Accurate classification of focal liver lesions is crucial for diagnosis and treatment in hepatology. However, traditional supervised deep learning models depend on large-scale annotated datasets, which are often limited in medical imaging. Recently, Vision-Language models (VLMs) such as Contrastive Language-Image Pre-training model (CLIP) has been applied to image classifications. Compared to the conventional convolutional neural network (CNN), which classifiers image based on visual information only, VLM leverages multimodal learning with text and images, allowing it to learn effectively even with a limited amount of labeled data. Inspired by CLIP, we pro-pose a Liver-VLM, a model specifically designed for focal liver lesions (FLLs) classification. First, Liver-VLM incorporates class information into the text encoder without introducing additional inference overhead. Second, by calculating the pairwise cosine similarities between image and text embeddings and optimizing the model with a cross-entropy loss, Liver-VLM ef-fectively aligns image features with class-level text features. Experimental results on MPCT-FLLs dataset demonstrate that the Liver-VLM model out-performs both the standard CLIP and MedCLIP models in terms of accuracy and Area Under the Curve (AUC). Further analysis shows that using a lightweight ResNet18 backbone enhances classification performance, particularly under data-constrained conditions.

We propose a multimodal spatiotemporal graph neural network (STG) framework to predict colorectal cancer liver metastasis (CRLM) progression. Current clinical models do not effectively integrate the tumor's spatial heterogeneity, dynamic evolution, and complex multimodal data relationships, limiting their predictive accuracy. Our STG framework combines preoperative CT imaging and clinical data into a heterogeneous graph structure, enabling joint modeling of tumor distribution and temporal evolution through spatial topology and cross-modal edges. The framework uses GraphSAGE to aggregate spatiotemporal neighborhood information and leverages supervised and contrastive learning strategies to enhance the model's ability to capture temporal features and improve robustness. A lightweight version of the model reduces parameter count by 78.55%, maintaining near-state-of-the-art performance. The model jointly optimizes recurrence risk regression and survival analysis tasks, with contrastive loss improving feature representational discriminability and cross-modal consistency. Experimental results on the MSKCC CRLM dataset show a time-adjacent accuracy of 85% and a mean absolute error of 1.1005, significantly outperforming existing methods. The innovative heterogeneous graph construction and spatiotemporal decoupling mechanism effectively uncover the associations between dynamic tumor microenvironment changes and prognosis, providing reliable quantitative support for personalized treatment decisions.

Thyroid nodule, as a common clinical endocrine disease, has become increasingly prevalent worldwide. Ultrasound, as the premier method of thyroid imaging, plays an important role in accurately diagnosing and managing thyroid nodules. However, there is a high degree of inter- and intra-observer variability in image interpretation due to the different knowledge and experience of sonographers who have huge ultrasound examination tasks everyday. Artificial intelligence based on computer-aided diagnosis technology maybe improve the accuracy and time efficiency of thyroid nodules diagnosis. This study introduced an artificial intelligence software called SW-TH01/II to evaluate ultrasound image characteristics of thyroid nodules including echogenicity, shape, border, margin, and calcification. We included 225 ultrasound images from two hospitals in Shanghai, respectively. The sonographers and software performed characteristics analysis on the same group of images. We analyzed the consistency of the two results and used the sonographers' results as the gold standard to evaluate the accuracy of SW-TH01/II. A total of 449 images were included in the statistical analysis. For the seven indicators, the proportions of agreement between SW-TH01/II and sonographers' analysis results were all greater than 0.8. For the echogenicity (with very hypoechoic), aspect ratio and margin, the kappa coefficient between the two methods were above 0.75 (P < 0.001). The kappa coefficients of echogenicity (echotexture and echogenicity level), border and calcification between the two methods were above 0.6 (P < 0.001). The median time it takes for software and sonographers to interpret an image were 3 (2, 3) seconds and 26.5 (21.17, 34.33) seconds, respectively, and the difference were statistically significant (z = -18.36, P < 0.001). SW-TH01/II has a high degree of accuracy and great time efficiency benefits in judging the characteristics of thyroid nodule. It can provide more objective results and improve the efficiency of ultrasound examination. SW-TH01/II can be used to assist the sonographers in characterizing the thyroid nodule ultrasound images.

