Artificial neural networks have been used in various fields to solve classification and prediction tasks. However, it is unclear if these may be adequate methods to predict psychological treatment outcomes. This study aimed to evaluate the prognostic accuracy of neural networks using psychological treatment outcomes data.

Three neural network models (TensorFlow, nnet, and monmlp) and a generalised linear regression model were compared in their ability to predict post-treatment remission of depression symptoms in a large naturalistic sample (n = 69,489) of patients accessing low intensity cognitive behavioural therapy. Prognostic accuracy was evaluated using the area under the curve (AUC) in an external cross-validation design.

The AUC of the neural networks in an external test sample ranged from 0.64 to 0.65 and the AUC of the linear regression model was 0.63.

Neural networks can help predict symptom remission in new samples with moderate accuracy, although these models were no more accurate than a simpler inferential statistical linear regression model.

This study introduces an ensemble framework that integrates Vision Transformer (ViT) and Convolutional Neural Networks (CNN) models to leverage their complementary strengths, generating visualized and decision-transparent recommendations for dual-energy X-ray absorptiometry (DXA) scans from chest low-dose computed tomography (LDCT).

The framework was developed using data from 321 individuals and validated with an independent test cohort of 186 individuals. It addresses two classification tasks: (1) distinguishing normal from abnormal bone mineral density (BMD) and (2) differentiating osteoporosis from non-osteoporosis. Three field-of-view (FOV) settings-fitFOV (entire vertebra), halfFOV (vertebral body only), and largeFOV (fitFOV + 20 %)-were analyzed to assess their impact on model performance. Model predictions were weighted and combined to enhance classification accuracy, and visualizations were generated to improve decision transparency. DXA scans were recommended for individuals classified as having abnormal BMD or osteoporosis.

The ensemble framework significantly outperformed individual models in both classification tasks (McNemar test, p < 0.001). In the development cohort, it achieved 91.6 % accuracy for task 1 with largeFOV (area under the receiver operating characteristic curve [AUROC]: 0.97) and 86.0 % accuracy for task 2 with fitFOV (AUROC: 0.94). In the test cohort, it demonstrated 86.6 % accuracy for task 1 (AUROC: 0.93) and 76.9 % accuracy for task 2 (AUROC: 0.99). DXA recommendation accuracy was 91.6 % and 87.1 % in the development and test cohorts, respectively, with notably high accuracy for osteoporosis detection (98.7 % and 100 %).

This combined ViT-CNN framework effectively assesses bone status from LDCT images, particularly when utilizing fitFOV and largeFOV settings. By visualizing classification confidence and vertebral abnormalities, the proposed framework enhances decision transparency and supports clinicians in making informed DXA recommendations following opportunistic osteoporosis screening.

Breast cancer is the second most deadly malignancy in women, behind lung cancer. Despite significant improvements in medical research, breast cancer is still accurately diagnosed with histological analysis. During this procedure, pathologists examine a physical sample for the presence of mitotic cells, or dividing cells. However, the high resolution of histopathology images and the difficulty of manually detecting tiny mitotic nuclei make it particularly challenging to differentiate mitotic cells from other types of cells. Numerous studies have addressed the detection and classification of mitosis, owing to increasing capacity and developments in automated approaches. The combination of machine learning and deep learning techniques has greatly revolutionized the process of identifying mitotic cells by offering automated, precise, and efficient solutions. In the last ten years, several pioneering methods have been presented, advancing towards practical applications in clinical settings. Unlike other forms of cancer, breast cancer and gliomas are categorized according to the number of mitotic divisions. Numerous papers have been published on techniques for identifying mitosis due to easy access to datasets and open competitions. Convolutional neural networks and other deep learning architectures can precisely identify mitotic cells, significantly decreasing the amount of labor that pathologists must perform. This article examines the techniques used over the past decade to identify and classify mitotic cells in histologically stained breast cancer hematoxylin and eosin images. Furthermore, we examine the benefits of current research techniques and predict forthcoming developments in the investigation of breast cancer mitosis, specifically highlighting machine learning and deep learning.

Patients with metastatic bone disease are at risk of pathological femoral fractures and may require prophylactic surgical fixation. Current clinical decision support tools often overestimate fracture risk, leading to overtreatment. While novel scores integrating femoral strength assessment via finite element (FE) models show promise, they require 3D imaging, extensive computation, and are difficult to automate. Predicting femoral strength directly from single 2D radiographic projections using convolutional neural networks (CNNs) could address these limitations, but this approach has not yet been explored for femora with metastatic lesions. This study aimed to test whether CNNs can accurately predict strength of femora with metastatic lesions from single 2D radiographic projections.

CNNs with various architectures were developed and trained using an FE model generated training dataset. This training dataset was based on 36,000 modified computed tomography (CT) scans, created by randomly inserting artificial lytic lesions into the CT scans of 36 intact anatomical femoral specimens. From each modified CT scan, an anterior-posterior 2D projection was generated and femoral strength in one-legged stance was determined using nonlinear FE models. Following training, the CNN performance was evaluated on an independent experimental test dataset consisting of 31 anatomical femoral specimens (16 intact, 15 with artificial lytic lesions). 2D projections of each specimen were created from corresponding CT scans and femoral strength was assessed in mechanical tests. The CNNs' performance was evaluated using linear regression analysis and compared to 2D densitometric predictors (bone mineral density and content) and CT-based 3D FE models.

All CNNs accurately predicted the experimentally measured strength in femora with and without metastatic lesions of the test dataset (R²≥0.80, CCC≥0.81). In femora with metastatic lesions, the performance of the CNNs (best: R²=0.84, CCC=0.86) was considerably superior to 2D densitometric predictors (R²≤0.07) and slightly inferior to 3D FE models (R²=0.90, CCC=0.94).

CNNs, trained on a large dataset generated via FE models, predicted experimentally measured strength of femora with artificial metastatic lesions with accuracy comparable to 3D FE models. By eliminating the need for 3D imaging and reducing computational demands, this novel approach demonstrates potential for application in a clinical setting.

To develop a deep learning (DL) model based on ultrasound (US) images of lymph nodes for predicting cervical lymph node metastasis (CLNM) in postoperative patients with differentiated thyroid carcinoma (DTC).

Retrospective collection of 352 lymph nodes from 330 patients with cytopathology findings between June 2021 and December 2023 at our institution. The database was randomly divided into the training and test cohort at an 8:2 ratio. The DL basic model of longitudinal and cross-sectional of lymph nodes was constructed based on ResNet50 respectively, and the results of the 2 basic models were fused (1:1) to construct a longitudinal + cross-sectional DL model. Univariate and multivariate analyses were used to assess US features and construct a conventional US model. Subsequently, a combined model was constructed by integrating DL and US.

The diagnostic accuracy of the longitudinal + cross-sectional DL model was higher than that of longitudinal or cross-sectional alone. The area under the curve (AUC) of the combined model (US + DL) was 0.855 (95% CI, 0.767-0.942) and the accuracy, sensitivity, and specificity were 0.786 (95% CI, 0.671-0.875), 0.972 (95% CI, 0.855-0.999), and 0.588 (95% CI, 0.407-0.754), respectively. Compared with US and DL models, the integrated discrimination improvement and net reclassification improvement of the combined models are both positive.

This preliminary study shows that the DL model based on US images of lymph nodes has a high diagnostic efficacy for predicting CLNM in postoperative patients with DTC, and the combined model of US+DL is superior to single conventional US and DL for predicting CLNM in this population.

We innovatively used DL of lymph node US images to predict the status of cervical lymph nodes in postoperative patients with DTC.

