PurposeIn this study, we aimed to use advanced machine learning (ML) techniques, specifically transfer learning and Vision Transformers (ViTs), to accurately classify meningioma in brain MRI scans. ViTs process images similarly to how humans visually perceive details and are useful for analyzing complex medical images. Transfer learning is a technique that uses models previously trained on large datasets and adapts them to specific use cases. Using transfer learning, this study aimed to enhance the diagnostic accuracy of meningioma location and demonstrate the capabilities the new technology. ApproachWe used a Google ViT model pre-trained on ImageNet-21k (a dataset with 14 million images and 21,843 classes) and fine-tuned on ImageNet 2012 (a dataset with 1 million images and 1,000 classes). Using this model, which was pre-trained and fine-tuned on large datasets of images, allowed us to leverage the predictive capabilities of the model trained on those large datasets without needing to train an entirely new model specific to only meningioma MRI scans. Transfer learning was used to adapt the pre-trained ViT to our specific use case, being meningioma location classification, using a dataset of 1,094 images of T1, contrast-enhanced, and T2-weighted MRI scans of meningiomas sorted according to location in the brain, with 11 different classes. ResultsThe final model trained and adapted on the meningioma MRI dataset achieved an average validation accuracy of 98.17% and a test accuracy of 89.95%. ConclusionsThis study demonstrates the potential of ViTs in meningioma location classification, leveraging their ability to analyze spatial relationships in medical images. While transfer learning enabled effective adaptation with limited data, class imbalance affected classification performance. Future work should focus on expanding datasets and incorporating ensemble learning to improve diagnostic reliability.

Breast cancer screening with mammography remains central to early detection and mortality reduction. Deep learning has shown strong potential for automating mammogram interpretation, yet limited-resolution datasets and small sample sizes continue to restrict performance. We revisit the Mini-DDSM dataset (9,684 images; 2,414 patients) and introduce a lightweight region-of-interest (ROI) augmentation strategy. During training, full images are probabilistically replaced with random ROI crops sampled from a precomputed, label-free bounding-box bank, with optional jitter to increase variability. We evaluate under strict patient-level cross-validation and report ROC-AUC, PR-AUC, and training-time efficiency metrics (throughput and GPU memory). Because ROI augmentation is training-only, inference-time cost remains unchanged. On Mini-DDSM, ROI augmentation (best: p_roi = 0.10, alpha = 0.10) yields modest average ROC-AUC gains, with performance varying across folds; PR-AUC is flat to slightly lower. These results demonstrate that simple, data-centric ROI strategies can enhance mammography classification in constrained settings without requiring additional labels or architectural modifications.

To assess the performance of state-of-the-art large language models in classifying vertebral metastasis stability using the Spinal Instability Neoplastic Score (SINS) compared to human experts, and to evaluate the impact of task-specific refinement including in-context learning on their performance. This retrospective study analyzed 100 synthetic CT and MRI reports encompassing a broad range of SINS scores. Four human experts (two radiologists and two neurosurgeons) and four large language models (Mistral, Claude, GPT-4 turbo, and GPT-4o) evaluated the reports. Large language models were tested in both generic form and with task-specific refinement. Performance was assessed based on correct SINS category assignment and attributed SINS points. Human experts demonstrated high median performance in SINS classification (98.5% correct) and points calculation (92% correct), with a median point offset of 0 [0-0]. Generic large language models performed poorly with 26-63% correct category and 4-15% correct SINS points allocation. In-context learning significantly improved chatbot performance to near-human levels (96-98/100 correct for classification, 86-95/100 for scoring, no significant difference to human experts). Refined large language models performed 71-85% better in SINS points allocation. In-context learning enables state-of-the-art large language models to perform at near-human expert levels in SINS classification, offering potential for automating vertebral metastasis stability assessment. The poor performance of generic large language models highlights the importance of task-specific refinement in medical applications of artificial intelligence.

Chronic kidney disease (CKD) is an advancing disease which significantly impacts global healthcare, requiring early detection and prompt treatment is required to prevent its advancement to end-stage renal disease. Conventional diagnostic methods tend to be invasive, lengthy, and costly, creating a demand for automated, precise, and efficient solutions. This study proposes a novel technique for identifying and classifying CKD from medical images by utilizing a Convolutional Neural Network based Crow Search (CNN based CS) algorithm. The method employs sophisticated pre-processing techniques, including Z-score standardization, min-max normalization and robust scaling to improve the input data's quality. Selection of features is carried out using the chi-square test, and the Crow Search Algorithm (CSA) further optimizes the feature set for the improvement of accuracy classification and effectivess. The CNN architecture is employed to capture complex patterns using deep learning methods to accurately classify CKD in medical pictures. The model optimized and examined using an open access Kidney CT Scan data set. It achieved 99.05% accuracy, 99.03% Area under the Receiver Operating Characteristic Curve (AUC-ROC), and 99.01% Area under the precision-recall curve (PR-AUC), along with high precision (99.04%), recall (99.02%), and F1-score (99.00%). The results show that the CNN-based CS method delivers high accuracy and improved diagnostic precision related to conventional machine learning techniques. By incorporating CSA for feature optimization, the approach minimizes redundancy and improves model interpretability. This makes it a promising tool for automated CKD diagnosis, contributing to the development of AI-driven medical diagnostics and providing a scalable solution for early detection and management of CKD.

