Resources


Software Credentialed Access

Code for generating the HAIM multimodal dataset of MIMIC-IV clinical data and x-rays

Luis R Soenksen, Yu Ma, Cynthia Zeng, Leonard David Jean Boussioux, Kimberly Villalobos Carballo, Liangyuan Na, Holly Wiberg, Michael Li, Ignacio Fuentes, Dimitris Bertsimas

Code for generating the HAIM multimodal dataset of MIMIC-IV clinical data and x-rays

database code multimodality

Published: Aug. 23, 2022. Version: 1.0.1

Database Credentialed Access

MS-CXR: Making the Most of Text Semantics to Improve Biomedical Vision-Language Processing

Benedikt Boecking, Naoto Usuyama, Shruthi Bannur, Daniel Coelho de Castro, Anton Schwaighofer, Stephanie Hyland, Harshita Sharma, Maria Teodora Wetscherek, Tristan Naumann, Aditya Nori, Javier Alvarez Valle, Hoifung Poon, Ozan Oktay

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.

vision-language processing chest x-ray localization phrase grounding

Published: Nov. 15, 2024. Version: 1.1.0

Database Credentialed Access

ReXPref-Prior: A MIMIC-CXR Preference Dataset for Reducing Hallucinated Prior Exams in Radiology Report Generation

Oishi Banerjee, Hong-Yu Zhou, Subathra Adithan, Stephen Kwak, Kay Wu, Pranav Rajpurkar

We propose ReXPref-Prior, an adapted version of MIMIC-CXR where GPT-4 has removed references to prior exams from both findings and impression sections of chest X-ray reports.

chest x-rays reinforcement learning hallucination

Published: Aug. 14, 2024. Version: 1.0.0

Database Credentialed Access

RadGraph2: Tracking Findings Over Time in Radiology Reports

Adam Dejl, Sameer Khanna, Patricia Therese Pile, Kibo Yoon, Steven QH Truong, Hanh Duong, Agustina Saenz, Pranav Rajpurkar

RadGraph2 is a dataset of 800 chest radiology reports annotated using a fine-grained entity-relationship schema, which captures key findings as well as mentions of changes that occurred in comparison with the previous radiology studies.

chest x-rays relation extraction disease progression information extraction radiology reports named entity recognition

Published: Aug. 8, 2024. Version: 1.0.0

Database Restricted Access

Application of Med-PaLM 2 in the refinement of MIMIC-CXR labels

Kendall Park, Rory Sayres, Andrew Sellergren, Tom Pollard, Fayaz Jamil, Timo Kohlberger, Charles Lau, Atilla Kiraly

This work further refines the labels associated with CheXpert in MIMIC-CXR-JPG 2.0.0 by filtering with Med-PaLM 2 followed by verification by manual review by three US board-certified radiologists.

mimic-cxr labels

Published: Feb. 4, 2025. Version: 1.0.0

Database Open Access

MUSIC (Sudden Cardiac Death in Chronic Heart Failure)

Alba Martin-Yebra, Juan Pablo Martínez, Pablo Laguna

The MUSIC study is a prospective, multicentre, longitudinal study designed to assess risk predictors of cardiac mortality and sudden cardiac death in ambulatory patients with chronic heart failure.

Published: Jan. 24, 2025. Version: 1.0.1

Visualize waveforms

Database Credentialed Access

FFA-IR: Towards an Explainable and Reliable Medical Report Generation Benchmark

Mingjie Li, Wenjia Cai, Rui Liu, Yuetian Weng, Tengfei Liu, Cong Wang, xin chen, zhong liu, Caineng Pan, Mengke Li, yingfeng zheng, Yizhi Liu, Flora Salim, Karin Verspoor, Xiaodan Liang, Xiaojun Chang

Benchmark dataset for report generation based on fundus fluorescein angiography images and reports.

fundus fluorescein angiography medical report generation vision and language explainable and reliable evaluation

Published: Jan. 21, 2025. Version: 1.1.0

Database Credentialed Access

MS-CXR: Making the Most of Text Semantics to Improve Biomedical Vision-Language Processing

Benedikt Boecking, Naoto Usuyama, Shruthi Bannur, Daniel Coelho de Castro, Anton Schwaighofer, Stephanie Hyland, Harshita Sharma, Maria Teodora Wetscherek, Tristan Naumann, Aditya Nori, Javier Alvarez Valle, Hoifung Poon, Ozan Oktay

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.

vision-language processing chest x-ray localization phrase grounding

Published: Nov. 15, 2024. Version: 1.1.0

Database Contributor Review

COVID Data for Shared Learning (CDSL): A comprehensive, multimodal COVID-19 dataset from HM Hospitales

Álvaro Ritoré, Andreea M Oprescu, Alberto Estirado Bronchalo, Miguel Ángel Armengol de la Hoz

COVID Data for Shared Learning (CDSL) is a multimodal database comprising de-identified structured health data and radiological images from 4,479 patients with COVID-19, as a comprehensive toolkit for developing predictive models.

covid-19 multimodal database radiological images open data healthcare data machine learning and ai

Published: Oct. 25, 2024. Version: 1.0.0

Database Credentialed Access

ReXPref-Prior: A MIMIC-CXR Preference Dataset for Reducing Hallucinated Prior Exams in Radiology Report Generation

Oishi Banerjee, Hong-Yu Zhou, Subathra Adithan, Stephen Kwak, Kay Wu, Pranav Rajpurkar

We propose ReXPref-Prior, an adapted version of MIMIC-CXR where GPT-4 has removed references to prior exams from both findings and impression sections of chest X-ray reports.

chest x-rays reinforcement learning hallucination

Published: Aug. 14, 2024. Version: 1.0.0