Accurate airway segmentation is vital for diagnosing and managing lung diseases, yet it remains challenging due to data imbalance and difficulty detecting small airway branches. This study proposes AirSeg, a learnable interconnected attention framework incorporating advanced attention mechanisms and a learnable embedding module, to enhance airway segmentation accuracy in computed tomography (CT) images. The proposed framework integrates multiple attention mechanisms, including image, positional, semantic, self-channel, and cross-spatial attention, to refine feature representations at various network and data levels. Additionally, a learnable variance-based embedding module dynamically adjusts input features, improving robustness against spatial inconsistencies and noise. This improves the model's robustness to spatial inconsistencies and noise, leading to more reliable segmentation results, especially in clinically challenging regions. AirSeg can be integrated with any UNet-like network with flexibility. The framework was evaluated on two datasets (in vivo and in situ) using several UNet-based architectures, comparing performance with and without AirSeg integration. Training employed data augmentation, a hybrid loss function combining Dice Similarity Coefficient and Intersection over Union losses, and statistical analysis to assess accuracy improvements. Integrating AirSeg into segmentation models led to statistically significant improvements in accuracy. Specifically, accuracy increased by 16.18% (p = 0.0035) for in vivo datasets and by 10.32% (p = 0.0097) for in situ datasets. These enhancements enable more precise identification of airway structures, including small branches, critical for early diagnosis and treatment planning in pulmonary care. The proposed model achieved a weighted average accuracy improvement of 12.43% (p = 0.0004) over other conventional models. AirSeg demonstrated superior performance in capturing both global structures and fine details, effectively segmenting large airways and intricate branches. Ablation studies validated the contributions and impact of individual attention mechanisms and the embedding module. The improvement in accuracy translates to more precise airway segmentation, enhancing the detection of small branches crucial for early diagnosis and treatment planning. The statistically significant p-values confirm that these gains are reliable, reducing manual correction efforts and improving the efficiency of automated airway analysis in clinical settings.

Deep learning methods provide enormous promise in automating manually intense tasks such as medical image segmentation and provide workflow assistance to clinical experts. Deep neural networks (DNN) require a significant amount of training examples and a variety of expert opinions to capture the nuances and the context, a challenging proposition in oncological studies (H. Wang et al., Nature, vol. 620, no. 7972, pp. 47-60, Aug 2023). Inter-reader variability among clinical experts is a real-world problem that severely impacts the generalization of DNN reproducibility. This study proposes quantifying the variability in DNN performance using expert opinions and exploring strategies to train the network and adapt between expert opinions. We address the inter-reader variability problem in the context of prostate gland segmentation using a well-studied DNN, the 3D U-Net model. Reference data includes magnetic resonance imaging (MRI, T2-weighted) with prostate glandular anatomy annotations from two expert readers (R#1, n = 342 and R#2, n = 204). 3D U-Net was trained and tested with individual expert examples (R#1 and R#2) and had an average Dice coefficient of 0.825 (CI, [0.81 0.84]) and 0.85 (CI, [0.82 0.88]), respectively. Combined training with a representative cohort proportion (R#1, n = 100 and R#2, n = 150) yielded enhanced model reproducibility across readers, achieving an average test Dice coefficient of 0.863 (CI, [0.85 0.87]) for R#1 and 0.869 (CI, [0.87 0.88]) for R#2. We re-evaluated the model performance across the gland volumes (large, small) and found improved performance for large gland size with an average Dice coefficient to be at 0.846 [CI, 0.82 0.87] and 0.872 [CI, 0.86 0.89] for R#1 and R#2, respectively, estimated using fivefold cross-validation. Performance for small gland sizes diminished with average Dice of 0.8 [0.79, 0.82] and 0.8 [0.79, 0.83] for R#1 and R#2, respectively.

Deep learning has been successfully applied to histopathology image classification tasks. However, the performance of deep models is data-driven, and the acquisition and annotation of pathological image samples are difficult, which limit the model's performance. Compared to whole slide images (WSI) of patients, histopathology image datasets of animal models are easier to acquire and annotate. Therefore, this paper proposes an unsupervised domain adaptation method based on semantic correlation clustering for histopathology image classification. The aim is to utilize Minmice model histopathology image dataset to achieve the classification and recognition of human WSIs. Firstly, the multi-scale fused features extracted from the source and target domains are normalized and mapped. In the new feature space, the cosine distance between class centers is used to measure the semantic correlation between categories. Then, the domain centers, class centers, and sample distributions are self-constrainedly aligned. Multi-granular information is applied to achieve cross-domain semantic correlation knowledge transfer between classes. Finally, the probabilistic heatmap is used to visualize the model's prediction results and annotate the cancerous regions in WSIs. Experimental results show that the proposed method has high classification accuracy for WSI, and the annotated result is close to manual annotation, indicating its potential for clinical applications.

Study DesignCross-sectional study.ObjectivesImaging classification of adolescent idiopathic scoliosis (AIS) is directly related to the surgical strategy, but the artificial classification is complex and depends on doctors' experience. This study investigated deep learning-based automated classification methods (DL group) for AIS and validated the consistency of machine classification and manual classification (M group).MethodsA total of 506 cases (81 males and 425 females) and 1812 AIS full spine images in the anteroposterior (AP), lateral (LAT), left bending (LB) and right bending (RB) positions were retrospectively used for training. The mean age was 13.6 ± 1.8. The mean maximum Cobb angle was 46.8 ± 12.0. U-Net semantic segmentation neural network technology and deep learning methods were used to automatically segment and establish the alignment relationship between multiple views of the spine, and to extract spinal features such as the Cobb angle. The type of each test case was automatically calculated according to Lenke's rule. An additional 107 cases of adolescent idiopathic scoliosis imaging were prospectively used for testing. The consistency of the DL group and M group was compared.ResultsAutomatic vertebral body segmentation and recognition, multi-view alignment of the spine and automatic Cobb angle measurement were implemented. Compare to the M group, the consistency of the DL group was significantly higher in 3 aspects: type of lateral convexity (0.989 vs 0.566), lumbar curvature modifier (0.932 vs 0.738), and sagittal plane modifier (0.987 vs 0.522).ConclusionsDeep learning enables automated Cobb angle measurement and automated Lenke classification of idiopathic scoliosis whole spine radiographs with higher consistency than manual measurement classification.

Accurate preoperative pathological staging of gastric cancer is crucial for optimal treatment selection and improved patient outcomes. Traditional imaging methods such as CT and endoscopy have limitations in staging accuracy.

This retrospective study included 691 gastric cancer patients treated from March 2017 to March 2024. Enhanced venous-phase CT and endoscopic images, along with postoperative pathological results, were collected. We developed three modeling approaches: (1) nine deep learning models applied to CT images (DeepCT), (2) 11 machine learning algorithms using handcrafted radiomic features from CT images (HandcraftedCT), and (3) ResNet-50-extracted deep features from endoscopic images followed by 11 machine learning algorithms (DeepEndo). The two top-performing models from each approach were combined into the Integrated Multi-Modal Model using a stacking ensemble method. Performance was assessed using ROC-AUC, sensitivity, and specificity.

The Integrated Multi-Modal Model achieved an ROC-AUC of 0.933 (95% CI, 0.887-0.979) on the test set, outperforming individual models. Sensitivity and specificity were 0.869 and 0.840, respectively. Various evaluation metrics demonstrated that the final fusion model effectively integrated the strengths of each sub-model, resulting in a balanced and robust performance with reduced false-positive and false-negative rates.

The Integrated Multi-Modal Model effectively integrates radiomic and deep learning features from CT and endoscopic images, demonstrating superior performance in preoperative pathological staging of gastric cancer. This multimodal approach enhances predictive accuracy and provides a reliable tool for clinicians to develop individualized treatment plans, thereby improving patient outcomes.

