Review Open Access
Copyright ©The Author(s) 2021. Published by Baishideng Publishing Group Inc. All rights reserved.
Artif Intell Gastroenterol. Apr 28, 2021; 2(2): 27-41
Published online Apr 28, 2021. doi: 10.35712/aig.v2.i2.27
Artificial intelligence in gastrointestinal radiology: A review with special focus on recent development of magnetic resonance and computed tomography
Kai-Po Chang, Shih-Huan Lin, Yen-Wei Chu, PhD Program in Medical Biotechnology, National Chung Hsing University, Taichung 40227, Taiwan
Kai-Po Chang, Department of Pathology, China Medical University Hospital, Taichung 40447, Taiwan
Yen-Wei Chu, Institute of Genomics and Bioinformatics, National Chung Hsing University, Taichung 40227, Taiwan
Yen-Wei Chu, Institute of Molecular Biology, National Chung Hsing University, Taichung 40227, Taiwan
Yen-Wei Chu, Agricultural Biotechnology Center, National Chung Hsing University, Taichung 40227, Taiwan
Yen-Wei Chu, Biotechnology Center, National Chung Hsing University, Taichung 40227, Taiwan
Yen-Wei Chu, PhD Program in Translational Medicine, National Chung Hsing University, Taichung 40227, Taiwan
Yen-Wei Chu, Rong Hsing Research Center for Translational Medicine, Taichung 40227, Taiwan
ORCID number: Kai-Po Chang (0000-0003-1730-9728); Shih-Huan Lin (0000-0002-9037-0683); Yen-Wei Chu (0000-0002-5525-4011).
Author contributions: Chu YW and Chang KP conceived the idea for the manuscript; Chang KP and Lin SH reviewed the literature and drafted the manuscript; Chu YW drafted and finally approved the manuscript.
Supported by Ministry of Science and Technology, No. 109-2321-B-005-024 and No. 109-2320-B-039-005; National Chung Hsing University and Chung-Shan Medical University, No. NCHU-CSMU 10911; China Medical University Hospital, No. DMR-109-258; and ChangHua Christian Hospital and National Chung Hsing University, No. NCHU-CCH-11006.
Conflict-of-interest statement: Authors declare no conflict of interests for this article.
Open-Access: This article is an open-access article that was selected by an in-house editor and fully peer-reviewed by external reviewers. It is distributed in accordance with the Creative Commons Attribution NonCommercial (CC BY-NC 4.0) license, which permits others to distribute, remix, adapt, build upon this work non-commercially, and license their derivative works on different terms, provided the original work is properly cited and the use is non-commercial. See:
Corresponding author: Yen-Wei Chu, PhD, Director, Professor, Institute of Genomics and Bioinformatics, National Chung Hsing University, Kuo Kuang Road, Taichung 40227, Taiwan.
Received: January 27, 2021
Peer-review started: January 27, 2021
First decision: March 7, 2021
Revised: March 21, 2021
Accepted: April 20, 2021
Article in press: April 20, 2021
Published online: April 28, 2021


Artificial intelligence (AI), particularly the deep learning technology, have been proven influential to radiology in the recent decade. Its ability in image classification, segmentation, detection and reconstruction tasks have substantially assisted diagnostic radiology, and has even been viewed as having the potential to perform better than radiologists in some tasks. Gastrointestinal radiology, an important subspecialty dealing with complex anatomy and various modalities including endoscopy, have especially attracted the attention of AI researchers and engineers worldwide. Consequently, recently many tools have been developed for lesion detection and image construction in gastrointestinal radiology, particularly in the fields for which public databases are available, such as diagnostic abdominal magnetic resonance imaging (MRI) and computed tomography (CT). This review will provide a framework for understanding recent advancements of AI in gastrointestinal radiology, with a special focus on hepatic and pancreatobiliary diagnostic radiology with MRI and CT. For fields where AI is less developed, this review will also explain the difficulty in AI model training and possible strategies to overcome the technical issues. The authors’ insights of possible future development will be addressed in the last section.

Key Words: Artificial intelligence, Deep learning, Image diagnosis, Radiology, Magnetic resonance imaging, Computed tomography

Core Tip: Gastrointestinal radiology is a subspecialty that is important and complex, and is thus a popular subject in artificial intelligence (AI). Recently many deep-learning based diagnosis assistance tool have been developed in gastrointestinal radiology, particularly in diagnostic abdominal magnetic resonance imaging (MRI) and computed tomography (CT). Herein we will review recent advance of AI in gastrointestinal radiology, with a special focus on abdominal MRI and CT. Current difficulty in less-developed fields will be explained as well.


The field of gastrointestinal radiology includes diagnostic radiology and interventional radiology. In the practice of diagnostic gastrointestinal radiology, various imaging tools are applied for the diagnosis of lesions in the abdominal cavity. These tools include X-ray used in abdominal plain film[1], angiography and abdominal computed tomography (CT)[2], magnetic resonance used in abdominal magnetic resonance imaging (MRI)[3,4], and ultrasound used in abdominal sonography[5]. For some diagnostic tasks, intravenous contrasts are used to enhance lesions for study. Contrast-enhanced, three-phase CT is the standard for examination of liver tumors and many other lesion types[6]. Contrast-enhanced ultrasound and MRI, though less frequently used, have some clinical use in examination of pancreatic lesions and inflammatory bowel disease[7-9]. Please refer to Ripollés et al[7] for example of contrast-enhanced ultrasound for diagnosis for Crohn’s disease.

Artificial intelligence (AI) have been influential in radiology recently, because it has potential to reduce workloads of radiologists, and diagnostic radiology tools stated above have provided feasible ground for machine learning model development. Potential of machine learning models to reduce radiologist workload come from its better stability, higher work efficiency, and better accuracy in some selected tasks[10] than human workers. Deep learning has proven its suitability for different imaging methods, and radiology and has been widely used in image classification, segmentation, detection, and reconstruction tasks[11]. There are some optimistic radiologists who are willing to let AI assist them in their work so that they can enhance their role in other places[12,13]. Of course, there are also pessimistic radiologists who worry that the development of AI systems will replace radiologists[14].

The most significant shortcoming of machine learning algorithms require a lot of data[15]. At the same time, the lack of unified standard training data will lead to a decrease in the efficiency of AI learning, but it is difficult for doctors to label a large amount of accurate data in complex diseases. In addition, the algorithm may learn false correlations, which may also lead to overfitting. At the same time, it is difficult for AI to explain the causality in the observation dataset. Semi-supervised learning is between supervised learning and unsupervised learning. In the training process, a small amount of labeled data and a large amount of unlabeled data are used at the same time. The development of semi-supervised learning algorithms is mainly because data labeling is very expensive or impossible in some fields[16-18]. The development of semi-supervised learning can also simultaneously solve the problems of a large number of labeling and overfitting.


Interventional radiology uses imaging techniques in diagnostic radiology to treat diseases or take specimens. The practice of interventional procedures in gastrointestinal radiology can be best exemplified by the treatment solid organ tumors. Among the most-frequently used non-surgical treatment procedures of hepatocellular carcinoma (HCC) are transcatheter arterial chemoembolization (TACE) and radiofrequency ablation (RFA). In TACE[19], liver tumors are first highlighted by angiography, and then embolized by particles coated with chemotherapeutic drugs. In RFA[20], the lesion is located by ultrasound rather than angiography and ablated by radiofrequency heating. In addition to liver cancer, any solid organ tumors with rich vasculature can be treated with this procedure. For example, pancreatic neuroendocrine tumors are frequently hypervascular, therefore are sometimes treated by embolization since last century[21,22], especially in patients with multiple endocrine neoplasia type 1 syndrome, where multiple tumors may make resection unfeasible[23]. are also widely applied in some of pancreatic tumors, such as neuroendocrine tumors. Application of RFA, which does not require rich vasculature, is even more versatile than TACE. There are reports of successful radiofrequency ablation on unresectable pancreatic cancer[24,25], and even intra-abdominal sarcomas such as gastrointestinal stromal tumor[26].

Interventional radiology also has broad application on non-tumor diseases, especially in vascular diseases. The best well-known example is emergent management of gastrointestinal bleeding, where the bleeding artery can be visualized by angiography, and embolized[27,28]. A similar approach can be also applied to thrombotic diseases such as Budd-Chiari syndrome or celiac artery occlusion[29,30]. In management of these disorders, the vessels are visualized and dilated with stents or dissolved with thrombolytic agents. Applications of interventional radiology are numerous and still developing, so a thorough review is out of scope of this article.

