Resources

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.

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.

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.

A radiologist-annotated benchmark of structured chest X-ray reports at single and sequential levels, comprising 1,473 reports across 18 relation types and 80 longitudinal cases.

A radiologist-annotated benchmark of structured chest X-ray reports at single and sequential levels, comprising 1,473 reports across 18 relation types and 80 longitudinal cases.

A radiologist-annotated benchmark of structured chest X-ray reports at single and sequential levels, comprising 1,473 reports across 18 relation types and 80 longitudinal cases.

MS-CXR is a new dataset containing 1162 chest X-ray bounding box labels paired with radiology text descriptions, annotated and verified by two board-certified radiologists.

MS-CXR is a new dataset containing 1162 chest X-ray bounding box labels paired with radiology text descriptions, annotated and verified by two board-certified radiologists.