The data presented in this study are available on request from the corresponding author. The data are not publicly available due to ethical reasons. All code used in this study is based on third-party libraries and all custom code developed for this study is available upon reasonable request from the corresponding author.

Distal radius fractures account for 12%-17% of all fractures, with accurate classification being crucial for proper treatment planning. Studies have shown that in emergency settings, the misdiagnosis rate of hand/wrist fractures can reach up to 29%, particularly among non-specialist physicians due to a high workload and limited experience. While existing AI methods can detect fractures, they typically require large training datasets and are limited to fracture detection without type classification. Therefore, there is an urgent need for an efficient and accurate method that can both detect and classify different types of distal radius fractures. To develop and validate an intelligent classifier for distal radius fractures by combining a statistical shape model (SSM) with a neural network (NN) based on CT imaging data.

From August 2022 to May 2023, a total of 80 CT scans were collected, including 43 normal radial bones and 37 distal radius fractures (17 Colles', 12 Barton's, and 8 Smith's fractures). We established the distal radius SSM by combining mean values with PCA (Principal Component Analysis) features and proposed six morphological indicators across four groups. The intelligent classifier (SSM + NN) was trained using SSM features as input data and different fracture types as output data. Four-fold cross-validations were performed to verify the classifier's robustness. The SSMs for both normal and fractured distal radius were successfully established based on CT data. Analysis of variance revealed significant differences in all six morphological indicators among groups (p < 0.001). The intelligent classifier achieved optimal performance when using the first 15 PCA-extracted features, with a cumulative variance contribution rate exceeding 75%. The classifier demonstrated excellent discrimination capability with a mean area under the curve (AUC) of 0.95 in four-fold cross-validation, and achieved an overall classification accuracy of 97.5% in the test set. The optimal prediction threshold range was determined to be 0.2-0.4.

The SSMs for both normal and fractured distal radius were successfully established based on CT data. Analysis of variance revealed significant differences in all six morphological indicators among groups (p < 0.001). The intelligent classifier achieved optimal performance when using the first 15 PCA-extracted features, with a cumulative variance contribution rate exceeding 75%. The classifier demonstrated excellent discrimination capability with a mean AUC of 0.95 in four-fold cross-validation and achieved an overall classification accuracy of 97.5% in the test set. The optimal prediction threshold range was determined to be 0.2-0.4.

The CT-based SSM + NN intelligent classifier demonstrated excellent performance in identifying and classifying different types of distal radius fractures. This novel approach provides an efficient, accurate, and automated tool for clinical fracture diagnosis, which could potentially improve diagnostic efficiency and treatment planning in orthopedic practice.

Providing high-quality predictions is no longer the sole goal for neural networks. As we live in an increasingly interconnected world, these models need to match the constraints of resource-limited devices powering the Internet of Things (IoT) and embedded systems. Moreover, in the era of climate change, reducing the carbon footprint of neural networks is a critical step for green artificial intelligence, which is no longer an aspiration but a major need. Enhancing the energy efficiency of neural networks, in both training and inference phases, became a predominant research topic in the field. Training optimization has grown in interest recently but remains challenging, as it involves changes in the learning procedure that can impact the prediction quality significantly. This article presents a study on the most popular techniques aiming to reduce the energy consumption of neural networks' training. We first propose a classification of the methods before discussing and comparing the different categories. In addition, we outline some energy measurement techniques. We discuss the limitations identified during our study as well as some interesting directions, such as neuromorphic and reservoir computing (RC).

Background/Objectives: In a previous study, we utilized categorical variables and machine learning (ML) algorithms to predict the success of non-surgical root canal treatments (NSRCTs) in apical periodontitis (AP), classifying the outcome as either success (healed) or failure (not healed). Given the importance of radiographic imaging in diagnosis, the present study evaluates the efficacy of deep learning (DL) in predicting NSRCT outcomes using two-dimensional (2D) periapical radiographs, comparing its performance with ML models. Methods: The DL model was trained and validated using leave-one-out cross-validation (LOOCV). Its output was incorporated into the set of categorical variables, and the ML study was reproduced using backward stepwise selection (BSS). The chi-square test was applied to assess the association between this new variable and NSRCT outcomes. Finally, after identifying the best-performing method from the ML study reproduction, statistical comparisons were conducted between this method, clinical professionals, and the image-based model using Fisher's exact test. Results: The association study yielded a p-value of 0.000000127, highlighting the predictive capability of 2D radiographs. After incorporating the DL-based predictive variable, the ML algorithm that demonstrated the best performance was logistic regression (LR), differing from the previous study, where random forest (RF) was the top performer. When comparing the deep learning-logistic regression (DL-LR) model with the clinician's prognosis (DP), DL-LR showed superior performance with a statistically significant difference (p-value < 0.05) in sensitivity, NPV, and accuracy. The same trend was observed in the DL vs. DP comparison. However, no statistically significant differences were found in the comparisons of RF vs. DL-LR, RF vs. DL, or DL vs. DL-LR. Conclusions: The findings of this study suggest that image-based artificial intelligence models exhibit superior predictive capability compared with those relying exclusively on categorical data. Moreover, they outperform clinician prognosis.

Thyroid nodules are frequent in clinical settings, and their diagnosis in adults is growing, with some persons experiencing symptoms. Ultrasound-guided thermal ablation can shrink nodules and alleviate discomfort. Because the degree and rate of lesion absorption vary greatly between individuals, there is no reliable model for predicting the therapeutic efficacy of thermal ablation.

Five convolutional neural network models including VGG19, Resnet 50, EfficientNetB1, EfficientNetB0, and InceptionV3, pre-trained with ImageNet, were compared for predicting the efficacy of ultrasound-guided microwave ablation (MWA) for benign thyroid nodules using ultrasound data. The patients were randomly assigned to one of two data sets: training (70%) or validation (30%). Accuracy, sensitivity, specificity, positive predictive value, negative predictive value, and area under the curve (AUC) were all used to assess predictive performance.

In the validation set, fine-tuned EfficientNetB1 performed best, with an AUC of 0.85 and an ACC of 0.79.

The study found that our deep learning model accurately predicts nodules with VRR < 50% after a single MWA session. Indeed, when thermal therapies compete with surgery, anticipating which nodules will be poor responders provides useful information that may assist physicians and patients determine whether thermal ablation or surgery is the preferable option. This was a preliminary study of deep learning, with a gap in actual clinical applications. As a result, more in-depth study should be undertaken to develop deep-learning models that can better help clinics. Prospective studies are expected to generate high-quality evidence and improve clinical performance in subsequent research.

Given the enormous output and pace of development of artificial intelligence (AI) methods in medical imaging, it can be challenging to identify the true success stories to determine the state-of-the-art of the field. This report seeks to provide the magnetic resonance imaging (MRI) community with an initial guide into the major areas in which the methods of AI are contributing to MRI in oncology. After a general introduction to artificial intelligence, we proceed to discuss the successes and current limitations of AI in MRI when used for image acquisition, reconstruction, registration, and segmentation, as well as its utility for assisting in diagnostic and prognostic settings. Within each section, we attempt to present a balanced summary by first presenting common techniques, state of readiness, current clinical needs, and barriers to practical deployment in the clinical setting. We conclude by presenting areas in which new advances must be realized to address questions regarding generalizability, quality assurance and control, and uncertainty quantification when applying MRI to cancer to maintain patient safety and practical utility.