Both diagnostic and interventional gastrointestinal radiology can be done endoscopically. For example, in endoscopic ultrasound (EUS), the ultrasound probe is inserted through an endoscope to visualize lesions that are not easily accessible by abdominal sonography[31,32]. Biopsy and other interventional procedures can then be done to the visualized lesion via the endoscope, as exemplified in publications by Williams et al[33]. and Kahaleh et al[34]. Endoscopic radiological images are more difficult to be collected in large amount, because like in EUS, most image from endoscopic procedures are manually captured with custom angle of the endoscopist, rather than in an automatic and standard manner. Therefore, unlike in development of AI in regular diagnostic radiology, in which large scale public dataset, such as pancreas CT dataset from The Cancer Imaging Archive[35-37], and Beyond the Cranial Vault Abdomen data set[38,39], are readily available, most AI studies in endoscopic radiology still requires collection and processing of multihospital data. Moreover, lack of standardization and technical difficulty can make researchers reluctant or afraid to make image public. For example, in the study of computer-aided diagnosis of gastrointestinal stromal tumors by Li et al[40], the authors made the research possible only after collecting data from 19 hospitals, and did not publish the dataset. To our knowledge, there is only one well-known, public database of endoscopic ultrasound, published in 2020[41], and we hope that more database will be available in the following decade. In the present situation, due to less available resource, endoscopic radiology is less developed, so in this review article, we will focus on non-endoscopic radiological examination, particularly on CT and MRI.


In the last five years, there have been marked progress in deep learning-assisted lesion detection for radiology, particularly in computed tomography. The progress can be exemplified by the DeepLesion tool developed by National Institutes of Health[42], which claims to detect all types of lesion in computed tomography regardless of the organ, with a sensitivity of 81.1% and five false-positives per case. DeepLesion was published along with an immense dataset with 32120 CT slices. With this annotated database in hand as a powerful tool, researchers refined lesion detection algorithm at an accelerated pace. For example, with the DeepLesion dataset, researchers from Chinese Academy of Sciences were able to develop the MVP-Net tool[43] by feature pyramid network, which claims to be 5.65% more sensitive than DeepLesion. With more developed advancements in deep learning algorithms and more databases available, we can expect that universal lesion detection in computed tomography will reach clinical use in reasonable time. An example of lesion detection in DeepLesion can be found in Yan et al[42].

For MRI, recent advancements are much less pronounced. Due to complex and variable sequencing techniques used in MRI, such as perfusion weighted imaging and T2* used in in stroke protocol[44] and diffusion weighted imaging[45] used in various organs, development of an universal, organ-neutral lesion detection algorithm is very difficult, if not impossible. Nonetheless, for individual organs, there is still marked progression. For example, using a deep learning algorithm, Amit et al[46] developed a tool for lesion detection in breast MRI. Later, in 2019, with the application of deep learning on T1-weighted, fat-suppressed MR images, Kijowski et al[47] further extended the technology to predict breast lesion type. Though not as effective as in breast lesion detection, the application of deep learning on musculoskeletal system MRI has achieved marked success for the detection of variable lesions, such as fracture, deformity, and metastatic disease. There are numerous studies about lesion detection on MRI in other organs, but it is beyond the scope of this review article.

Given the fact that there are on an average five false-positive lesions detected by DeepLesion, deep learning algorithms trained by radiographs are prone to over-detecting lesions. Researchers are aware of this problem and have tried to overcome it by various technologies. The most-used and earliest method applied is multi-view convolutional networks (CNN), wherein native 3D shapes are recognized from their rendered 2D views[48]. By using multi-view CNN, Setio et al[49], Kang et al[50] and El-Regaily et al[51] reported significant reduction of false-positive lesions in the lung with computed tomography, thus making this algorithm the most effective detection training tool for lung image. Recent results of the use of multi-view CNN in lung lesion detection are shown in Table 1.

Table 1 Recent results in usage of multi-view convolutional networks in lung lesion detection.
LIDCConvNets (2D)0.996Setio et al[49], 2016
LIDCInception-Resnet (3D)0.99Kang et al[50], 2017
LIDCMatConvNet (2D)0.94El-Regaily et al[51], 2020

In addition to lung computer tomography, multi-view CNN has been used with other imaging subjects as well. It is also used to increase specificity in mammographic image classification[52] and longitudinal multiple sclerosis lesion segmentation[53]. Besides multi-view CNN, masking techniques during neural network training are also used to reduce false positive lesions. For example, Zlocha et al[54] used dense masks to improve the performance of RetinaNet[55], and the researchers developing ULDor tool[56] used pseudo mask to reduce false positivity in universal lesion detector.

Taken together, in recent years, deep learning for lesion detection in technology has shown great progress. In the next section, we will focus on how these technical advancements have benefited the diagnosis of gastrointestinal lesions.

Cholangiographic diagnosis

One of the most advanced achievement in gastrointestinal radiology is the non-invasive evaluation of for the bile ducts. Before the era of image reconstruction and advanced endoscopy, visualization and diagnosis of lesions causing biliary disease usually required quite invasive procedures such as transhepatic cholangiography[57]. In late 20th century, with the advancements in endoscopy, it was replaced by endoscopic methods like retrograde cholangiopancreatography (ERCP)[58] and EUS cholangiography[59,60]. For achieving both treatment and diagnosis, endoscopic procedure maybe necessary and appropriate, but for the sole purpose of diagnosis, such as visualization of lesions in primary sclerosing cholangitis (PSC)[61] and choledochal cyst[62], endoscopic procedure maybe too invasive and inconvenient for patients.

Therefore, in the last three decades, with the increasing demand of non-invasive procedures and the progress of digital image reconstruction technologies, some radiology visualization tools, such as magnetic resonance cholangiopancreatography (MRCP)[63] and CT cholangiography[64], have been developed and achieved clinical importance. For diagnostic problems, the precision of non-invasive examination has become comparable to that of endoscopic procedure. MRCP achieved diagnostic accuracy of up to 97% in the diagnosis of choledocholithiasis as early as 2000[65]. In 2011, MRCP even rivaled the performance of pathologic examination, with an accuracy of 82.9% in predicting carcinomatous biliary obstruction[66]. In the meantime, CT cholangiography also reached the status of standard care in some situations, such as preoperative biliary anatomy assessment when MRCP is inconclusive[67].

These noninvasive diagnostic examinations are, of course, far from perfect. Despite early success, in some studies between 2010 and 2020, the sensitivity of MRCP for choledocholithiasis was reportedly inferior to that of EUS[68]. This outcome may be attributed to subjectivity and inter-observer variability of interpretation, because, even though it is less demanding than ERCP, the radiological assessment of the bile duct and pancreas still requires high level of expertise to interpret[69]. For more demanding tasks, such as detection and classification of pancreatic lesions[70,71], the performance of noninvasive tests can be even more disappointing.

To cope with the problem of interpretation difficulty in noninvasive cholangiopancreatography, researchers began to use variable deep learning methods in an attempt to achieve more subjective and sensitive lesion detection in the bile ducts and pancreas. For example, Ringe et al[72] developed a transfer learning-based system for automated detection of PSC, achieving a sensitivity of 95%. If this system is used clinically, radiologists can avoid all-manual interpretation for difficult PSC detection, thus reducing possible the inter-observer disagreement. Some of researchers also used deep learning to improve image reconstruction and segmentation in the pancreatobiliary region, to reduce pitfall in traditional MRCP and CT cholangiography. For example, Tang et al[73] used deep learning to improve highlighting of periampullary regions in MRI, which can be difficult with traditional MRCP method. Al-Oudat et al[74] used Denoising Convolutional Neural Networks for better construction of intrahepatic biliary segmentation in MRI image.

Besides its utility in noninvasive examination, deep learning can also benefit imaging difficulty in endoscopic procedure. By a segmentation algorithm trained by D-LinkNet34 and U-Net, Huang et al[75] developed a system to evaluate stone removal difficulty of ERCP. By training on a deep learning model using ultrasound images and videos, Zhang et al[76] developed a system to recognize pancreas segments and stations in EUS. With globally increasing computing power and maturing deep learning technology, we can expect radiological pancreaticobiliary system assessment to continuously improve in the future.

Detection and classification of solid organ tumor

Imaging studies, such as abdominal contrasted CT scan and contrast enhanced ultrasound, are crucial for the evaluation of solid organ tumor diagnosis, such as liver cancer, pancreatic cancer, and other solid organ tumors. The best example is screening for HCC in patients with cirrhosis[77]. Image diagnosis of liver tumor is crucial and effective to the point that HCC can be diagnosed by three-phase contrasted CT[78] alone, without the need of a biopsy[79]. Despite being less accurate, image diagnosis is helpful in more difficult-to-diagnose tumor types, such as focal nodular hyperplasia and hepatocellular adenoma[80-82]. CT diagnosis is also crucial and sensitive for pancreas cancer diagnosis[83] and prediction of malignant change in cystic lesion[84].

