People who are screened for breast cancer by AI-supported radiologists are less likely to develop aggressive cancers before their next screening round than those who are screened by radiologists alone, raising hopes that AI-assisted screening could save lives. "This is the first randomised controlled trial on the use of AI in mammography screening," says Kristina Lång at Lund University in Sweden. The AI-supported approach involves using the software - which has been trained on more than 200,000 mammography scans from 10 countries - to rank the likelihood of cancer being present in mammograms on a scale of 1 to 10, based on visual patterns in the scans. The scans receiving a score of 1 to 9 are then assessed by one experienced radiologist, while scans receiving a score of 10 - indicating cancer is most likely to be present - are assessed by two experienced radiologists. An earlier study found that this approach could detect 29 per cent more cancers than standard screening, where each mammogram is assessed by two radiologists, without increasing the rate of false detections - where a growth is flagged but follow-up tests reveal it isn't actually there or wouldn't go on to cause problems.

AI is asbestos in the walls of our tech society, stuffed there by monopolists run amok. What I do not do is predict the future. No one can predict the future, which is a good thing, since if the future were predictable, that would mean we couldn't change it. Now, not everyone understands the distinction. They think science-fiction writers are oracles. Even some of my colleagues labor under the delusion that we can "see the future". Then there are science-fiction fans who believe that they are the future. A depressing number of those people appear to have become AI bros. These guys can't shut up about the day that their spicy autocomplete machine will wake up and turn us all into paperclips has led many confused journalists and conference organizers to try to get me to comment on the future of AI. That's something I used to strenuously resist doing, because I wasted two years of my life explaining patiently and repeatedly why I thought crypto was stupid, and getting relentlessly bollocked by cryptocurrency cultists who at first insisted that I just didn't understand crypto.

In the medical multi-modal frameworks, the alignment of cross-modality features presents a significant challenge. However, existing works have learned features that are implicitly aligned from the data, without considering the explicit relationships in the medical context. This data-reliance may lead to low generalization of the learned alignment relationships. In this work, we propose the Eye-gaze Guided Multi-modal Alignment (EGMA) framework to harness eye-gaze data for better alignment of medical visual and textual features. We explore the natural auxiliary role of radiologists' eye-gaze data in aligning medical images and text, and introduce a novel approach by using eye-gaze data, collected synchronously by radiologists during diagnostic evaluations. We conduct downstream tasks of image classification and image-text retrieval on four medical datasets, where EGMA achieved state-of-the-art performance and stronger generalization across different datasets. Additionally, we explore the impact of varying amounts of eye-gaze data on model performance, highlighting the feasibility and utility of integrating this auxiliary data into multi-modal alignment framework.

Accurate segmentation of vertebral metastasis in CT is clinically important yet difficult to scale, as voxel-level annotations are scarce and both lytic and blastic lesions often resemble benign degenerative changes. We introduce a weakly supervised method trained solely on vertebra-level healthy/malignant labels, without any lesion masks. The method combines a Diffusion Autoencoder (DAE) that produces a classifier-guided healthy edit of each vertebra with pixel-wise difference maps that propose candidate lesion regions. To determine which regions truly reflect malignancy, we introduce Hide-and-Seek Attribution: each candidate is revealed in turn while all others are hidden, the edited image is projected back to the data manifold by the DAE, and a latent-space classifier quantifies the isolated malignant contribution of that component. High-scoring regions form the final lytic or blastic segmentation. On held-out radiologist annotations, we achieve strong blastic/lytic performance despite no mask supervision (F1: 0.91/0.85; Dice: 0.87/0.78), exceeding baselines (F1: 0.79/0.67; Dice: 0.74/0.55). These results show that vertebra-level labels can be transformed into reliable lesion masks, demonstrating that generative editing combined with selective occlusion supports accurate weakly supervised segmentation in CT.