Thanks to the recent achievements in task-driven image quality enhancement (IQE) models like ESTR (Liu et al. 2023), the image enhancement model and the visual recognition model can mutually enhance each other's quantitation while producing high-quality processed images that are perceivable by our human vision systems. However, existing task-driven IQE models tend to overlook an underlying fact-different levels of vision tasks have varying and sometimes conflicting requirements of image features. To address this problem, this paper proposes a generalized gradient promotion (GradProm) training strategy for task-driven IQE of medical images. Specifically, we partition a task-driven IQE system into two sub-models, i.e., a mainstream model for image enhancement and an auxiliary model for visual recognition. During training, GradProm updates only parameters of the image enhancement model using gradients of the visual recognition model and the image enhancement model, but only when gradients of these two sub-models are aligned in the same direction, which is measured by their cosine similarity. In case gradients of these two sub-models are not in the same direction, GradProm only uses the gradient of the image enhancement model to update its parameters. Theoretically, we have proved that the optimization direction of the image enhancement model will not be biased by the auxiliary visual recognition model under the implementation of GradProm. Empirically, extensive experimental results on four public yet challenging medical image datasets demonstrated the superior performance of GradProm over existing state-of-the-art methods.

The purpose of this scoping review is to analyze the application of artificial intelligence (AI) in ultrasound (US) imaging for diagnosing carpal tunnel syndrome (CTS), with an aim to explore the potential of AI in enhancing diagnostic accuracy, efficiency, and patient outcomes by automating tasks, providing objective measurements, and facilitating earlier detection of CTS.

We systematically searched multiple electronic databases, including Embase, PubMed, IEEE Xplore, and Scopus, to identify relevant studies published up to January 1, 2025. Studies were included if they focused on the application of AI in US imaging for CTS diagnosis. Editorials, expert opinions, conference papers, dataset publications, and studies that did not have a clear clinical application of the AI algorithm were excluded.

345 articles were identified, following abstract and full-text review by two independent reviewers, 18 manuscripts were included. Of these, thirteen studies were experimental studies, three were comparative studies, and one was a feasibility study. All eighteen studies shared the common objective of improving CTS diagnosis and/or initial assessment using AI, with shared aims ranging from median nerve segmentation (n = 12) to automated diagnosis (n = 9) and severity classification (n = 2). The majority of studies utilized deep learning approaches, particularly CNNs (n = 15), and some focused on radiomics features (n = 5) and traditional machine learning techniques.

The integration of AI in US imaging for CTS diagnosis holds significant promise for transforming clinical practice. AI has the potential to improve diagnostic accuracy, streamline the diagnostic process, reduce variability, and ultimately lead to better patient outcomes. Further research is needed to address challenges related to dataset limitations, variability in US imaging, and ethical considerations.

Vulnerable atherosclerotic plaque is a type of plaque that poses a significant risk of high mortality in patients with cardiovascular disease. Ultrasound has long been used for carotid atherosclerosis screening and plaque assessment due to its safety, low cost and non-invasive nature. However, conventional ultrasound techniques have limitations such as subjectivity, operator dependence, and low inter-observer agreement, leading to inconsistent and possibly inaccurate diagnoses. In recent years, a promising approach to address these limitations has emerged through the integration of artificial intelligence (AI) into ultrasound imaging. It was found that by training AI algorithms with large data sets of ultrasound images, the technology can learn to recognize specific characteristics and patterns associated with vulnerable plaques. This allows for a more objective and consistent assessment, leading to improved diagnostic accuracy. This article reviews the application of AI in the field of diagnostic ultrasound, with a particular focus on carotid vulnerable plaques, and discusses the limitations and prospects of AI-assisted ultrasound. This review also provides a deeper understanding of the role of AI in diagnostic ultrasound and promotes more research in the field.

Advances in machine learning (ML) have led to applications in safety-critical domains, including security, defense, and healthcare. These ML models are confronted with dynamically changing and actively hostile conditions characteristic of real-world applications, requiring systems incorporating ML to be reliable and resilient. Many studies propose techniques to improve the robustness of ML algorithms. However, fewer consider quantitative techniques to assess changes in the reliability and resilience of these systems over time. To address this gap, this study demonstrates how to collect relevant data during the training and testing of ML suitable for the application of software reliability, with and without covariates, and resilience models and the subsequent interpretation of these analyses. The proposed approach promotes quantitative risk assessment of ML technologies, providing the ability to track and predict degradation and improvement in the ML model performance and assisting ML and system engineers with an objective approach to compare the relative effectiveness of alternative training and testing methods. The approach is illustrated in the context of an image recognition model, which is subjected to two generative adversarial attacks and then iteratively retrained to improve the system's performance. Our results indicate that software reliability models incorporating covariates characterized the misclassification discovery process more accurately than models without covariates. Moreover, the resilience model based on multiple linear regression incorporating interactions between covariates tracks and predicts degradation and recovery of performance best. Thus, software reliability and resilience models offer rigorous quantitative assurance methods for ML-enabled systems and processes.

Cervical cancer remains a significant health challenge around the globe, with particularly high prevalence in low- and middle-income countries. This disease is preventable and curable if detected in early stages, making regular screening critically important. Cervical cytology, the most widely used screening method, has proven highly effective in reducing cervical cancer incidence and mortality in high income countries. However, its effectiveness in low-resource settings has been limited, among other factors, by insufficient diagnostic infrastructure and a shortage of trained healthcare personnel.

This paper introduces the development of a low-cost microscopy platform designed to address these limitations by enabling automatic reading of cervical cytology slides. The system features a robotized microscope capable of slide scanning, autofocus, and digital image capture, while supporting the integration of artificial intelligence (AI) algorithms. All at a production cost below 500 USD. A dataset of nearly 2,000 images, captured with the custom-built microscope and covering seven distinct cervical cellular types relevant in cytologic analysis, was created. This dataset was then used to fine-tune and test several pre-trained models for classifying between images containing normal and abnormal cell subtypes.

Most of the tested models showed good performance for properly classifying images containing abnormal and normal cervical cells, with sensitivities above 90%. Among these models, MobileNet demonstrated the highest accuracy in detecting abnormal cell types, achieving sensitivities of 98.26% and 97.95%, specificities of 88.91% and 88.72%, and F-scores of 96.42% and 96.23% on the validation and test sets, respectively.

The results indicate that MobileNet might be a suitable model for real-world deployment on the low-cost platform, offering high precision and efficiency in classifying cervical cytology images. This system presents a first step towards a promising solution for improving cervical cancer screening in low-resource settings.

Accurate brain tumor segmentation is critical for clinical diagnosis and treatment planning. This study proposes an advanced segmentation framework that combines Multiscale Attention U-Net with the EfficientNetB4 encoder to enhance segmentation performance. Unlike conventional U-Net-based architectures, the proposed model leverages EfficientNetB4's compound scaling to optimize feature extraction at multiple resolutions while maintaining low computational overhead. Additionally, the Multi-Scale Attention Mechanism (utilizing [Formula: see text], and [Formula: see text] kernels) enhances feature representation by capturing tumor boundaries across different scales, addressing limitations of existing CNN-based segmentation methods. Our approach effectively suppresses irrelevant regions and enhances tumor localization through attention-enhanced skip connections and residual attention blocks. Extensive experiments were conducted on the publicly available Figshare brain tumor dataset, comparing different EfficientNet variants to determine the optimal architecture. EfficientNetB4 demonstrated superior performance, achieving an Accuracy of 99.79%, MCR of 0.21%, Dice Coefficient of 0.9339, and an Intersection over Union (IoU) of 0.8795, outperforming other variants in accuracy and computational efficiency. The training process was analyzed using key metrics, including Dice Coefficient, dice loss, precision, recall, specificity, and IoU, showing stable convergence and generalization. Additionally, the proposed method was evaluated against state-of-the-art approaches, surpassing them in all critical metrics, including accuracy, IoU, Dice Coefficient, precision, recall, specificity, and mean IoU. This study demonstrates the effectiveness of the proposed method for robust and efficient segmentation of brain tumors, positioning it as a valuable tool for clinical and research applications.

