Resources

The Radiology Report Expert Evaluation (ReXVal) Dataset is a publicly available dataset of radiologist evaluations of errors in automatically generated radiology reports. The dataset contains annotations from 6 board certified radiologists on clinic…

CXR-PRO is an adaptation of the MIMIC-CXR dataset that omits references to prior radiology reports. Consisting of 374,139 free-text radiology reports and associated chest radiographs, CXR-PRO addresses the issue of hallucinated references to priors …

Automatically generated radiology reports often receive high scores from existing evaluation metrics but fail to earn clinicians' trust. This gap reveals fundamental flaws in how current metrics assess the quality of generated reports. We rethink th…

Patient’s unique information needs about their hospitalization can be addressed using clinical evidence from electronic health records (EHRs) and artificial intelligence (AI). However, robust datasets to assess the factuality and relevance of AI-gen…

MIMIC-III and MIMIC-IV are foundational resources for clinical NLP, but their scale is modest relative to the data volumes needed to train language models. Building on recent advances in synthetic data generation through LLM-based rephrasing, we con…

Metabolic dysfunction-associated steatotic liver disease (MASLD), including its progressive form metabolic dysfunction-associated steatohepatitis (MASH), is the leading cause of chronic liver disease. Accurate delineation of the metabolites and sign…

We present RadVLM, a compact (7B) multitask conversational foundation model designed for CXR interpretation. Its development relies on the curation of a large-scale instruction dataset comprising over 1 million image-instruction pairs containing bot…

We present MIMICEchoQA, a benchmark dataset for echocardiogram-based question answering, built from the publicly available MIMIC-IV-ECHO database. Each echocardiographic study was paired with the closest discharge summary within a 7-day window, and …

We release the RadVLM instruction dataset, a large-scale resource used to train the RadVLM model on diverse radiology tasks. The dataset contains 1,115,021 image–instruction pairs spanning five task families: (i) report generation from frontal CXRs …

Large-language models (LLMs) show promise for extracting information from clinical notes. Deploying these models at scale can be challenging due to high computational costs, regulatory constraints, and privacy concerns. To address these challenges, …