BackgroundGenerative Pre-trained Transformer 4 (GPT-4) has demonstrated strong performance in standardized medical examinations but has limitations in real-world clinical settings. The newly released multimodal GPT-4o model, which integrates text and image inputs to enhance diagnostic capabilities, and the multimodal o1 model, which incorporates advanced reasoning, may address these limitations. ObjectiveThis study aimed to compare the performance of GPT-4o and o1 against clinicians in real-world clinical case challenges. MethodsThis retrospective, cross-sectional study used Medscape case challenge questions from May 2011 to June 2024 (n = 1,426). Each case included text and images of patient history, physical examination findings, diagnostic test results, and imaging studies. Clinicians were required to choose one answer from among multiple options, with the most frequent response defined as the clinicians decision. Data-based decisions were made using GPT models (3.5 Turbo, 4 Turbo, 4 Omni, and o1) to interpret the text and images, followed by a process to provide a formatted answer. We compared the performances of the clinicians and GPT models using Mixed-effects logistic regression analysis. ResultsOf the 1,426 questions, clinicians achieved an overall accuracy of 85.0%, whereas GPT-4o and o1 demonstrated higher accuracies of 88.4% and 94.3% (mean difference 3.4%; P = .005 and mean difference 9.3%; P < .001), respectively. In the multimodal performance analysis, which included cases involving images (n = 917), GPT-4o achieved an accuracy of 88.3%, and o1 achieved 93.9%, both significantly outperforming clinicians (mean difference 4.2%; P = .005 and mean difference 9.8%; P < .001). o1 showed the highest accuracy across all question categories, achieving 92.6% in diagnosis (mean difference 14.5%; P < .001), 97.0% in disease characteristics (mean difference 7.2%; P < .001), 92.6% in examination (mean difference 7.3%; P = .002), and 94.8% in treatment (mean difference 4.3%; P = .005), consistently outperforming clinicians. In terms of medical specialty, o1 achieved 93.6% accuracy in internal medicine (mean difference 10.3%; P < .001), 96.6% in major surgery (mean difference 9.2%; P = .030), 97.3% in psychiatry (mean difference 10.6%; P = .030), and 95.4% in minor specialties (mean difference 10.0%; P < .001), significantly surpassing clinicians. Across five trials, GPT-4o and o1 provided the correct answer 5/5 times in 86.2% and 90.7% of the cases, respectively. ConclusionsThe GPT-4o and o1 models achieved higher accuracy than clinicians in clinical case challenge questions, particularly in disease diagnosis. The GPT-4o and o1 could serve as valuable tools to assist healthcare professionals in clinical settings.

PurposeTo assess and compare the accuracy and legitimacy of multimodal large language models (LLMs) on the Japan Diagnostic Radiology Board Examination (JDRBE). Materials and methodsThe dataset comprised questions from JDRBE 2021, 2023, and 2024, with ground-truth answers established through consensus among multiple board-certified diagnostic radiologists. Questions without associated images and those lacking unanimous agreement on answers were excluded. Eight LLMs were evaluated: GPT-4 Turbo, GPT-4o, GPT-4.5, GPT-4.1, o3, o4-mini, Claude 3.7 Sonnet, and Gemini 2.5 Pro. Each model was evaluated under two conditions: with inputting images (vision) and without (text-only). Performance differences between the conditions were assessed using McNemars exact test. Two diagnostic radiologists (with 2 and 18 years of experience) independently rated the legitimacy of responses from four models (GPT-4 Turbo, Claude 3.7 Sonnet, o3, and Gemini 2.5 Pro) using a five-point Likert scale, blinded to model identity. Legitimacy scores were analyzed using Friedmans test, followed by pairwise Wilcoxon signed-rank tests with Holm correction. ResultsThe dataset included 233 questions. Under the vision condition, o3 achieved the highest accuracy at 72%, followed by o4-mini (70%) and Gemini 2.5 Pro (70%). Under the text-only condition, o3 topped the list with an accuracy of 67%. Addition of image input significantly improved the accuracy of two models (Gemini 2.5 Pro and GPT-4.5), but not the others. Both o3 and Gemini 2.5 Pro received significantly higher legitimacy scores than GPT-4 Turbo and Claude 3.7 Sonnet from both raters. ConclusionRecent multimodal LLMs, particularly o3 and Gemini 2.5 Pro, have demonstrated remarkable progress on JDRBE questions, reflecting their rapid evolution in diagnostic radiology. Secondary abstract Eight multimodal large language models were evaluated on the Japan Diagnostic Radiology Board Examination. OpenAIs o3 and Google DeepMinds Gemini 2.5 Pro achieved high accuracy rates (72% and 70%) and received good legitimacy scores from human raters, demonstrating steady progress.