The placenta is a vital organ that supports the developing fetus during pregnancy. Histologic examination of the placenta can reveal abnormalities in morphology and structure that impact placental function. Machine learning (ML) models have been successfully developed for digital pathology, leveraging rich image datasets from human tissue. ML models can be advantageous to placenta researchers, either by supplementing pathologist expertise or providing knowledge to inform future hypothesis generation. Research projects fall into several categories: Cell classification methods have been introduced to the placental disc and membranes. Cell classification is useful as a "bottom up" approach to characterizing tissue, using smaller image inputs than at a tissue region or whole slide level. Classification of normal tissues, cells, and development can identify pathologies that deviate. Several studies have identified pathologies within the great obstetric syndromes or placental inflammation. These studies often use mechanisms to aggregate findings from small images patches up to the whole slide level. Digital pathology slides are rich with data that inform our knowledge of placental function and disease - while many articles focus on model design and performance, the features extracted can add valuable biological and clinical knowledge to the field.

Tuberculosis is a high-mortality infectious disease. Manual sputum smear microscopy is a common and effective method for screening tuberculosis. However, it is time-consuming, labor-intensive, and has low sensitivity. In this study, we propose ResGloTBNet, a framework that integrates convolutional neural network and graph convolutional network for sputum smear image classification with high discriminative power. In this framework, the global reasoning unit is introduced into the residual structure of ResNet to form the ResGloRe module, which not only fully extracts the local features of the image but also models the global relationship between different regions in the image. Furthermore, we applied activation maximization and class activation mapping to generate explanations for the model's predictions on the test sets. ResGloTBNet achieved remarkable results on a publicly available dataset, reaching 97.2 % accuracy and 99.0 % sensitivity. It also maintained a high level of performance on a private dataset, attaining 98.0 % accuracy and 96.6 % sensitivity. In addition, interpretable analysis demonstrated that ResGloTBNet can effectively identify the features and regions in the input images that contribute the most to the model's predictions, providing valuable insights into the decision-making process of the deep learning model.

In the field of medical science, skin segmentation has gained significant importance, particularly in dermatology and skin cancer research. This domain demands high precision in distinguishing critical regions (such as lesions or moles) from healthy skin in medical images. With growing technological advancements, deep learning models have emerged as indispensable tools in addressing these challenges. One of the state-of-the-art modules revealed in recent years, the 2D Selective Scan (SS2D), based on state-space models that have already seen great success in natural language processing, has been increasingly adopted and is gradually replacing Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs). Leveraging the strength of this module, this paper introduces LiteMamba-Bound, a lightweight model with approximately 957K parameters, designed for skin image segmentation tasks. Notably, the Channel Attention Dual Mamba (CAD-Mamba) block is proposed within both the encoder and decoder alongside the Mix Convolution with Simple Attention bottleneck block to emphasize key features. Additionally, we propose the Reverse Attention Boundary Module to highlight challenging boundary features. Also, the Normalized Active Contour loss function presented in this paper significantly improves the model's performance compared to other loss functions. To validate performance, we conducted tests on two skin image datasets, ISIC2018 and PH2, with results consistently showing superior performance compared to other models. Our code will be made publicly available at: https://github.com/kwanghwi242/A-new-segmentation-model.

Unsupervised domain adaptation (UDA) has received interest as a means to alleviate the burden of data annotation. Nevertheless, existing UDA segmentation methods exhibit performance degradation in fine intracranial vessel segmentation tasks due to the problem of structure mismatch in the image synthesis procedure. To improve the image synthesis quality and the segmentation performance, a novel UDA segmentation method with structure preservation approaches, named StruP-Net, is proposed. The StruP-Net employs adversarial learning for image synthesis and utilizes two domain-specific segmentation networks to enhance the semantic consistency between real images and synthesized images. Additionally, two distinct structure preservation approaches, feature-level structure preservation (F-SP) and image-level structure preservation (I-SP), are proposed to alleviate the problem of structure mismatch in the image synthesis procedure. The F-SP, composed of two domain-specific graph convolutional networks (GCN), focuses on providing feature-level constraints to enhance the structural similarity between real images and synthesized images. Meanwhile, the I-SP imposes constraints on structure similarity based on perceptual loss. The cross-modality experimental results from magnetic resonance angiography (MRA) images to computed tomography angiography (CTA) images indicate that StruP-Net achieves better segmentation performance compared with other state-of-the-art methods. Furthermore, high inference efficiency demonstrates the clinical application potential of StruP-Net. The code is available at https://github.com/Mayoiuta/StruP-Net .

This study aimed to design and systematically evaluate an architecture, proposed as the Explainable Mandibular Third Molar Convolutional Neural Network (E-mTMCNN), for detecting the presence of mandibular third molars (m-M3) in panoramic radiography (PR). The proposed architecture seeks to enhance the accuracy of early detection and improve clinical decision-making and treatment planning in dentistry.

A new dataset, named the Mandibular Third Molar (m-TM) dataset, was developed through expert labeling of raw PR images from the UESB dataset. This dataset was subsequently made publicly accessible to support further research. Several advanced image preprocessing techniques, including Gaussian filtering, gamma correction, and data augmentation, were applied to improve image quality. Various Deep learning (DL) based Convolutional Neural Network (CNN) architectures were trained and validated using Transfer Learning (TL) methodologies. Among these, the E-mTMCNN, leveraging the GoogLeNet architecture, achieved the highest performance metrics. To ensure transparency in the model's decision-making process, Local Interpretable Model-Agnostic Explanations (LIME) were integrated as an eXplainable Artificial Intelligence (XAI) approach. Clinical reliability and applicability were assessed through an expert survey conducted among specialized dentists using a decision support system based on the E-mTMCNN.

The E-mTMCNN architecture demonstrated a classification accuracy of 87.02%, with a sensitivity of 75%, specificity of 94.73%, precision of 77.68%, an F1 score of 75.51%, and an area under the curve (AUC) of 87.01%. The integration of LIME provided visual explanations of the model's decision-making rationale, reinforcing the robustness of the proposed architecture. Results from the expert survey indicated high clinical acceptance and confidence in the reliability of the system.

The findings demonstrate that the E-mTMCNN architecture effectively detects the presence of m-M3 in PRs, outperforming current state-of-the-art methodologies. The proposed architecture shows considerable potential for integration into computer-aided diagnostic systems, advancing early detection capabilities and enhancing the precision of treatment planning in dental practice.

This study was conducted to develop and validate a novel deep reinforcement learning (DRL) algorithm incorporating the segment anything model (SAM) to enhance the accuracy of automatic contouring organs at risk during radiotherapy for cervical cancer patients. CT images were collected from 150 cervical cancer patients treated at our hospital between 2021 and 2023. Among these images, 122 CT images were used as a training set for the algorithm training of the DRL model based on the SAM model, and 28 CT images were used for the test set. The model's performance was evaluated by comparing its segmentation results with the ground truth (manual contouring) obtained through manual contouring by expert clinicians. The test results were compared with the contouring results of commercial automatic contouring software based on the deep learning (DL) algorithm model. The Dice similarity coefficient (DSC), 95th percentile Hausdorff distance, average symmetric surface distance (ASSD), and relative absolute volume difference (RAVD) were used to quantitatively assess the contouring accuracy from different perspectives, enabling the contouring results to be comprehensively and objectively evaluated. The DRL model outperformed the DL model across all evaluated metrics. DRL achieved higher median DSC values, such as 0.97 versus 0.96 for the left kidney (P < 0.001), and demonstrated better boundary accuracy with lower HD95 values, e.g., 14.30 mm versus 17.24 mm for the rectum (P < 0.001). Moreover, DRL exhibited superior spatial agreement (median ASSD: 1.55 mm vs. 1.80 mm for the rectum, P < 0.001) and volume prediction accuracy (median RAVD: 10.25 vs. 10.64 for the duodenum, P < 0.001). These findings indicate that integrating SAM with RL (reinforcement learning) enhances segmentation accuracy and consistency compared to conventional DL methods. The proposed approach introduces a novel training strategy that improves performance without increasing model complexity, demonstrating its potential applicability in clinical practice.