The first problem in image diagnosis is that, even with state-of-the-art, highly sensitive technique, it can have less than ideal specificity. For example, image appearance of intrahepatic cholangiocarcinoma (ICC) can mimic HCC both in contrast-enhanced CT[85] and contrast-enhanced ultrasound[86]. Since the long-term outcome and treatment strategy are significantly different between HCC and ICC[87,88], this can be a severe misdiagnosis that impacts prognosis. Some vascular tumors like epithelioid hemangioendothelioma[89,90] and sclerosed hemangioma[91] may also mimic epithelial malignancy, making the image diagnosis even less specific. Moreover, because of a large volume of abdominal CT and MRI done for liver cancer screening, the workload is quite a lot for radiologists[92,93]. Pancreatic cancer is more problematic, since inflammatory process such as autoimmune pancreatitis can mimic adenocarcinoma, causing diagnostic difficulty in CT and MRI[94,95]. Less prevalent tumor types, such as acinar cell carcinoma of pancreas, can be even more challenging[96]. Therefore, there is strong demand for automatic tumor classification algorithm for abdominal imaging, to improve the accuracy of tumor classification and reduce radiologists’ workload.

Of the two purposes stated above, the most recent development was on assisted lesion detection to relieve radiologists’ workload. Using watershed transform and Gaussian mixture, Das et al[97] developed a tool that they claimed can detect hemangioma, HCC and metastatic carcinoma with a classification accuracy of 99.38%; however, they did not consider ICC in their differential diagnosis, therefore, this tool can be used only for screening, and not for final tumor diagnosis. Vorontsov et al[98] used fully convolutional network for the detection of liver metastatic colorectal cancer, with a sensitivity of up to 85%. There are several other developed for liver tumor detection and segmentation with variable success[99,100]. For automatic pancreatic cancer detection, there are also variable success. Li et al[101] developed a computer aided diagnosis model by Dual threshold principal component analysis for pancreas cancer on PET/CT image, with an accuracy of up to 87.72%. By using faster region-based CNN on CT image, Liu et al[102] built a diagnosis system which detected pancreatic cancer with an area under the curve (AUC) of 0.9632. These studies are only some examples of AI detection of digestive system cancer in medical images. For a more detailed discussion, readers can refer to the other review article focused on this subject[103].

Few researchers have published results about detailed tumor classification based on abdominal imaging. By training convolution CNN with both MRI image and clinical data, Zhen et al[104]’s model achieved AUC of up to 0.985 in the classification of malignant tumors as hepatocellular carcinoma, metastatic carcinoma or other primary malignancies. Yasaka et al[105] attempted automatic classification of liver tumor into five classes (HCC, other malignancy, indeterminate masses, and two classes of benign lesions) using CNN, and achieved an accuracy of 0.84. Scope of these classification tools are summarized in Table 2. Due to limited literature available, it is too early to predict whether automatic radiological tumor classification will be comparable to pathologic diagnosis, but the recent results seem promising, and would be a good subject for further research.

Table 2 Classification scope for recent deep learning-based tumor classification tools.
Ref.HCCICCMetastatic carcinomaOther malignancy Benign tumors
Das et al[97], 2019OXOXO
Vorontsov et al[98], 2019XXOXX
Zhen et al[104], 2020OOOOX
Yasaka et al[105], 2018OOOOO
Intelligent assistance on endoscopic radiology

Endoscopic radiological procedures, such as EUS and ERCP, can be very difficult to perform and interpret, and require a lot of training to achieve competence[106], particularly if combined with interventional procedures like ampullectomy or biopsy[107,108]. Artificial intelligence assistance to reduce difficulty and allow for a reasonable learning curve is therefore desired for these procedures.

Due to the limited availability of public image database of EUS and ERCP, the development of AI models for these modalities is, as stated in a previous review article, still in its infancy[109]. There are, however, already some promising results in assistance of endoscopic radiological procedure. The most pronounced progress is with depth assessment in EUS. EUS imaging for evaluation of tumor depth is crucial in predicting the safety of endoscopic submucosal dissection[110]; however, the image diagnosis can be subjective, and requires much expertise. Cho et al[111] developed a tool using deep learning that predicts tumor depth in EUS with a claimed AOC of 0.887. For less sophisticated tasks such as detection of pancreatic cancer in EUS, the result is even better, with a claimed AOC of 0.940[112]. Therefore, it is evident that deep learning-assisted diagnosis can be a reliable tool.

In summary, AI has proven helpful in radiological diagnosis. Although few of the tools described above have reached clinical use, with current development, we can expect AI-assisted diagnosis to advance further in few years, and it may eventually become relevant to everyday clinical practice.


Although AI has made a lot of contributions in radiology, there are still some challenges and pitfalls, and AI experts should be cautious when working with radiologists. One of the biggest challenges is the availability of data. Ordinary deep learning algorithms will be learned through millions of training datasets, but it is difficult for the medical field to have such a large amount of data, and even if there are a large number of training datasets, there is currently no unified classification standard[113,114]. If the training dataset is too small, multiple neuron training through deep learning will easily lead to overfitting[115,116] and will show poor accuracy in independent tests. How to choose the right amount of model depth to adapt to a smaller training dataset will be the biggest challenge for AI engineers. In addition, generative adversarial networks[117] is also very suitable for small training datasets. At the same time, the establishment of a large number of training databases can also effectively help improve the efficiency of AI. Physicians and engineers work together to establish an open database and set uniform standards, which can also enhance AI applicability in radiology and pathology.

In addition, some diseases (usually rare diseases) have a problem of extreme disparity in the classification ratio, which is called imbalanced data. Imbalanced data training is more difficult, which usually leads to high accuracy but poor results, because the machine only needs to guess more. The classification, you can get a good-looking accuracy. Although there are good solutions already available[118], these are still important challenges for using AI with rare diseases.

Finally, when an AI model that can be used clinically is to be developed, proper verification settings must be ensured in the experimental verification of the model. Lack of sufficient verification can lead to untrustworthy models[119]. It is common that the training dataset and the test dataset are not extensive at the time of collection, thus resulting in poor results in practical applications.


With advanced deep learning algorithm, computers can assist clinicians to make an accurate diagnostic decision by providing the right information. For difficulties in endoscopic and interventional procedure, however, information alone is of little help. Complete automation of a manual procedure must be assisted by both deep learning and robotics. For example, there have been marked advancements in robot-assisted endoscopy devices[120]. If these robots can be combined with an intelligent system that detect lesions via ultrasound[112], then it would have a potential to automatically take procure a biopsy sample from the lesion, or perform a surgical procedure, thus eliminating the difficulties of endoscopic and surgical technique.

The other factor that would augment the power of intelligent system is the development of radiological technology itself. The best example would be combination of radiology and endoscopic robotic capsule[121,122]. Recently, with the assistance of neural network, trajectory control and image visualization of endoscopic robotic capsules have been more automatic than they were previously[123]. In the future, if the size of ultrasound probe or other radiological device can be reduced to nanoscale, with an intelligent robotic capsule and intelligent ultrasound probe, fully automated detection and management of any lesion accessible by endoscopic capsules would be possible. Possible path to fully automatic diagnosis and intervention in gastroenterology by combining artificial intelligence with various technologies is shown in Figure 1.

Figure 1
Figure 1 Illustration of a possible path to automatic diagnostic and interventional system in gastroenterology.

The problems inherent to AI itself, that is, data acquisition and annotation, will also be solved by recent technical developments in deep learning models. The best sample would be using unsupervised learning or semi-supervised learning[16,18] to decrease or eliminate the need for radiologist annotation, making development of models faster. For research topics with large public database and well-developed models, such as abdominal CT, transfer learning with pre-trained model and included clinical data can also make training easier, more precise, and faster[124]. In addition to improvement of deep learning model itself, the advancement of advanced deep learning algorithm will enable in-vivo live visualization of lesion detection in endoscope[125], which will be a powerful, clinically applicable function. LeNet-5 architecture can be found in publication by Lecun et al[126].

However, areas with less data availability, such as EUS, cannot be advanced with AI technology alone. For developments of these areas, international collaboration for collection of multi-center image database and clinical data must be done to overcome data scarcity and facilitate precise training and evaluation of models. These multi-center database of image and clinical data will not only benefit model training, but also validation of previous models. Because multi-center data can be more unbiased than data from single source, validation or re-training by multi-center data may improve precision of models by eliminating sampling bias.

With future advancement in data science, deep learning algorithm and medical robotics, AI can play important role in gastrointestinal radiology in the future and may lead a medial revolution.