Segmentation is the identification of anatomical regions of interest, such as organs, tissue, and lesions, serving as a fundamental task in computer-aided diagnosis in medical imaging. Although deep learning models have achieved remarkable performance in medical image segmentation, the need for explainability remains critical for ensuring their acceptance and integration in clinical practice, despite the growing research attention in this area. Our approach explored the use of contrast-level Shapley values, a systematic perturbation of model inputs to assess feature importance. While other studies have investigated gradient-based techniques through identifying influential regions in imaging inputs, Shapley values offer a broader, clinically aligned approach, explaining how model performance is fairly attributed to certain imaging contrasts over others. Using the BraTS 2024 dataset, we generated rankings for Shapley values for four MRI contrasts across four model architectures. Two metrics were proposed from the Shapley ranking: agreement between model and ``clinician" imaging ranking, and uncertainty quantified through Shapley ranking variance across cross-validation folds. Higher-performing cases (Dice \textgreater0.6) showed significantly greater agreement with clinical rankings. Increased Shapley ranking variance correlated with decreased performance (U-Net: $r=-0.581$). These metrics provide clinically interpretable proxies for model reliability, helping clinicians better understand state-of-the-art segmentation models.

Deep learning has shown strong performance in musculoskeletal imaging, but prior work has largely targeted conditions where diagnosis is relatively straightforward. More challenging problems remain underexplored, such as detecting Bankart lesions (anterior-inferior glenoid labral tears) on standard MRIs. These lesions are difficult to diagnose due to subtle imaging features, often necessitating invasive MRI arthrograms (MRAs). We introduce ScopeMRI, the first publicly available, expert-annotated dataset for shoulder pathologies, and present a deep learning framework for Bankart lesion detection on both standard MRIs and MRAs. ScopeMRI contains shoulder MRIs from patients who underwent arthroscopy, providing ground-truth labels from intraoperative findings, the diagnostic gold standard. Separate models were trained for MRIs and MRAs using CNN- and transformer-based architectures, with predictions ensembled across multiple imaging planes. Our models achieved radiologist-level performance, with accuracy on standard MRIs surpassing radiologists interpreting MRAs. External validation on independent hospital data demonstrated initial generalizability across imaging protocols. By releasing ScopeMRI and a modular codebase for training and evaluation, we aim to accelerate research in musculoskeletal imaging and foster development of datasets and models that address clinically challenging diagnostic tasks.

Purpose: To benchmark open-source or commercial medical image-specific VLMs against real-world radiologist-written reports. Methods: This retrospective study included adult patients who presented to the emergency department between January 2022 and April 2025 and underwent same-day CXR and CT for febrile or respiratory symptoms. Reports from five VLMs (AIRead, Lingshu, MAIRA-2, MedGemma, and MedVersa) and radiologist-written reports were randomly presented and blindly evaluated by three thoracic radiologists using four criteria: RADPEER, clinical acceptability, hallucination, and language clarity. Comparative performance was assessed using generalized linear mixed models, with radiologist-written reports treated as the reference. Finding-level analyses were also performed with CT as the reference. Results: A total of 478 patients (median age, 67 years [interquartile range, 50-78]; 282 men [59.0%]) were included. AIRead demonstrated the lowest RADPEER 3b rate (5.3% [76/1434] vs. radiologists 13.9% [200/1434]; P<.001), whereas other VLMs showed higher disagreement rates (16.8-43.0%; P<.05). Clinical acceptability was the highest with AIRead (84.5% [1212/1434] vs. radiologists 74.3% [1065/1434]; P<.001), while other VLMs performed worse (41.1-71.4%; P<.05). Hallucinations were rare with AIRead, comparable to radiologists (0.3% [4/1425]) vs. 0.1% [1/1425]; P=.21), but frequent with other models (5.4-17.4%; P<.05). Language clarity was higher with AIRead (82.9% [1189/1434]), Lingshu (88.0% [1262/1434]), and MedVersa (88.4% [1268/1434]) compared with radiologists (78.1% [1120/1434]; P<.05). Sensitivity varied substantially across VLMs for the common findings: AIRead, 15.5-86.7%; Lingshu, 2.4-86.7%; MAIRA-2, 6.0-72.0%; MedGemma, 4.8-76.7%; and MedVersa, 20.2-69.3%. Conclusion: Medical VLMs for CXR report generation exhibited variable performance in report quality and diagnostic measures.