Deep learning approaches such as DeepACSA enable automated segmentation of muscle ultrasound cross-sectional area (CSA). Although they provide fast and accurate results, most are developed using data from healthy populations. The changes in muscle size and quality following anterior cruciate ligament (ACL) injury challenges the validity of these automated approaches in the ACL population. Quadriceps muscle CSA is an important outcome following ACL injury; therefore, our aim was to validate DeepACSA, a convolutional neural network (CNN) approach for ACL injury.

Quadriceps panoramic CSA ultrasound images (vastus lateralis [VL] n = 430, rectus femoris [RF] n = 349, and vastus medialis [VM] n = 723) from 124 participants with an ACL injury (age 22.8 ± 7.9 y, 61 females) were used to train CNN models. For VL and RF, combined models included extra images from healthy participants (n = 153, age 38.2, range 13-78) that the DeepACSA was developed from. All models were tested on unseen external validation images (n = 100) from ACL-injured participants. Model predicted CSA results were compared to manual segmentation results.

All models showed good comparability (ICC > 0.81, < 14.1% standard error of measurement, mean differences of <1.56 cm2) to manual segmentation. Removal of the erroneous predictions resulted in excellent comparability (ICC > 0.94, < 7.40% standard error of measurement, mean differences of <0.57 cm2). Erroneous predictions were 17% for combined VL, 11% for combined RF, and 20% for ACL-only VM models.

The new CNN models provided can be used in ACL-injured populations to measure CSA of VL, RF, and VM muscles automatically. The models yield high comparability to manual segmentation results and reduce the burden of manual segmentation.

Artificial intelligence (AI) algorithms for the detection of retinoblastoma (RB) by fundus image analysis have been proposed as a potentially effective technique to facilitate diagnosis and screening programs. However, doubts remain about the accuracy of the technique, the best type of AI for this situation, and its feasibility for everyday use. Therefore, we performed a systematic review and meta-analysis to evaluate this issue.

Following PRISMA 2020 guidelines, a comprehensive search of MEDLINE, Embase, ClinicalTrials.gov and IEEEX databases identified 494 studies whose titles and abstracts were screened for eligibility. We included diagnostic studies that evaluated the accuracy of AI in identifying retinoblastoma based on fundus imaging. Univariate and bivariate analysis was performed using the random effects model. The study protocol was registered in PROSPERO under CRD42024499221.

Six studies with 9902 fundus images were included, of which 5944 (60%) had confirmed RB. Only one dataset used a semi-supervised machine learning (ML) based method, all other studies used supervised ML, three using architectures requiring high computational power and two using more economical models. The pooled analysis of all models showed a sensitivity of 98.2% (95% CI: 0.947-0.994), a specificity of 98.5% (95% CI: 0.916-0.998) and an AUC of 0.986 (95% CI: 0.970-0.989). Subgroup analyses comparing models with high and low computational power showed no significant difference (p=0.824).

AI methods showed a high precision in the diagnosis of RB based on fundus images with no significant difference when comparing high and low computational power models, suggesting a viability of their use. Validation and cost-effectiveness studies are needed in different income countries. Subpopulations should also be analyzed, as AI may be useful as an initial screening tool in populations at high risk for RB, serving as a bridge to the pediatric ophthalmologist or ocular oncologist, who are scarce globally.

What is known Retinoblastoma is the most common intraocular cancer in childhood and diagnostic delay is the main factor leading to a poor prognosis. The application of machine learning techniques proposes reliable methods for screening and diagnosis of retinal diseases. What is new The meta-analysis of the diagnostic accuracy of artificial intelligence methods for diagnosing retinoblastoma based on fundus images showed a sensitivity of 98.2% (95% CI: 0.947-0.994) and a specificity of 98.5% (95% CI: 0.916-0.998). There was no statistically significant difference in the diagnostic accuracy of high and low computational power models. The overall performance of supervised machine learning was best than unsupervised, although few studies were available on the second type.

Orthodontically induced root resorption (OIRR) is a common and undesirable consequence of orthodontic treatment. Traditionally, studies employ manual methods to conduct 3-dimensional quantitative analysis of OIRR via cone-beam computed tomography (CBCT), which is often subjective and time-consuming. With advancements in computer technology, deep learning-based approaches have gained traction in medical image processing. This study presents a deep learning-based model for the fully automatic extraction of root volume information and the localization of root resorption from CBCT images.

In this cross-sectional, retrospective study, 4534 teeth from 105 patients were used to train and validate an automatic model for OIRR quantification. The protocol encompassed several steps: preprocessing of CBCT images involving automatic tooth segmentation and conversion into point clouds, followed by segmentation of tooth crowns and roots via the Dynamic Graph Convolutional Neural Network. The root volume was subsequently calculated, and OIRR localization was performed. The intraclass correlation coefficient was employed to validate the consistency between the automatic model and manual measurements.

The proposed method strongly correlated with manual measurements in terms of root volume and OIRR severity assessment. The intraclass correlation coefficient values for average volume measurements at each tooth position exceeded 0.95 (P <0.001), with the accuracy of different OIRR severity classifications surpassing 0.8.

The proposed methodology provides automatic and reliable tools for OIRR assessment, offering potential improvements in orthodontic treatment planning and monitoring.

An increasing number of nasopharyngeal carcinoma (NPC) patients benefit from immunotherapy with chemotherapy as an induction treatment. Currently, there isn't a reliable method to assess the efficacy of this regimen, which hinders informed decision-making for follow-up care.

To establish and evaluate a model for predicting the efficacy of programmed death-1 (PD-1) inhibitor combined with GP (gemcitabine and cisplatin) induction chemotherapy based on deep learning features (DLFs) and radiomic features.

Ninety-nine patients diagnosed with advanced NPC were enrolled and randomly divided into training set and test set in a 7:3 ratio. From MRI scans, DLFs and conventional radiomic characteristics were recovered. The random forest algorithm was employed to identify the most valuable features. A prediction model was then created using these radiomic characteristics and DLFs to determine the effectiveness of PD-1 inhibitor combined with GP chemotherapy. The model's performance was assessed using Receiver Operating Characteristic (ROC) curve analysis, area under the curve (AUC), accuracy (ACC), and negative predictive value (NPV).

Twenty-one prediction models were constructed. The Tf_Radiomics+Resnet101 model, which combines radiomic features and DLFs, demonstrated the best performance. The model's AUC, ACC, and NPV values in the training and test sets were 0.936 (95%CI: 0.827-1.0), 0.9, and 0.923, respectively.

The Tf_Radiomics+Resnet101 model, based on MRI and Resnet101 deep learning, shows a high ability to predict the clinically complete response (cCR) efficacy of PD-1 inhibitor combined with GP in advanced NPC. This model can significantly enhance the treatment management of patients with advanced NPC.