PURPOSECardiac amyloidosis (CA), a life-threatening infiltrative cardiomyopathy, can be non-invasively diagnosed using [99mTc]Tc-bisphosphonate SPECT/CT. However, subjective visual interpretation risks diagnostic inaccuracies. We developed and validated a machine learning (ML) framework leveraging SPECT/CT radiomics to automate CA detection. METHODSThis retrospective multicenter study analyzed 290 patients of suspected CA who underwent [99mTc]Tc-PYP or [99mTc]Tc-DPD SPECT/CT. Radiomic features were extracted from co-registered SPECT and CT images, harmonized via intra-class correlation and Pearson correlation filtering, and optimized through LASSO regression. A stacking ensemble model incorporating support vector machine (SVM), random forest (RF), gradient boosting decision tree (GBDT), and adaptive boosting (AdaBoost) classifiers was constructed. The model was validated using an internal validation set (n = 54) and two external test set (n = 54 and n = 58).Model performance was evaluated using the area under the receiver operating characteristic curve (AUC), calibration, and decision curve analysis (DCA). Feature importance was interpreted using SHapley Additive exPlanations (SHAP) values. RESULTSOf 290 patients, 117 (40.3%) had CA. The stacking radiomics model attained AUCs of 0.871, 0.824, and 0.839 in the validation, test 1, and test 2 cohorts, respectively, significantly outperforming the clinical model (AUC 0.546 in validation set, P<0.05). DCA demonstrated superior net benefit over the clinical model across relevant thresholds, and SHAP analysis highlighted wavelet-transformed first-order and texture features as key predictors. CONCLUSIONA stacking ML model with SPECT/CT radiomics improves CA diagnosis, showing strong generalizability across varied imaging protocols and populations and highlighting its potential as a decision-support tool.

Acute ischemic stroke (AIS) remains the leading cause of mortality and disability worldwide. While revascularization therapies-such as intravenous thrombolysis (IVT) and endovascular thrombectomy (EVT)-have significantly improved outcomes, their success is strongly influenced by the status of cerebral collateral circulation. Collateral vessels sustain cerebral perfusion during vascular occlusion, limiting infarct growth and extending therapeutic windows. Despite this recognized importance, standardized methods for assessing collateral status and integrating it into treatment strategies are still evolving. This narrative review synthesizes current evidence on the role of collateral circulation in AIS, focusing on its impact on infarct dynamics, treatment efficacy, and functional recovery. We highlight findings from major clinical trials-including MR CLEAN, DAWN, DEFUSE-3, and SWIFT PRIME which consistently demonstrate that robust collateral networks are associated with improved outcomes and expanded eligibility for reperfusion therapies. Advances in neuroimaging, such as multiphase CTA and perfusion MRI, alongside emerging AI-driven automated collateral grading, are reshaping patients' selection and clinical decision-making. We also discuss novel therapeutic strategies aimed at enhancing collateral flow, such as vasodilators, neuroprotective agents, statins, and stem cell therapies. Despite growing evidence supporting collateral-based treatment approaches, real-time clinical implementation remains limited by challenges in standardization and access. Cerebral collateral circulation is a critical determinant of stroke prognosis and treatment response. Incorporating collateral assessment into acute stroke workflows-supported by advanced imaging, artificial intelligence, and personalized medicine-offers a promising pathway to optimize outcomes. As the field moves beyond a strict "time is brain" model, the emerging paradigm of "time is collaterals" may better reflect the dynamic interplay between perfusion, tissue viability, and therapeutic opportunity in AIS management.

Radiographic knee alignment (KA) measurement is important for predicting joint health and surgical outcomes after total knee replacement. Traditional methods for KA measurements are manual, time-consuming and require long-leg radiographs. This study proposes a deep learning-based method to measure KA in anteroposterior knee radiographs via automatically localized knee anatomical landmarks. Our method builds on hourglass networks and incorporates an attention gate structure to enhance robustness and focus on key anatomical features. To our knowledge, this is the first deep learning-based method to localize over 100 knee anatomical landmarks to fully outline the knee shape while integrating KA measurements on both pre-operative and post-operative images. It provides highly accurate and reliable anatomical varus/valgus KA measurements using the anatomical tibiofemoral angle, achieving mean absolute differences ~1{\deg} when compared to clinical ground truth measurements. Agreement between automated and clinical measurements was excellent pre-operatively (intra-class correlation coefficient (ICC) = 0.97) and good post-operatively (ICC = 0.86). Our findings demonstrate that KA assessment can be automated with high accuracy, creating opportunities for digitally enhanced clinical workflows.

Deep learning-based medical image classification techniques are rapidly advancing in medical image analysis, making it crucial to develop accurate and trustworthy models that can be efficiently deployed across diverse clinical scenarios. Concept Bottleneck Models (CBMs), which first predict a set of explainable concepts from images and then perform classification based on these concepts, are increasingly being adopted for explainable medical image classification. However, the inherent explainability of CBMs introduces new challenges when deploying trained models to new environments. Variations in imaging protocols and staining methods may induce concept-level shifts, such as alterations in color distribution and scale. Furthermore, since CBM training requires explicit concept annotations, fine-tuning models solely with image-level labels could compromise concept prediction accuracy and faithfulness - a critical limitation given the high cost of acquiring expert-annotated concept labels in medical domains. To address these challenges, we propose a training-free confusion concept identification strategy. By leveraging minimal new data (e.g., 4 images per class) with only image-level labels, our approach enhances out-of-domain performance without sacrificing source domain accuracy through two key operations: masking misactivated confounding concepts and amplifying under-activated discriminative concepts. The efficacy of our method is validated on both skin and white blood cell images. Our code is available at: https://github.com/riverback/TF-TTI-XMed.

