node metastasis is important for ensuring accurate diagnosis and appropriate surgical treatment in patients with gastric cancer. However, precise detection of lymph node metastasis remains difficult. Most nodal metastases in gastric cancer are microscopic metastases, which often occur in small-sized lymph nodes, and are thus difficult to diagnose both preoperatively and intraoperatively. Preoperative nodal diagnoses are mainly made using computed tomography, although the specificity of this method is low because it is mainly based on the size of the lymph node. Furthermore, peripheral nodal metastases cannot be palpated intraoperatively, nodal harvesting of resected specimens remains difficult, and the number of lymph nodes detected vary greatly depending on the skill of the technician. Based on these findings, gastrectomy with prophylactic lymph node dissection is considered the standard surgical procedure for gastric cancer. In contrast, several groups have examined the value of sentinel node biopsy for accurately evaluating nodal metastasis in patients with early gastric cancer, reporting high sensitivity and accuracy. Sentinel node biopsy is also important for individualizing and optimizing the extent of uniform prophylactic lymph node dissection and determining whether patients are indicated for function-preserving curative gastrectomy, which is superior in preventing post-gastrectomy symptoms and maintaining dietary habits. Notably, advancements in surgical treatment for early gastric cancer are expected to result in individualized surgical strategies with sentinel node biopsy. Chemotherapy for advanced gastric cancer has also progressed, and conversion gastrectomy can now be performed after downstaging, even in cases previously regarded as inoperable. In this review, we discuss the importance of determining lymph node metastasis in the treatment of gastric cancer, the associated difficulties, and the need to investigate strategies that can improve the diagnosis of lymph node metastasis.
Collapse
Affiliation(s)
- Shinichi Kinami
- Department of Surgical Oncology, Kanazawa Medical University, 1-1 Daigaku, Uchinada-machi, Kahoku-gun, Japan
- Department of General and Gastroenterologic Surgery, Kanazawa Medical University Himi Municipal Hospital, Himi City, Japan
| | - Hitoshi Saito
- Department of General and Gastroenterologic Surgery, Kanazawa Medical University Himi Municipal Hospital, Himi City, Japan
| | - Hiroyuki Takamura
- Department of Surgical Oncology, Kanazawa Medical University, 1-1 Daigaku, Uchinada-machi, Kahoku-gun, Japan
| |
Collapse
|