Currently, there are inconsistencies among different studies on preoperative prediction of Cytokeratin 19 (CK19) expression in HCC using traditional imaging, radiomics, and deep learning. We aimed to systematically analyze and compare the performance of non-invasive methods for predicting CK19-positive HCC, thereby providing insights for the stratified management of HCC patients. A comprehensive literature search was conducted in PubMed, EMBASE, Web of Science, and the Cochrane Library from inception to February 2025. Two investigators independently screened and extracted data based on inclusion and exclusion criteria. Eligible studies were included, and key findings were summarized in tables to provide a clear overview. Ultimately, 22 studies involving 3395 HCC patients were included. 72.7% (16/22) focused on traditional imaging, 36.4% (8/22) on radiomics, 9.1% (2/22) on deep learning, and 54.5% (12/22) on combined models. The magnetic resonance imaging was the most commonly used imaging modality (19/22), and over half of the studies (12/22) were published between 2022 and 2025. Moreover, 27.3% (6/22) were multicenter studies, 36.4% (8/22) included a validation set, and only 13.6% (3/22) were prospective. The area under the curve (AUC) range of using clinical and traditional imaging was 0.560 to 0.917. The AUC ranges of radiomics were 0.648 to 0.951, and the AUC ranges of deep learning were 0.718 to 0.820. Notably, the AUC ranges of combined models of clinical, imaging, radiomics and deep learning were 0.614 to 0.995. Nevertheless, the multicenter external data were limited, with only 13.6% (3/22) incorporating validation. The combined model integrating traditional imaging, radiomics and deep learning achieves excellent potential and performance for predicting CK19 in HCC. Based on current limitations, future research should focus on building an easy-to-use dynamic online tool, combining multicenter-multimodal imaging and advanced deep learning approaches to enhance the accuracy and robustness of model predictions.

While Artificial Intelligence (AI) has demonstrated human-level capabilities in many prediction tasks, collaboration between humans and machines is crucial in mission-critical applications, especially in the healthcare sector. An important factor that enables successful human-AI collaboration is the user interface (UI). This paper evaluated the UI of BiTNet, an intelligent assisting tool for human biliary tract diagnosis via ultrasound images. We evaluated the UI of the assisting tool with 11 healthcare professionals through two main research questions: 1) did the assisting tool help improve the diagnosis performance of the healthcare professionals who use the tool? and 2) how did different UI elements of the assisting tool influence the users' decisions? To analyze the impacts of different UI elements without multiple rounds of experiments, we propose the novel AISIM strategy. We demonstrated that our proposed strategy, AISIM, can be used to analyze the influence of different elements in the user interface in one go. Our main findings show that the assisting tool improved the diagnostic performance of healthcare professionals from different levels of experience (OR  = 3.326, p-value <10-15). In addition, high AI prediction confidence and correct AI attention area provided higher than twice the odds that the users would follow the AI suggestion. Finally, the interview results agreed with the experimental result that BiTNet boosted the users' confidence when they were assigned to diagnose abnormality in the biliary tract from the ultrasound images.

To develop an interpretable machine learning (ML) model using dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) radiomic data, dosimetric parameters, and clinical data for predicting radiation-induced hepatic toxicity (RIHT) in patients with hepatocellular carcinoma (HCC) following intensity-modulated radiation therapy (IMRT). A retrospective analysis of 150 HCC patients was performed, with a 7:3 ratio used to divide the data into training and validation cohorts. Radiomic features from the original MRI sequences and Delta-radiomic features were extracted. Seven ML models based on radiomics were developed: logistic regression (LR), random forest (RF), support vector machine (SVM), eXtreme Gradient Boosting (XGBoost), adaptive boosting (AdaBoost), decision tree (DT), and artificial neural network (ANN). The predictive performance of the models was evaluated using receiver operating characteristic (ROC) curve analysis and calibration curves. Shapley additive explanations (SHAP) were employed to interpret the contribution of each variable and its risk threshold. Original radiomic features and Delta-radiomic features were extracted from DCE-MRI images and filtered to generate Radiomics-scores and Delta-Radiomics-scores. These were then combined with independent risk factors (Body Mass Index (BMI), V5, and pre-Child-Pugh score(pre-CP)) identified through univariate and multivariate logistic regression and Spearman correlation analysis to construct the ML models. In the training cohort, the AUC values were 0.8651 for LR, 0.7004 for RF, 0.6349 for SVM, 0.6706 for XGBoost, 0.7341 for AdaBoost, 0.6806 for Decision Tree, and 0.6786 for ANN. The corresponding accuracies were 84.4%, 65.6%, 75.0%, 65.6%, 71.9%, 68.8%, and 71.9%, respectively. The validation cohort further confirmed the superiority of the LR model, which was selected as the optimal model. SHAP analysis revealed that Delta-radiomics made a substantial positive contribution to the model. The interpretable ML model based on radiomics provides a non-invasive tool for predicting RIHT in patients with HCC, demonstrating satisfactory discriminative performance.