As demonstrated in the assistance of liver tumor diagnosis and cholangiography, AI has the potential to reduce radiology workload and improve diagnostic specificity, thus making radiologic diagnoses faster and more reliable. In some tasks like the detection of a malignant stricture, we can even hope for machine diagnosis to surpass human diagnosis, making fully automated diagnosis possible. Conversely, for fields where training data collection is more difficult, such as endoscopic ultrasound, training deep learning models would still be slow using today’s technology.

To overcome the problem of lack of technical advancement due to limited data in these areas, particularly in endoscopic procedure, two approaches maybe used. The first solution is to use algorithms that are designed to increase data availability in small medical dataset, such as generative adversarial network and transfer learning. The other suggestion is to build public, global endoscopic image library for model training. In conclusion, though a lot have to be done to make AI universally successful in gastrointestinal radiology, the researchers and developers actually already have the facility to deal with the difficult aspects of this task. Therefore, it is reasonable to expect more scientific advancements and clinical use of AI in the coming decade.


Manuscript source: Invited manuscript

Specialty type: Gastroenterology and hepatology

Country/Territory of origin: Taiwan

Peer-review report’s scientific quality classification

Grade A (Excellent): 0

Grade B (Very good): 0

Grade C (Good): C

Grade D (Fair): D

Grade E (Poor): 0

P-Reviewer: Lu G, Lui TK S-Editor: Wang JL L-Editor: A P-Editor: Li JH

1.  Gans SL, Stoker J, Boermeester MA. Plain abdominal radiography in acute abdominal pain; past, present, and future. Int J Gen Med. 2012;5:525-533.  [PubMed]  [DOI]  [Cited in This Article: ]
2.  Tsapaki V, Rehani M, Saini S. Radiation safety in abdominal computed tomography. Semin Ultrasound CT MR. 2010;31:29-38.  [PubMed]  [DOI]  [Cited in This Article: ]
3.  Hussain SM, Wielopolski PA, Martin DR. Abdominal magnetic resonance imaging at 3.0 T: problem or a promise for the future? Top Magn Reson Imaging. 2005;16:325-335.  [PubMed]  [DOI]  [Cited in This Article: ]
4.  Attenberger UI, Morelli J, Budjan J, Henzler T, Sourbron S, Bock M, Riffel P, Hernando D, Ong MM, Schoenberg SO. Fifty Years of Technological Innovation: Potential and Limitations of Current Technologies in Abdominal Magnetic Resonance Imaging and Computed Tomography. Invest Radiol. 2015;50:584-593.  [PubMed]  [DOI]  [Cited in This Article: ]
5.  Spaulding KA. A review of sonographic identification of abdominal blood vessels and juxtavascular organs. Vet Radiol Ultrasound. 1997;38:4-23.  [PubMed]  [DOI]  [Cited in This Article: ]
6.  Dietrich CF, Maddalena ME, Cui XW, Schreiber-Dietrich D, Ignee A. Liver tumor characterization--review of the literature. Ultraschall Med. 2012;33 Suppl 1:S3-10.  [PubMed]  [DOI]  [Cited in This Article: ]
7.  Ripollés T, Martínez-Pérez MJ, Paredes JM, Vizuete J, García-Martínez E, Jiménez-Restrepo DH. Contrast-enhanced ultrasound in the differentiation between phlegmon and abscess in Crohn's disease and other abdominal conditions. Eur J Radiol. 2013;82:e525-e531.  [PubMed]  [DOI]  [Cited in This Article: ]
8.  Ziech ML, Hummel TZ, Smets AM, Nievelstein RA, Lavini C, Caan MW, Nederveen AJ, Roelofs JJ, Bipat S, Benninga MA, Kindermann A, Stoker J. Accuracy of abdominal ultrasound and MRI for detection of Crohn disease and ulcerative colitis in children. Pediatr Radiol. 2014;44:1370-1378.  [PubMed]  [DOI]  [Cited in This Article: ]
9.  Faccioli N, Dietrich CF, Foti G, Santi E, Comai A, D'Onofrio M. Activity-Based Cost Analysis of Including Contrast-Enhanced Ultrasound (CEUS) in the Diagnostic Pathway of Focal Pancreatic Lesions Detected by Abdominal Ultrasound. Ultraschall Med. 2019;40:618-624.  [PubMed]  [DOI]  [Cited in This Article: ]
10.  Obermeyer Z, Emanuel EJ. Predicting the Future - Big Data, Machine Learning, and Clinical Medicine. N Engl J Med. 2016;375:1216-1219.  [PubMed]  [DOI]  [Cited in This Article: ]
11.  Litjens G, Kooi T, Bejnordi BE, Setio AAA, Ciompi F, Ghafoorian M, van der Laak JAWM, van Ginneken B, Sánchez CI. A survey on deep learning in medical image analysis. Med Image Anal. 2017;42:60-88.  [PubMed]  [DOI]  [Cited in This Article: ]
12.  Pesapane F, Codari M, Sardanelli F. Artificial intelligence in medical imaging: threat or opportunity? Eur Radiol Exp. 2018;2:35.  [PubMed]  [DOI]  [Cited in This Article: ]
13.  European Society of Radiology (ESR). Impact of artificial intelligence on radiology: a EuroAIM survey among members of the European Society of Radiology. Insights Imaging. 2019;10:105.  [PubMed]  [DOI]  [Cited in This Article: ]
14.  Collado-Mesa F, Alvarez E, Arheart K. The Role of Artificial Intelligence in Diagnostic Radiology: A Survey at a Single Radiology Residency Training Program. J Am Coll Radiol. 2018;15:1753-1757.  [PubMed]  [DOI]  [Cited in This Article: ]
15.  Halevy A, Norvig P, Pereira F. The Unreasonable Effectiveness of Data. EEE Intell Syst. 2009;24:8-12.  [PubMed]  [DOI]  [Cited in This Article: ]
16.  Khan FM  Semi-supervised transductive regression for survival analysis in medical prognostics, 2016. Available from:  [PubMed]  [DOI]  [Cited in This Article: ]
17.  Zhou Y, Wang Y, Tang P, Bai S, Shen W, Fishman E, Yuille A.   Semi-Supervised 3D Abdominal Multi-Organ Segmentation Via Deep Multi-Planar Co-Training. In: 2019 IEEE Winter Conference on Applications of Computer Vision (WACV); 2019 Jan 7-11; Waikoloa, USA. IEEE, 2019: 121-140.  [PubMed]  [DOI]  [Cited in This Article: ]
18.  Chaitanya K, Karani N, Baumgartner CF, Becker A, Donati O, Konukoglu E.   Semi-supervised and Task-Driven Data Augmentation. In: Chung ACS, Gee JC, Yushkevich PA, Bao S. Information Processing in Medical Imaging. Cham: Springer International Publishing, 2019: 29-41.  [PubMed]  [DOI]  [Cited in This Article: ]
19.  Sergio A, Cristofori C, Cardin R, Pivetta G, Ragazzi R, Baldan A, Girardi L, Cillo U, Burra P, Giacomin A, Farinati F. Transcatheter arterial chemoembolization (TACE) in hepatocellular carcinoma (HCC): the role of angiogenesis and invasiveness. Am J Gastroenterol. 2008;103:914-921.  [PubMed]  [DOI]  [Cited in This Article: ]
20.  McGhana JP, Dodd GD 3rd. Radiofrequency ablation of the liver: current status. AJR Am J Roentgenol. 2001;176:3-16.  [PubMed]  [DOI]  [Cited in This Article: ]
21.  Moore TJ, Peterson LM, Harrington DP, Smith RJ. Successful arterial embolization of an insulinoma. JAMA. 1982;248:1353-1355.  [PubMed]  [DOI]  [Cited in This Article: ]
22.  Uflacker R. Arterial embolization as definitive treatment for benign insulinoma of the pancreas. J Vasc Interv Radiol. 1992;3:639-44; discussion 644.  [PubMed]  [DOI]  [Cited in This Article: ]