AI-assisted report generation offers the opportunity to reduce radiologists' workload stemming from expanded screening guidelines, complex cases and workforce shortages, while maintaining diagnostic accuracy. In addition to describing pathological findings in chest X-ray reports, interpreting lines and tubes (L&T) is demanding and repetitive for radiologists, especially with high patient volumes. We introduce MAIRA-X, a clinically evaluated multimodal AI model for longitudinal chest X-ray (CXR) report generation, that encompasses both clinical findings and L&T reporting. Developed using a large-scale, multi-site, longitudinal dataset of 3.1 million studies (comprising 6 million images from 806k patients) from Mayo Clinic, MAIRA-X was evaluated on three holdout datasets and the public MIMIC-CXR dataset, where it significantly improved AI-generated reports over the state of the art on lexical quality, clinical correctness, and L&T-related elements. A novel L&T-specific metrics framework was developed to assess accuracy in reporting attributes such as type, longitudinal change and placement. A first-of-its-kind retrospective user evaluation study was conducted with nine radiologists of varying experience, who blindly reviewed 600 studies from distinct subjects. The user study found comparable rates of critical errors (3.0% for original vs. 4.6% for AI-generated reports) and a similar rate of acceptable sentences (97.8% for original vs. 97.4% for AI-generated reports), marking a significant improvement over prior user studies with larger gaps and higher error rates. Our results suggest that MAIRA-X can effectively assist radiologists, particularly in high-volume clinical settings.

With the rapid advancement of retrieval-augmented vision-language models, multimodal medical retrieval-augmented generation (MMed-RAG) systems are increasingly adopted in clinical decision support. These systems enhance medical applications by performing cross-modal retrieval to integrate relevant visual and textual evidence for tasks, e.g., report generation and disease diagnosis. However, their complex architecture also introduces underexplored adversarial vulnerabilities, particularly via visual input perturbations. In this paper, we propose Medusa, a novel framework for crafting cross-modal transferable adversarial attacks on MMed-RAG systems under a black-box setting. Specifically, Medusa formulates the attack as a perturbation optimization problem, leveraging a multi-positive InfoNCE loss (MPIL) to align adversarial visual embeddings with medically plausible but malicious textual targets, thereby hijacking the retrieval process. To enhance transferability, we adopt a surrogate model ensemble and design a dual-loop optimization strategy augmented with invariant risk minimization (IRM). Extensive experiments on two real-world medical tasks, including medical report generation and disease diagnosis, demonstrate that Medusa achieves over 90% average attack success rate across various generation models and retrievers under appropriate parameter configuration, while remaining robust against four mainstream defenses, outperforming state-of-the-art baselines. Our results reveal critical vulnerabilities in the MMed-RAG systems and highlight the necessity of robustness benchmarking in safety-critical medical applications. The code and data are available at https://anonymous.4open.science/r/MMed-RAG-Attack-F05A.

Chest radiography remains one of the most widely used imaging modalities for thoracic diagnosis, yet increasing imaging volumes and radiologist workload continue to challenge timely interpretation. In this work, we investigate the use of MedImageInsight, a medical imaging foundational model, for automated binary classification of chest X-rays into Normal and Abnormal categories. Two approaches were evaluated: (1) fine-tuning MedImageInsight for end-to-end classification, and (2) employing the model as a feature extractor for a transfer learning pipeline using traditional machine learning classifiers. Experiments were conducted using a combination of the ChestX-ray14 dataset and real-world clinical data sourced from partner hospitals. The fine-tuned classifier achieved the highest performance, with an ROC-AUC of 0.888 and superior calibration compared to the transfer learning models, demonstrating performance comparable to established architectures such as CheXNet. These results highlight the effectiveness of foundational medical imaging models in reducing task-specific training requirements while maintaining diagnostic reliability. The system is designed for integration into web-based and hospital PACS workflows to support triage and reduce radiologist burden. Future work will extend the model to multi-label pathology classification to provide preliminary diagnostic interpretation in clinical environments.