Increasing evidence suggests that non-operative management (NOM) with antibiotics could serve as a safe alternative to surgery for the treatment of uncomplicated acute appendicitis (AA). However, accurately differentiating between uncomplicated and complicated AA remains challenging. Our aim was to develop and validate machine-learning-based diagnostic models to differentiate uncomplicated from complicated AA. This was a multicenter cohort trial conducted from January 2021 and December 2022 across five tertiary hospitals. Three distinct diagnostic models were created, namely, the clinical-parameter-based model, the CT-radiomics-based model, and the clinical-radiomics-fused model. These models were developed using a comprehensive set of eight machine-learning algorithms, which included logistic regression (LR), support vector machine (SVM), random forest (RF), decision tree (DT), gradient boosting (GB), K-nearest neighbors (KNN), Gaussian Naïve Bayes (GNB), and multi-layer perceptron (MLP). The performance and accuracy of these diverse models were compared. All models exhibited excellent diagnostic performance in the training cohort, achieving a maximal AUC of 1.00. For the clinical-parameter model, the GB classifier yielded the optimal AUC of 0.77 (95% confidence interval [CI]: 0.64-0.90) in the testing cohort, while the LR classifier yielded the optimal AUC of 0.76 (95% CI: 0.66-0.86) in the validation cohort. For the CT-radiomics-based model, GB classifier achieved the best AUC of 0.74 (95% CI: 0.60-0.88) in the testing cohort, and SVM yielded an optimal AUC of 0.63 (95% CI: 0.51-0.75) in the validation cohort. For the clinical-radiomics-fused model, RF classifier yielded an optimal AUC of 0.84 (95% CI: 0.74-0.95) in the testing cohort and 0.76 (95% CI: 0.67-0.86) in the validation cohort. An open-access, user-friendly online tool was developed for clinical application. This multicenter study suggests that the clinical-radiomics-fused model, constructed using RF algorithm, effectively differentiated between complicated and uncomplicated AA.

Diagnosis and treatment of endometrial diseases are crucial for women's health. Over the past decade, ultrasound has emerged as a non-invasive, safe, and cost-effective imaging tool, significantly contributing to endometrial disease diagnosis and generating extensive datasets. The introduction of artificial intelligence has enabled the application of machine learning and deep learning to extract valuable information from these datasets, enhancing ultrasound diagnostic capabilities. This paper reviews the progress of artificial intelligence in ultrasound image analysis for endometrial diseases, focusing on applications in diagnosis, decision support, and prognosis analysis. We also summarize current research challenges and propose potential solutions and future directions to advance ultrasound artificial intelligence technology in endometrial disease diagnosis, ultimately improving women's health through digital tools.

Prostate cancer is a common malignancy in men, and accurately distinguishing between benign and malignant nodules at an early stage is crucial for optimizing treatment. Multimodal imaging (such as ADC and T2) plays an important role in the diagnosis of prostate cancer, but effectively combining these imaging features for accurate classification remains a challenge. This retrospective study included MRI data from 199 prostate cancer patients. Radiomic features from both the tumor and peritumoral regions were extracted, and a random forest model was used to select the most contributive features for classification. Three machine learning models-Random Forest, XGBoost, and Extra Trees-were then constructed and trained on four different feature combinations (tumor ADC, tumor T2, tumor ADC+T2, and tumor + peritumoral ADC+T2). The model incorporating multimodal imaging features and peritumoral characteristics showed superior classification performance. The Extra Trees model outperformed the others across all feature combinations, particularly in the tumor + peritumoral ADC+T2 group, where the AUC reached 0.729. The AUC values for the other combinations also exceeded 0.65. While the Random Forest and XGBoost models performed slightly lower, they still demonstrated strong classification abilities, with AUCs ranging from 0.63 to 0.72. SHAP analysis revealed that key features, such as tumor texture and peritumoral gray-level features, significantly contributed to the model's classification decisions. The combination of multimodal imaging data with peritumoral features moderately improved the accuracy of prostate cancer classification. This model provides a non-invasive and effective diagnostic tool for clinical use and supports future personalized treatment decisions.