23.  Peppa M, Brountzos E, Economopoulos N, Boutati E, Pikounis V, Patapis P, Economopoulos T, Raptis SA, Hadjidakis D. Embolization as an alternative treatment of insulinoma in a patient with multiple endocrine neoplasia type 1 syndrome. Cardiovasc Intervent Radiol. 2009;32:807-811.  [PubMed]  [DOI]  [Cited in This Article: ]
24.  Girelli R, Frigerio I, Salvia R, Barbi E, Tinazzi Martini P, Bassi C. Feasibility and safety of radiofrequency ablation for locally advanced pancreatic cancer. Br J Surg. 2010;97:220-225.  [PubMed]  [DOI]  [Cited in This Article: ]
25.  Hadjicostas P, Malakounides N, Varianos C, Kitiris E, Lerni F, Symeonides P. Radiofrequency ablation in pancreatic cancer. HPB (Oxford). 2006;8:61-64.  [PubMed]  [DOI]  [Cited in This Article: ]
26.  Jones RL, McCall J, Adam A, O'Donnell D, Ashley S, Al-Muderis O, Thway K, Fisher C, Judson IR. Radiofrequency ablation is a feasible therapeutic option in the multi modality management of sarcoma. Eur J Surg Oncol. 2010;36:477-482.  [PubMed]  [DOI]  [Cited in This Article: ]
27.  Ramaswamy RS, Choi HW, Mouser HC, Narsinh KH, McCammack KC, Treesit T, Kinney TB. Role of interventional radiology in the management of acute gastrointestinal bleeding. World J Radiol. 2014;6:82-92.  [PubMed]  [DOI]  [Cited in This Article: ]
28.  Takeuchi N, Emori M, Yoshitani M, Soneda J, Takada M, Nomura Y. Gastrointestinal Bleeding Successfully Treated Using Interventional Radiology. Gastroenterology Res. 2017;10:259-267.  [PubMed]  [DOI]  [Cited in This Article: ]
29.  Cura M, Haskal Z, Lopera J. Diagnostic and interventional radiology for Budd-Chiari syndrome. Radiographics. 2009;29:669-681.  [PubMed]  [DOI]  [Cited in This Article: ]
30.  Ikeda O, Tamura Y, Nakasone Y, Yamashita Y. Celiac artery stenosis/occlusion treated by interventional radiology. Eur J Radiol. 2009;71:369-377.  [PubMed]  [DOI]  [Cited in This Article: ]
31.  Rösch T, Lorenz R, Braig C, Feuerbach S, Siewert JR, Schusdziarra V, Classen M. Endoscopic ultrasound in pancreatic tumor diagnosis. Gastrointest Endosc. 1991;37:347-352.  [PubMed]  [DOI]  [Cited in This Article: ]
32.  Kelly S, Harris KM, Berry E, Hutton J, Roderick P, Cullingworth J, Gathercole L, Smith MA. A systematic review of the staging performance of endoscopic ultrasound in gastro-oesophageal carcinoma. Gut. 2001;49:534-539.  [PubMed]  [DOI]  [Cited in This Article: ]
33.  Williams DB, Sahai AV, Aabakken L, Penman ID, van Velse A, Webb J, Wilson M, Hoffman BJ, Hawes RH. Endoscopic ultrasound guided fine needle aspiration biopsy: a large single centre experience. Gut. 1999;44:720-726.  [PubMed]  [DOI]  [Cited in This Article: ]
34.  Kahaleh M, Shami VM, Conaway MR, Tokar J, Rockoff T, De La Rue SA, de Lange E, Bassignani M, Gay S, Adams RB, Yeaton P. Endoscopic ultrasound drainage of pancreatic pseudocyst: a prospective comparison with conventional endoscopic drainage. Endoscopy. 2006;38:355-359.  [PubMed]  [DOI]  [Cited in This Article: ]
35.  Clark K, Vendt B, Smith K, Freymann J, Kirby J, Koppel P, Moore S, Phillips S, Maffitt D, Pringle M, Tarbox L, Prior F. The Cancer Imaging Archive (TCIA): maintaining and operating a public information repository. J Digit Imaging. 2013;26:1045-1057.  [PubMed]  [DOI]  [Cited in This Article: ]
36.  Roth H, Farag A, Turkbey EB, Lu L, Liu J, Summers RM.   Data From Pancreas-CT, 2016. Available from:  [PubMed]  [DOI]  [Cited in This Article: ]
37.  Roth HR, Lu L, Farag A, Shin H-C, Liu J, Turkbey E, Summers RM.   DeepOrgan: Multi-level Deep Convolutional Networks for Automated Pancreas Segmentation. 2015 Preprint. Available from: arXiv:150606448.  [PubMed]  [DOI]  [Cited in This Article: ]
38.  Xu Z, Lee CP, Heinrich MP, Modat M, Rueckert D, Ourselin S, Abramson RG, Landman BA. Evaluation of Six Registration Methods for the Human Abdomen on Clinically Acquired CT. IEEE Trans Biomed Eng. 2016;63:1563-1572.  [PubMed]  [DOI]  [Cited in This Article: ]
39.  Synapse  Multi-Atlas Labeling Beyond the Cranial Vault - Workshop and Challenge - syn3193805 - Wiki. Available from:!Synapse:syn3193805/wiki/89480.  [PubMed]  [DOI]  [Cited in This Article: ]
40.  Li X, Jiang F, Guo Y, Jin Z, Wang Y. Computer-aided diagnosis of gastrointestinal stromal tumors: a radiomics method on endoscopic ultrasound image. Int J Comput Assist Radiol Surg. 2019;14:1635-1645.  [PubMed]  [DOI]  [Cited in This Article: ]
41.  Jaramillo M, Ruano J, Gómez M, Romero E.   Endoscopic ultrasound database of the pancreas. In: Proceedings Volume 11583, 16th International Symposium on Medical Information Processing and Analysis; 2020 Nov 3; Lima, Peru. International Society for Optics and Photonics, 2020: 115830G.  [PubMed]  [DOI]  [Cited in This Article: ]
42.  Yan K, Wang X, Lu L, Summers RM. DeepLesion: automated mining of large-scale lesion annotations and universal lesion detection with deep learning. J Med Imaging (Bellingham). 2018;5:036501.  [PubMed]  [DOI]  [Cited in This Article: ]
43.  Li Z, Zhang S, Zhang J, Huang K, Wang Y, Yu Y.   MVP-Net: Multi-view FPN with Position-Aware Attention for Deep Universal Lesion Detection. In: Shen D, Liu T, Peters TM, Staib LH, Essert C, Zhou S, Yap RT, Khan A, editors. Medical Image Computing and Computer Assisted Intervention - MICCAI 2019. Cham: Springer International Publishing, 2019: 13-21.  [PubMed]  [DOI]  [Cited in This Article: ]
44.  Schellinger PD, Jansen O, Fiebach JB, Hacke W, Sartor K. A standardized MRI stroke protocol: comparison with CT in hyperacute intracerebral hemorrhage. Stroke. 1999;30:765-768.  [PubMed]  [DOI]  [Cited in This Article: ]
45.  Bammer R. Basic principles of diffusion-weighted imaging. Eur J Radiol. 2003;45:169-184.  [PubMed]  [DOI]  [Cited in This Article: ]
46.  Amit G, Hadad O, Alpert S, Tlusty T, Gur Y, Ben-Ari R, Hashoul S.   Hybrid Mass Detection in Breast MRI Combining Unsupervised Saliency Analysis and Deep Learning. In: Descoteaux M, Maier-Hein L, Franz A, Jannin P, Collins DL, Duchesne S, editors. Medical Image Computing and Computer Assisted Intervention - MICCAI 2017. Cham: Springer International Publishing, 2017: 594-602.  [PubMed]  [DOI]  [Cited in This Article: ]
47.  Kijowski R, Liu F, Caliva F, Pedoia V. Deep Learning for Lesion Detection, Progression, and Prediction of Musculoskeletal Disease. J Magn Reson Imaging. 2020;52:1607-1619.  [PubMed]  [DOI]  [Cited in This Article: ]
48.  Su H, Maji S, Kalogerakis E, Learned-Miller E.   Multi-View Convolutional Neural Networks for 3D Shape Recognition, 2015. Available from:  [PubMed]  [DOI]  [Cited in This Article: ]
49.  Setio AA, Ciompi F, Litjens G, Gerke P, Jacobs C, van Riel SJ, Wille MM, Naqibullah M, Sanchez CI, van Ginneken B. Pulmonary Nodule Detection in CT Images: False Positive Reduction Using Multi-View Convolutional Networks. IEEE Trans Med Imaging. 2016;35:1160-1169.  [PubMed]  [DOI]  [Cited in This Article: ]
50.  Kang G, Liu K, Hou B, Zhang N. 3D multi-view convolutional neural networks for lung nodule classification. PLoS One. 2017;12:e0188290.  [PubMed]  [DOI]  [Cited in This Article: ]
51.  El-Regaily SA, Salem MAM, Abdel Aziz MH, Roushdy MI. Multi-view Convolutional Neural Network for lung nodule false positive reduction. Expert Syst Appl. 2020;162:113017.  [PubMed]  [DOI]  [Cited in This Article: ]