ObjectivePost-surgical lip symmetry assessment is a key indicator of cleft repair success. Traditional methods rely on distances between anatomical landmarks, which are impractical for video analysis and overlook texture and appearance. We propose an artificial intelligence (AI) approach to automate this process, analyzing lateral lip morphology for a quantitative symmetry evaluation.DesignWe utilize contrastive learning to quantify lip symmetry by measuring the similarity between the representations of the sides, which is subsequently used to classify the severity of asymmetry. Our model does not require patient images for training. Instead, we introduce dissimilarities in face images from open datasets using two methods: temporal misalignment for video frames and face transformations to simulate lip asymmetry observed in the target population. The model differentiates the left and right image representations to assess asymmetry. We evaluated our model on 146 images of patients with repaired cleft lip.ResultsThe deep learning model trained with face transformations categorized patient images into five asymmetry levels, achieving a weighted accuracy of 75% and a Pearson correlation of 0.31 with medical expert human evaluations. The model utilizing temporal misalignment achieved a weighted accuracy of 69% and a Pearson correlation of 0.27 for the same classification task.ConclusionsWe propose an automated approach for assessing lip asymmetry in patients with repaired cleft lip by transforming facial images of control subjects to train a deep learning model, eliminating manual anatomical landmarks. Our promising results provide a more efficient and objective tool for evaluating surgical outcomes.

The training of deep learning (DL) models in medical images requires large amounts of sensitive patient data. However, acquiring adequately labeled datasets is challenging because of the heavy workload of manual annotations and the stringent privacy protocols.

Federated learning (FL) provides an alternative approach in which a coalition of clients collaboratively trains models without exchanging the underlying datasets. In this study, a novel Personalized Federated Learning Framework (PAF-Fed) is presented for abdominal multi-organ segmentation. Different from traditional FL algorithms, PAF-Fed selectively gathers partial model parameters for inter-client collaboration, retaining the remaining parameters to learn local data distributions at individual sites. Additionally, the Fourier Transform with the Self-attention mechanism is employed to aggregate the low-frequency components of parameters, promoting the extraction of shared knowledge and tackling statistical heterogeneity from diverse client datasets.

The proposed method was evaluated on the Combined Healthy Abdominal Organ Segmentation magnetic resonance imaging (MRI) dataset (CHAOS 2019) and a private computed tomography (CT) dataset, achieving an average Dice Similarity Coefficient (DSC) of 72.65% for CHAOS and 85.50% for the private CT dataset, respectively.

The experimental results demonstrate the superiority of our PAF-Fed by outperforming state-of-the-art FL methods.

Large-scale Artificial General Intelligence (AGI) models, including Large Language Models (LLMs) such as ChatGPT/GPT-4, have achieved unprecedented success in a variety of general domain tasks. Yet, when applied directly to specialized domains like medical imaging, which require in-depth expertise, these models face notable challenges arising from the medical field's inherent complexities and unique characteristics. In this review, we delve into the potential applications of AGI models in medical imaging and healthcare, with a primary focus on LLMs, Large Vision Models, and Large Multimodal Models. We provide a thorough overview of the key features and enabling techniques of LLMs and AGI, and further examine the roadmaps guiding the evolution and implementation of AGI models in the medical sector, summarizing their present applications, potentialities, and associated challenges. In addition, we highlight potential future research directions, offering a holistic view on upcoming ventures. This comprehensive review aims to offer insights into the future implications of AGI in medical imaging, healthcare, and beyond.

Vision transformer (ViT)and convolutional neural networks (CNNs) each possess distinct strengths in medical imaging: ViT excels in capturing long-range dependencies through self-attention, while CNNs are adept at extracting local features via spatial convolution filters. While ViT may struggle with capturing detailed local spatial information, critical for tasks like anomaly detection in medical imaging, shallow CNNs often fail to effectively abstract global context. This study aims to explore and evaluate hybrid architectures that integrate ViT and CNN to leverage their complementary strengths for enhanced performance in medical vision tasks, such as segmentation, classification, reconstruction, and prediction. Following PRISMA guideline, a systematic review was conducted on 34 articles published between 2020 and Sept. 2024. These articles proposed novel hybrid ViT-CNN architectures specifically for medical imaging tasks in radiology. The review focused on analyzing architectural variations, merging strategies between ViT and CNN, innovative applications of ViT, and efficiency metrics including parameters, inference time (GFlops), and performance benchmarks. The review identified that integrating ViT and CNN can mitigate the limitations of each architecture offering comprehensive solutions that combine global context understanding with precise local feature extraction. We benchmarked the articles based on architectural variations, merging strategies, innovative uses of ViT, and efficiency metrics (number of parameters, inference time (GFlops), and performance), and derived a ranked list. By synthesizing current literature, this review defines fundamental concepts of hybrid vision transformers and highlights emerging trends in the field. It provides a clear direction for future research aimed at optimizing the integration of ViT and CNN for effective utilization in medical imaging, contributing to advancements in diagnostic accuracy and image analysis. We performed systematic review of hybrid vision transformer architecture using PRISMA guideline and performed thorough comparative analysis to benchmark the architectures.

Manual labeling of lesions in medical image analysis presents a significant challenge due to its labor-intensive and inefficient nature, which ultimately strains essential medical resources and impedes the advancement of computer-aided diagnosis. This paper introduces a novel medical image-segmentation framework named Efficient Generative-Adversarial U-Net (EGAUNet), designed to facilitate rapid and accurate multi-organ labeling. To enhance the model's capability to comprehend spatial information, we propose the Global Spatial-Channel Attention Mechanism (GSCA). This mechanism enables the model to concentrate more effectively on regions of interest. Additionally, we have integrated Efficient Mapping Convolutional Blocks (EMCB) into the feature-learning process, allowing for the extraction of multi-scale spatial information and the adjustment of feature map channels through optimized weight values. Moreover, the proposed framework progressively enhances its performance by utilizing a generative-adversarial learning strategy, which contributes to improvements in segmentation accuracy. Consequently, EGAUNet demonstrates exemplary segmentation performance on public multi-organ datasets while maintaining high efficiency. For instance, in evaluations on the CHAOS T2SPIR dataset, EGAUNet achieves approximately 2% higher performance on the Jaccard metric, 1% higher on the Dice metric, and nearly 3% higher on the precision metric in comparison to advanced networks such as Swin-Unet and TransUnet.

The prevalence of neurodegenerative diseases has significantly increased, necessitating a deeper understanding of their symptoms, diagnostic processes, and prevention strategies. Frontotemporal dementia (FTD) and Alzheimer's disease (AD) are two prominent neurodegenerative conditions that present diagnostic challenges due to overlapping symptoms. To address these challenges, experts utilize a range of imaging techniques, including magnetic resonance imaging (MRI), diffusion tensor imaging (DTI), functional MRI (fMRI), positron emission tomography (PET), and single-photon emission computed tomography (SPECT). These techniques facilitate a detailed examination of the manifestations of these diseases. Recent research has demonstrated the potential of artificial intelligence (AI) in automating the diagnostic process, generating significant interest in this field.

This narrative review aims to compile and analyze articles related to the AI-assisted diagnosis of FTD and AD. We reviewed 31 articles published between 2012 and 2024, with 23 focusing on machine learning techniques and 8 on deep learning techniques. The studies utilized features extracted from both single imaging modalities and multi-modal approaches, and evaluated the performance of various classification models.

Among the machine learning studies, Support Vector Machines (SVM) exhibited the most favorable performance in classifying FTD and AD. In deep learning studies, the ResNet convolutional neural network outperformed other networks.

This review highlights the utility of different imaging modalities as diagnostic aids in distinguishing between FTD and AD. However, it emphasizes the importance of incorporating clinical examinations and patient symptom evaluations to ensure comprehensive and accurate diagnoses.

Mental health issues like insomnia, anxiety, and depression have increased significantly. Artificial intelligence (AI) has shown promise in diagnosing and providing personalized treatment.

