ASTAR is an LLM-based framework that automatically generates standardized radiology reporting templates from large-scale clinical free-text corpora, eliminating the manual, expert-driven template construction process. In experiments on 4,215 fetal brain MRI reports from multiple centers, ASTAR‑induced templates outperformed two expert‑curated templates in template coverage, information fidelity, diagnostic fidelity, and expert‑rated usability. The approach reduces template development time from weeks of committee deliberation to hours of automated processing.
arXiv:2605.30984v2 Announce Type: replace-cross Abstract: Modern 3D medical vision-language models (VLMs) can generate fluent radiology-style text while exhibit critically low pathology detection and...
arXiv:2609.14226v1 Announce Type: new Abstract: Automated radiology report generation has advanced rapidly in diagnostic accuracy, yet generated reports frequently diverge from the stylistic conventi...
arXiv:2603.11938v2 Announce Type: replace-cross Abstract: Structured radiology reporting promises faster, more consistent communication than free text, but automation remains difficult as models must...
arXiv:2601.16753v2 Announce Type: replace-cross Abstract: Longitudinal information in radiology reports refers to the sequential tracking of findings across multiple examinations over time, which is...
arXiv:2411. 15122v2 Announce Type: replace-cross Abstract: AI-driven models have demonstrated significant potential in automating radiology report generation for chest X-rays.
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.
As vision-language models (VLMs) are increasingly applied to medical AI, existing benchmarks mainly focus on evaluating their diagnosis ability over given medical images and texts, implicitly assuming that standardized medical images, texts or question-answer pairs are already prepared. However, this assumption does not hold when we apply VLMs in real clinical practice, where medical data is often raw, heterogeneous, and fragmented across different sources.
arXiv:2608.22323v1 Announce Type: new Abstract: The application of Large Language Models (LLMs) to diagnostic decision-making has garnered growing interest. However, existing benchmarks largely focus...
arXiv:2607. 05880v1 Announce Type: cross Abstract: Imaging demand is growing faster than the radiology workforce can expand, and reporting backlogs cannot be resolved through training and recruitment alone.
arXiv:2607. 14116v1 Announce Type: cross Abstract: Free-form radiology reports contain rich clinical descriptions, yet converting them for reliable segmentation remains challenging due to the inherent variability of natural language.
The paper examines how Retrieval-Augmented Generation (RAG) and Named Entity Recognition (NER) affect the quality of lay summaries of radiology reports. Using a framework that extracts clinically relevant findings via NER and grounds them with RAG, the authors evaluate few‑shot and fine‑tuned versions of Qwen and BioBART. Results show that NER consistently improves readability and overall quality, RAG alone offers no benefit and can introduce hallucinations, and the best performance comes from fine‑tuned BioBART with NER.
The paper introduces the Medical Data Standardization Benchmark (MDS‑Bench), which evaluates vision‑language models (VLMs) on their ability to process raw, heterogeneous medical data. Models must identify source formats, convert raw images into VLM‑compatible inputs, extract relevant text, and organize the results into structured image‑text pairs. Experiments show that even the top VLM, Gemini 3 Flash, achieves only a 48.6% end‑to‑end success rate, underscoring the challenge of raw data standardization in clinical settings.