52.  Sun L, Wang J, Hu Z, Xu Y, Cui Z. Multi-View Convolutional Neural Networks for Mammographic Image Classification. IEEE Access. 2019;7:126273-126282.  [PubMed]  [DOI]  [Cited in This Article: ]
53.  Birenbaum A, Greenspan H.   Longitudinal Multiple Sclerosis Lesion Segmentation Using Multi-view Convolutional Neural Networks. In: Carneiro G, Mateus D, Peter L, Bradley A, Tavares JMRS, Belagiannis V, Papa JP, Nascimento JC, Loog M, Lu Z, Cardoso JS, Cornebise J. Deep Learning and Data Labeling for Medical Applications. Cham: Springer International Publishing, 2016: 58-67.  [PubMed]  [DOI]  [Cited in This Article: ]
54.  Zlocha M, Dou Q, Glocker B.   Improving RetinaNet for CT Lesion Detection with Dense Masks from Weak RECIST Labels. In: Shen D, Liu T, Peters TM, Staib LH, Essert C, Zhou S, Yap RT, Khan A. Medical Image Computing and Computer Assisted Intervention - MICCAI 2019. Cham: Springer International Publishing, 2019: 402-410.  [PubMed]  [DOI]  [Cited in This Article: ]
55.  Lin TY, Goyal P, Girshick R, He K, Dollar P. Focal Loss for Dense Object Detection. IEEE Trans Pattern Anal Mach Intell. 2020;42:318-327.  [PubMed]  [DOI]  [Cited in This Article: ]
56.  Tang Y, Yan K, Tang Y, Liu J, Xiao J, Summers RM.   Uldor: A Universal Lesion Detector For Ct Scans With Pseudo Masks And Hard Negative Example Mining. In: 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019); 2019 Apr 8-11; Venice, Italy. IEEE, 2019: 833-836.  [PubMed]  [DOI]  [Cited in This Article: ]
57.  Harbin WP, Mueller PR, Ferrucci JT Jr. Transhepatic cholangiography: complicatons and use patterns of the fine-needle technique: a multi-institutional survey. Radiology. 1980;135:15-22.  [PubMed]  [DOI]  [Cited in This Article: ]
58.  Korman J, Cosgrove J, Furman M, Nathan I, Cohen J. The role of endoscopic retrograde cholangiopancreatography and cholangiography in the laparoscopic era. Ann Surg. 1996;223:212-216.  [PubMed]  [DOI]  [Cited in This Article: ]
59.  Ney MV, Maluf-Filho F, Sakai P, Zilberstein B, Gama-Rodrigues J, Rosa H. Echo-endoscopy versus endoscopic retrograde cholangiography for the diagnosis of choledocholithiasis: the influence of the size of the stone and diameter of the common bile duct. Arq Gastroenterol. 2005;42:239-243.  [PubMed]  [DOI]  [Cited in This Article: ]
60.  Maranki J, Hernandez AJ, Arslan B, Jaffan AA, Angle JF, Shami VM, Kahaleh M. Interventional endoscopic ultrasound-guided cholangiography: long-term experience of an emerging alternative to percutaneous transhepatic cholangiography. Endoscopy. 2009;41:532-538.  [PubMed]  [DOI]  [Cited in This Article: ]
61.  Angulo P, Lindor KD. Primary sclerosing cholangitis. Hepatology. 1999;30:325-332.  [PubMed]  [DOI]  [Cited in This Article: ]
62.  O'Neill JA Jr. Choledochal cyst. Curr Probl Surg. 1992;29:361-410.  [PubMed]  [DOI]  [Cited in This Article: ]
63.  Sahni VA, Mortele KJ.   Magnetic Resonance Cholangiopancreatography. In: Hawkey CJ, Bosch J, Richter JE, Garcia-Tsao G, Chan FKL. Textbook of Clinical Gastroenterology and Hepatology. John Wiley & Sons, 2012: 1021-1026.  [PubMed]  [DOI]  [Cited in This Article: ]
64.  Fleischmann D, Ringl H, Schöfl R, Pötzi R, Kontrus M, Henk C, Bankier AA, Kettenbach J, Mostbeck GH. Three-dimensional spiral CT cholangiography in patients with suspected obstructive biliary disease: comparison with endoscopic retrograde cholangiography. Radiology. 1996;198:861-868.  [PubMed]  [DOI]  [Cited in This Article: ]
65.  Varghese JC, Liddell RP, Farrell MA, Murray FE, Osborne DH, Lee MJ. Diagnostic accuracy of magnetic resonance cholangiopancreatography and ultrasound compared with direct cholangiography in the detection of choledocholithiasis. Clin Radiol. 2000;55:25-35.  [PubMed]  [DOI]  [Cited in This Article: ]
66.  Liang C, Mao H, Wang Q, Han D, Li Yuxia L, Yue J, Cui H, Sun F, Yang R. Diagnostic performance of magnetic resonance cholangiopancreatography in malignant obstructive jaundice. Cell Biochem Biophys. 2011;61:383-388.  [PubMed]  [DOI]  [Cited in This Article: ]
67.  McSweeney SE, Kim TK, Jang HJ, Khalili K. Biliary anatomy in potential right hepatic lobe living donor liver transplantation (LDLT): the utility of CT cholangiography in the setting of inconclusive MRCP. Eur J Radiol. 2012;81:6-12.  [PubMed]  [DOI]  [Cited in This Article: ]
68.  De Castro VL, Moura EG, Chaves DM, Bernardo WM, Matuguma SE, Artifon EL. Endoscopic ultrasound versus magnetic resonance cholangiopancreatography in suspected choledocholithiasis: A systematic review. Endosc Ultrasound. 2016;5:118-128.  [PubMed]  [DOI]  [Cited in This Article: ]
69.  Guarise A, Baltieri S, Mainardi P, Faccioli N. Diagnostic accuracy of MRCP in choledocholithiasis. Radiol Med. 2005;109:239-251.  [PubMed]  [DOI]  [Cited in This Article: ]
70.  de Jong K, Nio CY, Mearadji B, Phoa SS, Engelbrecht MR, Dijkgraaf MG, Bruno MJ, Fockens P. Disappointing interobserver agreement among radiologists for a classifying diagnosis of pancreatic cysts using magnetic resonance imaging. Pancreas. 2012;41:278-282.  [PubMed]  [DOI]  [Cited in This Article: ]
71.  Uribarri-Gonzalez L, Keane MG, Pereira SP, Iglesias-García J, Dominguez-Muñoz JE, Lariño-Noia J. Agreement among Magnetic Resonance Imaging/Magnetic Resonance Cholangiopancreatography (MRI-MRCP) and Endoscopic Ultrasound (EUS) in the evaluation of morphological features of Branch Duct Intraductal Papillary Mucinous Neoplasm (BD-IPMN). Pancreatology. 2018;18:170-175.  [PubMed]  [DOI]  [Cited in This Article: ]
72.  Ringe KI, Vo Chieu VD, Wacker F, Lenzen H, Manns MP, Hundt C, Schmidt B, Winther HB. Fully automated detection of primary sclerosing cholangitis (PSC)-compatible bile duct changes based on 3D magnetic resonance cholangiopancreatography using machine learning. Eur Radiol. 2021;31:2482-2489.  [PubMed]  [DOI]  [Cited in This Article: ]
73.  Tang Y, Chen X, Wang W, Wu J, Zheng Y, Q Guo, Shu J, Su S.   Identifying Periampullary Regions in MRI Images Using Deep Learning. 2020 Preprint. Available from: ResearchSquare:109396.  [PubMed]  [DOI]  [Cited in This Article: ]
74.  AL-Oudat MA, Oudat MA, Migdady H, Munaizel TA, Mahmoud MA, Jaafreh S.   Automatic Intrahepatic Biliary Segmentation Based Image Processing Techniques using Magnetic Resonance Images. 2020 Preprint. Available from: ResearchSquare:106936.  [PubMed]  [DOI]  [Cited in This Article: ]
75.  Huang L, Lu X, Huang X, Zou X, Wu L, Zhou Z, Wu D, Tang D, Chen D, Wan X, Zhu Z, Deng T, Shen L, Liu J, Zhu Y, Gong D, Zhong Y, Liu F, Yu H. Intelligent difficulty scoring and assistance system for endoscopic extraction of common bile duct stones based on deep learning: multicenter study. Endoscopy. 2020;.  [PubMed]  [DOI]  [Cited in This Article: ]
76.  Zhang J, Zhu L, Yao L, Ding X, Chen D, Wu H, Lu Z, Zhou W, Zhang L, An P, Xu B, Tan W, Hu S, Cheng F, Yu H. Deep learning-based pancreas segmentation and station recognition system in EUS: development and validation of a useful training tool (with video). Gastrointest Endosc 2020; 92: 874-885. e3.  [PubMed]  [DOI]  [Cited in This Article: ]