This study aims to systematically review the application of AI in addressing insomnia, anxiety, and depression, identifying key research hotspots, and forecasting future trends through bibliometric analysis.

We analyzed a total of 875 articles from the Web of Science Core Collection (2000-2024) using bibliometric tools such as VOSviewer and CiteSpace. These tools were used to map research trends, highlight international collaboration, and examine the contributions of leading countries, institutions, and authors in the field.

The United States and China lead the field in terms of research output and collaborations. Key research areas include "neural networks," "machine learning," "deep learning," and "human-robot interaction," particularly in relation to personalized treatment approaches. However, challenges around data privacy, ethical concerns, and the interpretability of AI models need to be addressed.

This study highlights the growing role of AI in mental health research and identifies future priorities, such as improving data quality, addressing ethical challenges, and integrating AI more seamlessly into clinical practice. These advancements will be crucial in addressing the global mental health crisis.

Hip dysplasia is the second most common orthopedic condition in children with cerebral palsy (CP) and may result in disability and pain. The migration percentage (MP) is a widely used metric in hip surveillance, calculated based on an anterior-posterior pelvis radiograph. However, manual quantification of MP values using hip X-ray scans in current standard practice has challenges including being time-intensive, requiring expert knowledge, and not considering human bias. The purpose of this study is to develop a machine learning algorithm to automatically quantify MP values using a hip X-ray scan, and hence provide an assessment for severity, which then can be used for surveillance, treatment planning, and management.

X-ray scans from 210 patients were curated, pre-processed, and manually annotated at our clinical center. Several machine learning models were trained using pre-trained weights from Inception ResNet-V2, VGG-16, and VGG-19, with different strategies (pre-processing, with and without region of interest (ROI) detection, with and without data augmentation) to find an optimal model for automatic hip landmarking. The predicted landmarks were then used by our geometric algorithm to quantify the MP value for the input hip X-ray scan.

The pre-trained VGG-19 model, fine-tuned with additional custom layers, outputted the lowest mean squared error values for both train and test data, when ROI cropped images were used along with data augmentation for model training. The MP value calculated by the algorithm was compared to manual ground truth labels from our orthopedic fellows using the hip screen application for benchmarking.

The results showed the feasibility of the machine learning model in automatic hip landmark detection for reliably quantifying MP value from hip X-ray scans. The algorithm could be used as an accurate and reliable tool in orthopedic care for diagnosing, severity assessment, and hence treatment and surgical planning for hip displacement.

Developing cost-effective, consumer-accessible platforms for point-of-use environmental and clinical pathogen testing is a priority, to reduce reliance on laborious, time-consuming culturing approaches. Unfortunately, a system offering ultrasensitive detection capabilities in a form that requires little auxiliary equipment or training has remained elusive. Here, a colorimetric DNAzyme-crosslinked hydrogel sensor is presented. In the presence of a target pathogen, DNAzyme cleavage results in hydrogel dissolution, yielding the release of entrapped gold nanoparticles in a manner visible to the naked eye. Recognizing that Escherichia coli holds high relevance within both environmental and clinical environments, an E. coli-responsive DNAzyme is incorporated into this platform. Through the optimization of the hydrogel polymerization process and the discovery of bacteriophage-induced DNAzyme signal amplification, 101 CFU mL-1 E. coli is detected within real-world lake water samples. Subsequent pairing with an artificial intelligence model removed ambiguity in sensor readout, offering 96% true positive and 100% true negative accuracy. Finally, high sensor specificity and stability results supported clinical use, where 100% of urine samples collected from patients with E. coli urinary tract infections are accurately identified. No false positives are observed when testing healthy samples. Ultimately, this platform stands to significantly improve population health by substantially increasing pathogen testing accessibility.

Despite advances in modern medicine including the use of computed tomography for detecting COVID-19, precise identification and segmentation of lesions remain a significant challenge owing to indistinct boundaries and low degrees of contrast between infected and healthy lung tissues. This study introduces a novel model called the edge-based dual-parallel attention (EDA)-guided feature-filtering network (EF-Net), specifically designed to accurately segment the edges of COVID-19 lesions. The proposed model comprises two modules: an EDA module and a feature-filtering module (FFM). EDA efficiently extracts structural and textural features from low-level features, enabling the precise identification of lesion boundaries. FFM receives semantically rich features from a deep-level encoder and integrates features with abundant texture and contour information obtained from the EDA module. After filtering through a gating mechanism of the FFM, the EDA features are fused with deep-level features, yielding features rich in both semantic and textural information. Experiments demonstrate that our model outperforms existing models including Inf_Net, GFNet, and BSNet considering various metrics, offering better and clearer segmentation results, particularly for segmenting lesion edges. Moreover, superior performance on the three datasets is achieved, with dice coefficients of 98.1, 97.3, and 72.1 %.

Bladder cancer (BCa) is a heterogeneous malignancy characterized by distinct immune subtypes, primarily due to differences in tumor-infiltrating immune cells and their functional characteristics. Therefore, understanding the tumor immune microenvironment (TIME) landscape in BCa is crucial for prognostic prediction and guiding precision therapy. In this study, we integrated 10 machine learning algorithms to develop an immune-related machine learning signature (IRMLS) and subsequently created a deep learning model to detect the IRMLS subtype based on pathological images. The IRMLS proved to be an independent prognostic factor for overall survival (OS) and demonstrated robust and stable performance (p < 0.01). The high-risk group exhibited an immune-inflamed phenotype, associated with poorer prognosis and higher levels of immune cell infiltration. We further investigated the cancer immune cycle and mutation landscape within the IRMLS model, confirming that the high-risk group is more sensitive to immune checkpoint immunotherapy (ICI) and adjuvant chemotherapy with cisplatin (p = 2.8e-10), docetaxel (p = 8.8e-13), etoposide (p = 1.8e-07), and paclitaxel (p = 6.2e-13). In conclusion, we identified and validated a machine learning-based molecular characteristic, IRMLS, which reflects various aspects of the BCa biological process and offers new insights into personalized precision therapy for BCa patients.

Myelodysplastic syndromes (MDSs) are a group of hematologic neoplasms accompanied by dysplasia of bone marrow (BM) hematopoietic cells with cytopenia. Recently, digitalized pathology and pathomics using computerized feature analysis have been actively researched for classifying and predicting prognosis in various tumors of hematopoietic tissues. This study analyzed the pathomic features of hematopoietic cells in BM aspiration smears of patients with MDS according to each hematopoietic cell lineage and dysplasia. We included 24 patients with an MDS and 21 with normal BM. The 12,360 hematopoietic cells utilized were to be classified into seven types: normal erythrocytes, normal granulocytes, normal megakaryocytes, dysplastic erythrocytes, dysplastic granulocytes, dysplastic megakaryocytes, and others. Four hundred seventy-six pathomic features quantifying cell intensity, shape, and texture were extracted from each segmented cell. After comparing the combination of feature selection and machine learning classifier methods using 5-fold cross-validation area under the receiver operating characteristic curve (AUROC), the quadratic discriminant analysis (QDA) with gradient boosting decision tree (AUROC = 0.63) and QDA with eXtreme gradient boosting (XGB) (AUROC = 0.64) showed a high AUROC combination. Through a feature selection process, 30 characteristics were further analyzed. Dysplastic erythrocytes and granulocytes showed lower median values on heatmap analysis compared to that of normal erythrocytes and granulocytes. The data suggest that pathomic features could be applied to cell differentiation in hematologic malignancies. It could be used as a new biomarker with an auxiliary role for more accurate diagnosis. Further studies including prediction survival and prognosis with larger cohort of patients are needed.