Resources


Database Credentialed Access

CXReasonBench: A Benchmark for Evaluating Structured Diagnostic Reasoning in Chest X-rays

Hyungyung Lee, Geon Choi, Jung Oh Lee, et al.

CheXStruct is an automated pipeline that derives structured diagnostic reasoning steps from chest X-rays. CXReasonBench builds on this to evaluate whether models perform clinically grounded, multi-step reasoning beyond final diagnoses.

evaluation chest x-ray benchmark structured chest x-ray qa intermediate reasoning steps structured reasoning grounded reasoning diagnostic reasoning structured diagnostic pipeline

Published: Oct. 23, 2025. Version: 1.0.1

Database Credentialed Access

EHRXQA: A Multi-Modal Question Answering Dataset for Electronic Health Records with Chest X-ray Images

Seongsu Bae, Daeun Kyung, Jaehee Ryu, et al.

We present EHRXQA, the first multi-modal EHR QA dataset combining structured patient records with aligned chest X-ray images. EHRXQA contains a comprehensive set of QA pairs covering image-related, table-related, and image+table-related questions.

question answering machine learning electronic health records evaluation chest x-ray multi-modal question answering ehr question answering semantic parsing benchmark deep learning visual question answering

Published: July 23, 2024. Version: 1.0.0

Database Credentialed Access

EHRXQA: A Multi-Modal Question Answering Dataset for Electronic Health Records with Chest X-ray Images

Seongsu Bae, Daeun Kyung, Jaehee Ryu, et al.

We present EHRXQA, the first multi-modal EHR QA dataset combining structured patient records with aligned chest X-ray images. EHRXQA contains a comprehensive set of QA pairs covering image-related, table-related, and image+table-related questions.

question answering machine learning electronic health records evaluation chest x-ray multi-modal question answering ehr question answering semantic parsing benchmark deep learning visual question answering

Published: July 23, 2024. Version: 1.0.0

Database Credentialed Access

MIMIC-Ext-CXR-QBA: A Structured, Tagged, and Localized Visual Question Answering Dataset with Question-Box-Answer Triplets and Scene Graphs for Chest X-ray Images

Philip Müller, Friederike Jungmann, Georgios Kaissis, et al.

We present a large-scale CXR VQA dataset derived from MIMIC-CXR with 42M QA pairs, featuring hierarchical answers, bounding boxes, and structured tags. We generated QA-pairs using LLM-based extraction from radiology reports and localization models.

chest x-rays vqa localization scene graphs

Published: July 22, 2025. Version: 1.0.0

Database Credentialed Access

MIMIC-Ext-CXR-QBA: A Structured, Tagged, and Localized Visual Question Answering Dataset with Question-Box-Answer Triplets and Scene Graphs for Chest X-ray Images

Philip Müller, Friederike Jungmann, Georgios Kaissis, et al.

We present a large-scale CXR VQA dataset derived from MIMIC-CXR with 42M QA pairs, featuring hierarchical answers, bounding boxes, and structured tags. We generated QA-pairs using LLM-based extraction from radiology reports and localization models.

chest x-rays vqa localization scene graphs

Published: July 22, 2025. Version: 1.0.0