77.  Chalasani N, Said A, Ness R, Hoen H, Lumeng L. Screening for hepatocellular carcinoma in patients with cirrhosis in the United States: results of a national survey. Am J Gastroenterol. 1999;94:2224-2229.  [PubMed]  [DOI]  [Cited in This Article: ]
78.  Boraschi P, Tarantini G, Pacciardi F, Donati F.   Dynamic and Multi-phase Contrast-Enhanced CT Scan. In: Radu-Ionita F, Pyrsopoulos NT, Jinga M, Tintoiu IC, Sun Z, Bontas E, editors. Liver Diseases: A Multidisciplinary Textbook. Cham: Springer International Publishing, 2020: 479-491.  [PubMed]  [DOI]  [Cited in This Article: ]
79.  Tejeda-Maldonado J, García-Juárez I, Aguirre-Valadez J, González-Aguirre A, Vilatobá-Chapa M, Armengol-Alonso A, Escobar-Penagos F, Torre A, Sánchez-Ávila JF, Carrillo-Pérez DL. Diagnosis and treatment of hepatocellular carcinoma: An update. World J Hepatol. 2015;7:362-376.  [PubMed]  [DOI]  [Cited in This Article: ]
80.  Hussain SM, Terkivatan T, Zondervan PE, Lanjouw E, de Rave S, Ijzermans JN, de Man RA. Focal nodular hyperplasia: findings at state-of-the-art MR imaging, US, CT, and pathologic analysis. Radiographics. 2004;24:3-17; discussion 18.  [PubMed]  [DOI]  [Cited in This Article: ]
81.  Choi JY, Lee HC, Yim JH, Shim JH, Lim YS, Shin YM, Yu ES, Suh DJ. Focal nodular hyperplasia or focal nodular hyperplasia-like lesions of the liver: a special emphasis on diagnosis. J Gastroenterol Hepatol. 2011;26:1004-1009.  [PubMed]  [DOI]  [Cited in This Article: ]
82.  Mathieu D, Bruneton JN, Drouillard J, Pointreau CC, Vasile N. Hepatic adenomas and focal nodular hyperplasia: dynamic CT study. Radiology. 1986;160:53-58.  [PubMed]  [DOI]  [Cited in This Article: ]
83.  Toft J, Hadden WJ, Laurence JM, Lam V, Yuen L, Janssen A, Pleass H. Imaging modalities in the diagnosis of pancreatic adenocarcinoma: A systematic review and meta-analysis of sensitivity, specificity and diagnostic accuracy. Eur J Radiol. 2017;92:17-23.  [PubMed]  [DOI]  [Cited in This Article: ]
84.  Chakraborty J, Midya A, Gazit L, Attiyeh M, Langdon-Embry L, Allen PJ, Do RKG, Simpson AL. CT radiomics to predict high-risk intraductal papillary mucinous neoplasms of the pancreas. Med Phys. 2018;45:5019-5029.  [PubMed]  [DOI]  [Cited in This Article: ]
85.  Li R, Cai P, Ma KS, Ding SY, Guo DY, Yan XC. Dynamic enhancement patterns of intrahepatic cholangiocarcinoma in cirrhosis on contrast-enhanced computed tomography: risk of misdiagnosis as hepatocellular carcinoma. Sci Rep. 2016;6:26772.  [PubMed]  [DOI]  [Cited in This Article: ]
86.  Galassi M, Iavarone M, Rossi S, Bota S, Vavassori S, Rosa L, Leoni S, Venerandi L, Marinelli S, Sangiovanni A, Veronese L, Fraquelli M, Granito A, Golfieri R, Colombo M, Bolondi L, Piscaglia F. Patterns of appearance and risk of misdiagnosis of intrahepatic cholangiocarcinoma in cirrhosis at contrast enhanced ultrasound. Liver Int. 2013;33:771-779.  [PubMed]  [DOI]  [Cited in This Article: ]
87.  Massarweh NN, El-Serag HB. Epidemiology of Hepatocellular Carcinoma and Intrahepatic Cholangiocarcinoma. Cancer Control. 2017;24:1073274817729245.  [PubMed]  [DOI]  [Cited in This Article: ]
88.  Zhou XD, Tang ZY, Fan J, Zhou J, Wu ZQ, Qin LX, Ma ZC, Sun HC, Qiu SJ, Yu Y, Ren N, Ye QH, Wang L, Ye SL. Intrahepatic cholangiocarcinoma: report of 272 patients compared with 5,829 patients with hepatocellular carcinoma. J Cancer Res Clin Oncol. 2009;135:1073-1080.  [PubMed]  [DOI]  [Cited in This Article: ]
89.  Neofytou K, Chrysochos A, Charalambous N, Dietis M, Petridis C, Andreou C, Petrou A. Hepatic epithelioid hemangioendothelioma and the danger of misdiagnosis: report of a case. Case Rep Oncol Med. 2013;2013:243939.  [PubMed]  [DOI]  [Cited in This Article: ]
90.  Mehrabi A, Kashfi A, Fonouni H, Schemmer P, Schmied BM, Hallscheidt P, Schirmacher P, Weitz J, Friess H, Buchler MW, Schmidt J. Primary malignant hepatic epithelioid hemangioendothelioma: a comprehensive review of the literature with emphasis on the surgical therapy. Cancer. 2006;107:2108-2121.  [PubMed]  [DOI]  [Cited in This Article: ]
91.  Yamada S, Shimada M, Utsunomiya T, Morine Y, Imura S, Ikemoto T, Mori H, Hanaoka J, Iwahashi S, Saitoh Y, Asanoma M. Hepatic screlosed hemangioma which was misdiagnosed as metastasis of gastric cancer: report of a case. J Med Invest. 2012;59:270-274.  [PubMed]  [DOI]  [Cited in This Article: ]
92.  Pitman A, Cowan IA, Floyd RA, Munro PL. Measuring radiologist workload: Progressing from RVUs to study ascribable times. J Med Imaging Radiat Oncol. 2018;62:605-618.  [PubMed]  [DOI]  [Cited in This Article: ]
93.  Khan SH, Hedges WP. Workload of consultant radiologists in a large DGH and how it compares to international benchmarks. Clin Radiol. 2013;68:e239-e244.  [PubMed]  [DOI]  [Cited in This Article: ]
94.  Muhi A, Ichikawa T, Motosugi U, Sou H, Sano K, Tsukamoto T, Fatima Z, Araki T. Mass-forming autoimmune pancreatitis and pancreatic carcinoma: differential diagnosis on the basis of computed tomography and magnetic resonance cholangiopancreatography, and diffusion-weighted imaging findings. J Magn Reson Imaging. 2012;35:827-836.  [PubMed]  [DOI]  [Cited in This Article: ]
95.  Zaheer A, Singh VK, Akshintala VS, Kawamoto S, Tsai SD, Gage KL, Fishman EK. Differentiating autoimmune pancreatitis from pancreatic adenocarcinoma using dual-phase computed tomography. J Comput Assist Tomogr. 2014;38:146-152.  [PubMed]  [DOI]  [Cited in This Article: ]
96.  Chiou YY, Chiang JH, Hwang JI, Yen CH, Tsay SH, Chang CY. Acinar cell carcinoma of the pancreas: clinical and computed tomography manifestations. J Comput Assist Tomogr. 2004;28:180-186.  [PubMed]  [DOI]  [Cited in This Article: ]
97.  Das A, Acharya UR, Panda SS, Sabut S. Deep learning based liver cancer detection using watershed transform and Gaussian mixture model techniques. Cogn Syst Res. 2019;54:165-175.  [PubMed]  [DOI]  [Cited in This Article: ]
98.  Vorontsov E, Cerny M, Régnier P, Di Jorio L, Pal CJ, Lapointe R, Vandenbroucke-Menu F, Turcotte S, Kadoury S, Tang A. Deep learning for automated segmentation of liver lesions at CT in patients with colorectal cancer liver metastases. Radiol Artif Intell. 2019;1:180014.  [PubMed]  [DOI]  [Cited in This Article: ]
99.  Kuo C, Cheng S, Lin C, Hsiao K, Lee S.   Texture-based treatment prediction by automatic liver tumor segmentation on computed tomography. In: 2017 International Conference on Computer, Information and Telecommunication Systems (CITS); 2017 July 21-23; Dalian, China. IEEE, 2017: 128-132.  [PubMed]  [DOI]  [Cited in This Article: ]
100.  Huang W, Li N, Lin Z, Huang G, Zong W, Zhou J, Duan Y.   Liver tumor detection and segmentation using kernel-based extreme learning machine. In: 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC); 2013 July 3-7; Osaka, Japan. IEEE, 2013: 3662-3665.  [PubMed]  [DOI]  [Cited in This Article: ]
