arXiv:2509. 19671v3 Announce Type: replace Abstract: Public datasets of Chest X-Rays (CXRs) have long been a popular benchmark for developing machine learning (ML) computer vision models in healthcare.
arXiv:2607. 26333v1 Announce Type: cross Abstract: Chest X-ray (CXR) machine learning relies heavily on automated evaluation using reference standards that aim to approximate clinical judgment.
arXiv:2605.07785v3 Announce Type: replace Abstract: Concept Bottleneck Models (CBMs) in medical imaging aim to improve model interpretability by predicting intermediate clinical concepts before final...
arXiv:2608. 09774v1 Announce Type: cross Abstract: Thoracic pathologies rarely occur in isolation, yet standard multi-label classifiers rely on shared global descriptors, discarding \emph{where} findings lie and \emph{how} they co-occur.
Med-AR introduces two autoregressive vision‑language models, Med‑AR‑8B and Med‑AR‑2B, pretrained on structured radiology reports, abnormality‑focused text, and region annotations to address long‑tailed chest X‑ray classification. The models outperform existing contrastive, self‑supervised, and supervised encoders—including Med‑CLIP, CheXFound, EVA‑Base, ARK, and BioViL‑T—across PadChest, MIMIC‑CXR, and CheXpert, achieving higher mean AUROC and AUPRC for head, medium, and tail findings and lower excess area under the risk‑coverage curve. Med‑AR also demonstrates improved selective‑prediction performance, with Med‑AR‑8B raising tail‑label mean AUPRC on MIMIC‑CXR from 0.1033 to 0.1441 and Med‑AR‑2B delivering the strongest discrimination on PadChest.
Current evaluation protocols for Vision-Language Models (VLMs) in Radiology Report Generation (RRG) rely on report-level metrics that measure lexical overlap or aggregate clinical correctness. However, such metrics do not test whether individual diagnostic statements stem from the actual pathological evidence visible in the image.
The CXR‑LT 2026 Challenge introduces a multi‑center, long‑tailed chest X‑ray classification benchmark with over 145,000 radiologist‑annotated images from PadChest and NIH datasets. It defines two core tasks: robust multi‑label classification on 30 known classes and open‑world generalization to 6 unseen rare disease classes. The paper outlines data collection, annotation, solution strategies, and evaluates performance across head‑vs‑tail, calibration, and cross‑center gaps, noting that vision‑language models improve in‑distribution and zero‑shot performance but rare‑finding detection under multi‑center shift remains difficult.
arXiv:2606. 17710v1 Announce Type: cross Abstract: Medical vision-language models report strong chest radiograph accuracy, and this is increasingly read as evidence that they use the image.
The study examines how differences in radiologists’ reporting styles—such as terminology, shorthand, formatting, and detail—affect the evaluation of AI-generated chest X‑ray reports. By quantifying the sensitivity of common metrics to these variations, the authors show that changes in reference reports can shift model rankings. They introduce a taxonomy of reporting variations and a rewriting method, ReRef, that preserves clinical meaning while altering style, and release a validated dataset of paired reference reports to aid future research.
arXiv:2608. 05341v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) for radiology report generation are typically trained on retrospective clinical reports, which suffer from omission noise: clinically present findings are left unreported due to the omission of subtle findings.
The study evaluates the robustness of medical vision‑language models for tuberculosis screening on chest X‑rays by testing them across multiple datasets, prompts, and evaluation settings. Three specialized models (BioMedCLIP, CheXficient, MedSigLIP) and a general OpenCLIP model were audited on 12,200 images, producing 244,000 model–image–prompt scores. Results show that no model consistently outperforms others across all cohorts and reliability criteria, with prompt changes and control group composition significantly affecting AUROC, and that high training‑set performance does not reliably transfer to external cohorts.
The paper introduces a label‑free method called AURCC for selecting the best foundational model for medical image classification when the target domain lacks labels. AURCC uses a pseudo‑label discrepancy computed by the SUDO framework to score models without fine‑tuning. Experiments on chest X‑ray data across three inter‑hospital shifts show that AURCC closely matches the true model ranking, outperforming simple source‑accuracy baselines especially when source data are limited.
arXiv:2608. 16268v1 Announce Type: cross Abstract: Medical foundation models improve generalization when training AI models with limited labeled data, but remain confined to a single specialty, such as pathology or radiology, and to either sparse or dense outputs, such as classification or segmentation.