Colorectal cancer (CRC) is the third most common cause of cancer-related morbidity and mortality in the world. Radiomics and radiogenomics are utilized for the high-throughput quantification of features from medical images, providing non-invasive means to characterize cancer heterogeneity and gain insight into the underlying biology. Such radiomics-based artificial intelligence (AI)-methods have demonstrated great potential to improve the accuracy of CRC diagnosis and staging, to distinguish between benign and malignant lesions, to aid in the detection of lymph node and hepatic metastasis, and to predict the effects of therapy and prognosis for patients. This review presents the latest evidence on the clinical applications of radiomics models based on different imaging modalities in CRC. We also discuss the challenges facing clinical translation, including differences in image acquisition, issues related to reproducibility, a lack of standardization, and limited external validation. Given the progress of machine learning (ML) and deep learning (DL) algorithms, radiomics is expected to have an important effect on the personalized treatment of CRC and contribute to a more accurate and individualized clinical decision-making in the future.

Endoscopic ultrasound (EUS) is crucial for diagnosing and managing mediastinal diseases but lacks effective quality control. This study developed and evaluated an artificial intelligence (AI) system to assist in anatomical landmark identification and scanning guidance, aiming to improve quality control of mediastinal EUS examinations in clinical practice. The AI system for mediastinal EUS was trained on 11,230 annotated images from 120 patients, validated internally (1,972 images) and externally (824 images from three institutions). A single-center randomized controlled trial was designed to evaluate the effect of quality control, which enrolled patients requiring mediastinal EUS, randomized 1:1 to AI-assisted or control groups. Four endoscopists performed EUS, with the AI group receiving real-time AI feedback. The primary outcome was standard station completeness; secondary outcomes included structure completeness, procedure time, and adverse events. Blinded analysis ensured objectivity. Between 16 September 2023, and 28 February 2025, a total of 148 patients were randomly assigned and analyzed, with 72 patients in the AI-assisted group and 76 in the control group. The overall station completeness was significantly higher in the AI-assisted group than in the control group (1.00 [IQR, 1.00-1.00] vs. 0.80 [IQR, 0.60-0.80]; p < 0.001), with the AI-assisted group also demonstrating significantly higher anatomical structure completeness (1.00 [IQR, 1.00-1.00] vs. 0.85 [IQR, 0.62-0.92]; p < 0.001). However, no significant differences were found for station 2 (subcarinal area) or average procedural time, and no adverse events were reported. The AI system significantly improved the scan completeness and shows promise in enhancing EUS quality control.

Pulmonary hypertension (PH) is a progressive disorder characterized by elevated pulmonary artery pressure and increased pulmonary vascular resistance, ultimately leading to right heart failure. Early detection is critical for improving patient outcomes. The diagnosis of PH primarily relies on right heart catheterization, but its invasive nature significantly limits its clinical use. Echocardiography, as the most common noninvasive screening and diagnostic tool for PH, provides valuable patient information. This study aims to identify key PH predictors from echocardiographic parameters, laboratory tests, and demographic data using machine learning, ultimately constructing a predictive model to support early noninvasive diagnosis of PH. This study compiled comprehensive datasets comprising echocardiography measurements, clinical laboratory data, and fundamental demographic information from patients with PH and matched controls. The final analytical cohort consisted of 895 participants with 85 evaluated variables. Recursive feature elimination was used to select the most relevant echocardiographic variables, which were subsequently integrated into a composite ultrasound index using machine learning techniques, XGBoost (Extreme Gradient Boosting). LASSO (least absolute shrinkage and selection operator) regression was applied to select the potential predictive variable from laboratory tests. Then, the ultrasound index variables and selected laboratory tests were combined to construct a logistic regression model for the predictive diagnosis of PH. The model's performance was rigorously evaluated using receiver operating characteristic curves, calibration plots, and decision curve analysis to ensure its clinical relevance and accuracy. Both internal and external validation were used to assess the performance of the constructed model. A total of 16 echocardiographic parameters (right atrium diameter, pulmonary artery diameter, left atrium diameter, tricuspid valve reflux degree, right ventricular diameter, E/E' [ratio of mitral valve early diastolic inflow velocity (E) to mitral annulus early diastolic velocity (E')], interventricular septal thickness, left ventricular diameter, ascending aortic diameter, left ventricular ejection fraction, left ventricular outflow tract velocity, mitral valve reflux degree, pulmonary valve outflow velocity, mitral valve inflow velocity, aortic valve reflux degree, and left ventricular posterior wall thickness) combined with 2 laboratory biomarkers (prothrombin time activity and cystatin C) were identified as optimal predictors, forming a high-performance PH prediction model. The diagnostic model demonstrated high predictive accuracy, with an area under the receiver operating characteristic curve of 0.997 in the internal validation and 0.974 in the external validation. Both calibration plots and decision curve analysis validated the model's predictive accuracy and clinical applicability, with optimal performance observed at higher risk stratification cutoffs. This model enhances early PH diagnosis through a noninvasive approach and demonstrates strong predictive accuracy. It facilitates early intervention and personalized treatment, with potential applications in broader cardiovascular disease management.