101.  Li S, Jiang H, Wang Z, Zhang G, Yao YD. An effective computer aided diagnosis model for pancreas cancer on PET/CT images. Comput Methods Programs Biomed. 2018;165:205-214.  [PubMed]  [DOI]  [Cited in This Article: ]
102.  Liu SL, Li S, Guo YT, Zhou YP, Zhang ZD, Lu Y. Establishment and application of an artificial intelligence diagnosis system for pancreatic cancer with a faster region-based convolutional neural network. Chin Med J (Engl). 2019;132:2795-2803.  [PubMed]  [DOI]  [Cited in This Article: ]
103.  Xu J, Jing M, Wang S, Yang C, Chen X. A review of medical image detection for cancers in digestive system based on artificial intelligence. Expert Rev Med Devices. 2019;16:877-889.  [PubMed]  [DOI]  [Cited in This Article: ]
104.  Zhen SH, Cheng M, Tao YB, Wang YF, Juengpanich S, Jiang ZY, Jiang YK, Yan YY, Lu W, Lue JM, Qian JH, Wu ZY, Sun JH, Lin H, Cai XJ. Deep Learning for Accurate Diagnosis of Liver Tumor Based on Magnetic Resonance Imaging and Clinical Data. Front Oncol. 2020;10:680.  [PubMed]  [DOI]  [Cited in This Article: ]
105.  Yasaka K, Akai H, Abe O, Kiryu S. Deep Learning with Convolutional Neural Network for Differentiation of Liver Masses at Dynamic Contrast-enhanced CT: A Preliminary Study. Radiology. 2018;286:887-896.  [PubMed]  [DOI]  [Cited in This Article: ]
106.  Wani S, Keswani RN, Han S, Aagaard EM, Hall M, Simon V, Abidi WM, Banerjee S, Baron TH, Bartel M, Bowman E, Brauer BC, Buscaglia JM, Carlin L, Chak A, Chatrath H, Choudhary A, Confer B, Coté GA, Das KK, DiMaio CJ, Dries AM, Edmundowicz SA, El Chafic AH, El Hajj I, Ellert S, Ferreira J, Gamboa A, Gan IS, Gangarosa LM, Gannavarapu B, Gordon SR, Guda NM, Hammad HT, Harris C, Jalaj S, Jowell PS, Kenshil S, Klapman J, Kochman ML, Komanduri S, Lang G, Lee LS, Loren DE, Lukens FJ, Mullady D, Muthusamy VR, Nett AS, Olyaee MS, Pakseresht K, Perera P, Pfau P, Piraka C, Poneros JM, Rastogi A, Razzak A, Riff B, Saligram S, Scheiman JM, Schuster I, Shah RJ, Sharma R, Spaete JP, Singh A, Sohail M, Sreenarasimhaiah J, Stevens T, Tabibian JH, Tzimas D, Uppal DS, Urayama S, Vitterbo D, Wang AY, Wassef W, Yachimski P, Zepeda-Gomez S, Zuchelli T, Early D. Competence in Endoscopic Ultrasound and Endoscopic Retrograde Cholangiopancreatography, From Training Through Independent Practice. Gastroenterology 2018; 155: 1483-1494. e7.  [PubMed]  [DOI]  [Cited in This Article: ]
107.  Levy MJ, Wiersema MJ. EUS-guided Trucut biopsy. Gastrointest Endosc. 2005;62:417-426.  [PubMed]  [DOI]  [Cited in This Article: ]
108.  Patel R, Varadarajulu S, Wilcox CM. Endoscopic ampullectomy: techniques and outcomes. J Clin Gastroenterol. 2012;46:8-15.  [PubMed]  [DOI]  [Cited in This Article: ]
109.  Tonozuka R, Mukai S, Itoi T. The Role of Artificial Intelligence in Endoscopic Ultrasound for Pancreatic Disorders. Diagnostics (Basel). 2020;11.  [PubMed]  [DOI]  [Cited in This Article: ]
110.  Kikuchi D, Iizuka T, Hoteya S, Yamada A, Furuhata T, Yamashita S, Domon K, Nakamura M, Matsui A, Mitani T, Ogawa O, Kaise M. Prospective Study about the Utility of Endoscopic Ultrasound for Predicting the Safety of Endoscopic Submucosal Dissection in Early Gastric Cancer (T-HOPE 0801). Gastroenterol Res Pract. 2013;2013:329385.  [PubMed]  [DOI]  [Cited in This Article: ]
111.  Cho BJ, Bang CS, Lee JJ, Seo CW, Kim JH. Prediction of Submucosal Invasion for Gastric Neoplasms in Endoscopic Images Using Deep-Learning. J Clin Med. 2020;9.  [PubMed]  [DOI]  [Cited in This Article: ]
112.  Tonozuka R, Itoi T, Nagata N, Kojima H, Sofuni A, Tsuchiya T, Ishii K, Tanaka R, Nagakawa Y, Mukai S. Deep learning analysis for the detection of pancreatic cancer on endosonographic images: a pilot study. J Hepatobiliary Pancreat Sci. 2021;28:95-104.  [PubMed]  [DOI]  [Cited in This Article: ]
113.  Scott IA, Cook D, Coiera EW, Richards B. Machine learning in clinical practice: prospects and pitfalls. Med J Aust 2019; 211: 203-205. e1.  [PubMed]  [DOI]  [Cited in This Article: ]
114.  Goyal S. An Overview of Current Trends, Techniques, Prospects, and Pitfalls of Artificial Intelligence in Breast Imaging. RMI. 2021;14:15-25.  [PubMed]  [DOI]  [Cited in This Article: ]
115.  Mazurowski MA, Buda M, Saha A, Bashir MR. Deep learning in radiology: An overview of the concepts and a survey of the state of the art with focus on MRI. J Magn Reson Imaging. 2019;49:939-954.  [PubMed]  [DOI]  [Cited in This Article: ]
116.  Ahmad R. Reviewing the relationship between machines and radiology: the application of artificial intelligence. Acta Radiol Open. 2021;10:2058460121990296.  [PubMed]  [DOI]  [Cited in This Article: ]
117.  Goodfellow IJ, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, Aaron Courville A, Bengio Y.   Generative Adversarial Networks. 2014 Preprint. Available from: arxiv:1406.2661.  [PubMed]  [DOI]  [Cited in This Article: ]
118.  Sun Y, Wong AKC, Kamel MS. Classification of imbalanced data: a review. Int J Patt Recogn Artif Intell. 2009;23:687-719.  [PubMed]  [DOI]  [Cited in This Article: ]
119.  Roberts M, Driggs D, Thorpe M, Gilbey J, Yeung M, Ursprung S, Aviles-Rivero AI, Etmann C, McCague C, Beer L, Weir-McCall JR, Teng Z, Gkrania-Klotsas E, Covnet A, Rudd JHF, Sala E, Schönlieb CB. Common pitfalls and recommendations for using machine learning to detect and prognosticate for COVID-19 using chest radiographs and CT scans. Nat Mach Intell. 2021;3:199-217.  [PubMed]  [DOI]  [Cited in This Article: ]
120.  Yeung BP, Chiu PW. Application of robotics in gastrointestinal endoscopy: A review. World J Gastroenterol. 2016;22:1811-1825.  [PubMed]  [DOI]  [Cited in This Article: ]
121.  Quaglia C, Buselli E, Webster RJ, Valdastri P, Menciassi A, Dario P. An endoscopic capsule robot: a meso-scale engineering case study. J Micromech Microeng. 2009;19:105007.  [PubMed]  [DOI]  [Cited in This Article: ]
122.  Turan M, Almalioglu Y, Araujo H, Konukoglu E, Sitti M. A non-rigid map fusion-based direct SLAM method for endoscopic capsule robots. Int J Intell Robot Appl. 2017;1:399-409.  [PubMed]  [DOI]  [Cited in This Article: ]
123.  Turan M, Almalioglu Y, Araujo H, Konukoglu E, Sitti M. Deep EndoVO: A recurrent convolutional neural network (RCNN) based visual odometry approach for endoscopic capsule robots. Neurocomputing. 2018;275:1861-1870.  [PubMed]  [DOI]  [Cited in This Article: ]
124.  Cheng PM, Malhi HS. Transfer Learning with Convolutional Neural Networks for Classification of Abdominal Ultrasound Images. J Digit Imaging. 2017;30:234-243.  [PubMed]  [DOI]  [Cited in This Article: ]
125.  de Groof AJ, Struyvenberg MR, Fockens KN, van der Putten J, van der Sommen F, Boers TG, Zinger S, Bisschops R, de With PH, Pouw RE, Curvers WL, Schoon EJ, Bergman JJGHM. Deep learning algorithm detection of Barrett's neoplasia with high accuracy during live endoscopic procedures: a pilot study (with video). Gastrointest Endosc. 2020;91:1242-1250.  [PubMed]  [DOI]  [Cited in This Article: ]
126.  Lecun Y, Bottou L, Bengio Y, Haffner P. Gradient-based learning applied to document recognition. Proc IEEE Inst Electr Electron Eng. 1998;86:2278-2324.  [PubMed]  [DOI]  [Cited in This Article: ]