In biomedical vision-language modeling, datasets are typically mined from scientific literature, pairing compound figures with captions that are short, context-dependent, and oftern partially informative. Prior work on subfigure extraction has been limited in both dataset size and generalizability. In addition, no existing effort has incorporated rich medical context in image-text pairs. We revisit data curation as a foundational component of effective biomedical representation learning. Our data curation process integrates transformer-based subfigure detection, subcaption extraction, and contextual text enrichment derived from inline references. Our subfigure extraction model, trained on a corpus of 500,000 compound figures, achieves state-of-the-art performance on real and synthetic benchmarks. Using this process, we curate and release Open-PMC-18M, a large-scale high-fidelity biomedical dataset comprising 18 million image-text pairs, spanning radiology, microscopy, and visible light photography. We train vision-language models on our dataset and perform extensive evaluation on 6 retrieval and 19 zero-shot classification tasks across three major modalities. The models trained on our dataset set a new state-of-the-art results in medical representation learning. We release our dataset, models, and code to support reproducible benchmarks and further study into biomedical vision-language modeling and representation learning.
@article{arxiv.2506.02738,
title = {Open-PMC-18M: A High-Fidelity Large Scale Medical Dataset for Multimodal Representation Learning},
author = {Negin Baghbanzadeh and Mohammed Saidul Islam and Sajad Ashkezari and Elham Dolatabadi and Arash Afkanpour},
journal= {arXiv preprint arXiv:2506.02738},
year = {2025}
}