Aimed to develop and validate a CT radiomics-based explainable machine learning model for diagnosing malignancy and benignity specifically in endometrial cancer (EC) patients. A total of 83 EC patients from two centers, including 46 with malignant and 37 with benign conditions, were included, with data split into a training set (n=59) and a testing set (n=24). The regions of interest (ROIs) were manually segmented from pre-surgical CT scans, and 1132 radiomic features were extracted from the pre-surgical CT scans using Pyradiomics. Six explainable machine learning modeling algorithms were implemented respectively, for determining the optimal radiomics pipeline. The diagnostic performance of the radiomic model was evaluated by using sensitivity, specificity, accuracy, precision, F1 score, confusion matrices, and ROC curves. To enhance clinical understanding and usability, we separately implemented SHAP analysis and feature mapping visualization, and evaluated the calibration curve and decision curve. By comparing six modeling strategies, the Random Forest model emerged as the optimal choice for diagnosing EC, with a training AUC of 1.00 and a testing AUC of 0.96. SHAP identified the most important radiomic features, revealing that all selected features were significantly associated with EC (P < 0.05). Radiomics feature maps also provide a feasible assessment tool for clinical applications. DCA indicated a higher net benefit for our model compared to the "All" and "None" strategies, suggesting its clinical utility in identifying high-risk cases and reducing unnecessary interventions. In conclusion, the CT radiomics-based explainable machine learning model achieved high diagnostic performance, which could be used as an intelligent auxiliary tool for the diagnosis of endometrial cancer.

Thyroid cancer is among the most common cancers in the United States. Thyroid nodules are frequently detected through ultrasound (US) imaging, and some require further evaluation via fine-needle aspiration (FNA) biopsy. Despite its effectiveness, FNA often leads to unnecessary biopsies of benign nodules, causing patient discomfort and anxiety. To address this, the American College of Radiology Thyroid Imaging Reporting and Data System (TI-RADS) has been developed to reduce benign biopsies. However, such systems are limited by interobserver variability. Recent deep learning approaches have sought to improve risk stratification, but they often fail to utilize the rich temporal and spatial context provided by US cine clips, which contain dynamic global information and surrounding structural changes across various views. In this work, we propose the Spatio-Temporal Cross Attention for Cine Thyroid Ultrasound Time Series Classification (STACT-Time) model, a novel representation learning framework that integrates imaging features from US cine clips with features from segmentation masks automatically generated by a pretrained model. By leveraging self-attention and cross-attention mechanisms, our model captures the rich temporal and spatial context of US cine clips while enhancing feature representation through segmentation-guided learning. Our model improves malignancy prediction compared to state-of-the-art models, achieving a cross-validation precision of 0.91 (plus or minus 0.02) and an F1 score of 0.89 (plus or minus 0.02). By reducing unnecessary biopsies of benign nodules while maintaining high sensitivity for malignancy detection, our model has the potential to enhance clinical decision-making and improve patient outcomes.

With the advancement of Large Language Model (LLM) for natural language processing, this paper presents an intriguing finding: a frozen pre-trained LLM layer can process visual tokens for medical image segmentation tasks. Specifically, we propose a simple hybrid structure that integrates a pre-trained, frozen LLM layer within the CNN encoder-decoder segmentation framework (LLM4Seg). Surprisingly, this design improves segmentation performance with a minimal increase in trainable parameters across various modalities, including ultrasound, dermoscopy, polypscopy, and CT scans. Our in-depth analysis reveals the potential of transferring LLM's semantic awareness to enhance segmentation tasks, offering both improved global understanding and better local modeling capabilities. The improvement proves robust across different LLMs, validated using LLaMA and DeepSeek.

Synthetic data has recently reached a level of visual fidelity that makes it nearly indistinguishable from real data, offering great promise for privacy-preserving data sharing in medical imaging. However, fully synthetic datasets still suffer from significant limitations: First and foremost, the legal aspect of sharing synthetic data is often neglected and data regulations, such as the GDPR, are largley ignored. Secondly, synthetic models fall short of matching the performance of real data, even for in-domain downstream applications. Recent methods for image generation have focused on maximising image diversity instead of fidelity solely to improve the mode coverage and therefore the downstream performance of synthetic data. In this work, we shift perspective and highlight how maximizing diversity can also be interpreted as protecting natural persons from being singled out, which leads to predicate singling-out (PSO) secure synthetic datasets. Specifically, we propose a generalisable framework for training diffusion models on personal data which leads to unpersonal synthetic datasets achieving performance within one percentage point of real-data models while significantly outperforming state-of-the-art methods that do not ensure privacy. Our code is available at https://github.com/MischaD/Trichotomy.