Serological screening, endoscopic imaging, morphological visual verification of precancerous gastric diseases and changes in the gastric mucosa are the main stages of early detection, accurate diagnosis and preventive treatment of gastric precancer. Laboratory - serological, endoscopic and histological diagnostics are carried out by medical laboratory technicians, endoscopists, and histologists. Human factors have a very large share of subjectivity. Endoscopists and histologists are guided by the descriptive principle when formulating imaging conclusions. Diagnostic reports from doctors often result in contradictory and mutually exclusive conclusions. Erroneous results of diagnosticians and clinicians have fatal consequences, such as late diagnosis of gastric cancer and high mortality of patients. Effective population serological screening is only possible with the use of machine processing of laboratory test results. Currently, it is possible to replace subjective imprecise description of endoscopic and histological images by a diagnostician with objective, highly sensitive and highly specific visual recognition using convolutional neural networks with deep machine learning. There are many machine learning models to use. All machine learning models have predictive capabilities. Based on predictive models, it is necessary to identify the risk levels of gastric cancer in patients with a very high probability.

Public healthcare datasets of Chest X-Rays (CXRs) have long been a popular benchmark for developing computer vision models in healthcare. However, strong average-case performance of machine learning (ML) models on these datasets is insufficient to certify their clinical utility. In this paper, we use clinical context, as captured by prior discharge summaries, to provide a more holistic evaluation of current ``state-of-the-art'' models for the task of CXR diagnosis. Using discharge summaries recorded prior to each CXR, we derive a ``prior'' or ``pre-test'' probability of each CXR label, as a proxy for existing contextual knowledge available to clinicians when interpreting CXRs. Using this measure, we demonstrate two key findings: First, for several diagnostic labels, CXR models tend to perform best on cases where the pre-test probability is very low, and substantially worse on cases where the pre-test probability is higher. Second, we use pre-test probability to assess whether strong average-case performance reflects true diagnostic signal, rather than an ability to infer the pre-test probability as a shortcut. We find that performance drops sharply on a balanced test set where this shortcut does not exist, which may indicate that much of the apparent diagnostic power derives from inferring this clinical context. We argue that this style of analysis, using context derived from clinical notes, is a promising direction for more rigorous and fine-grained evaluation of clinical vision models.

This study aimed to identify key image parameters from the traditional and advanced MR sequences within the peritumoral edema in glioblastoma, which could predict the sub-volume with high risk of tumor recurrence. The retrospective cohort involved 32 cases with recurrent glioblastoma, while the retrospective validation cohort consisted of 5 cases. The volume of interest (VOI) including tumor and edema were manually contoured on each MR sequence. Rigid registration was performed between sequences before and after tumor recurrence. The edema before tumor recurrence was divided into the subedema-rec and subedema-no-rec depending on whether tumors occurred after registration. The histogram parameters of VOI on each sequence were collected and statistically analyzed. Beside Spearman's rank correlation analysis, Wilcoxon's paired test, least absolute shrinkage and selection operator (LASSO) analysis, and a forward stepwise logistic regression model(FSLRM) comparing with two machine learning models was developed to distinguish the subedema-rec and subedema-no-rec. The efficiency and applicability of the model was evaluated using receiver operating characteristic (ROC) curve analysis, image prediction and pathological detection. Differences of the characteristics from the ADC map between the subedema-rec and subedema-no-rec were identified, which included the standard deviation of the mean ADC value (stdmeanADC), the maximum ADC value (maxiADC), the minimum ADC value (miniADC), the Ratio-maxiADC/meanADC (maxiADC divided by the meanADC), and the kurtosis coefficient of the ADC value (all P < 0.05). FSLRM showed that the area under the ROC curve (AUC) of a single-parameter model based on Ratio-maxiADC/meanADC (0.823) was higher than that of the support vector machine (0.813) and random forest models (0.592), compared to the retrospective validation cohort's AUC of 0.776. The location prediction in image revealed that tumor recurrent mostly in the area with Ratio-maxiADC/meanADC less than 2.408. Pathological detection in 10 patients confirmed that the tumor cell dotted within the subedema-rec while not in the subedema-no-rec. The Ratio-maxiADC/meanADC is useful in predicting location of the subedema-rec.