An Explainable Biomedical Foundation Model via Large-Scale Concept-Enhanced Vision-Language Pre-training

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Nie, Yuxiang, He, Sunan, Bie, Yequan, Wang, Yihui, Chen, Zhixuan, Yang, Shu, Cai, Zhiyuan, Wang, Hongmei, Wang, Xi, Luo, Luyang, Wu, Mingxiang, Wu, Xian, Chan, Ronald Cheong Kin, Lau, Yuk Ming, Zheng, Yefeng, Rajpurkar, Pranav, Chen, Hao
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912348593192960
author Nie, Yuxiang
He, Sunan
Bie, Yequan
Wang, Yihui
Chen, Zhixuan
Yang, Shu
Cai, Zhiyuan
Wang, Hongmei
Wang, Xi
Luo, Luyang
Wu, Mingxiang
Wu, Xian
Chan, Ronald Cheong Kin
Lau, Yuk Ming
Zheng, Yefeng
Rajpurkar, Pranav
Chen, Hao
author_facet Nie, Yuxiang
He, Sunan
Bie, Yequan
Wang, Yihui
Chen, Zhixuan
Yang, Shu
Cai, Zhiyuan
Wang, Hongmei
Wang, Xi
Luo, Luyang
Wu, Mingxiang
Wu, Xian
Chan, Ronald Cheong Kin
Lau, Yuk Ming
Zheng, Yefeng
Rajpurkar, Pranav
Chen, Hao
contents The clinical adoption of artificial intelligence (AI) in medical imaging requires models that are both diagnostically accurate and interpretable to clinicians. While current multimodal biomedical foundation models prioritize performance, their black-box nature hinders explaining the decision-making process in clinically meaningful concepts. Here, we present ConceptCLIP, the first explainable biomedical foundation model that achieves state-of-the-art diagnostic accuracy while delivering human-interpretable explanations across diverse imaging modalities. We curate MedConcept-23M, the largest pre-training dataset comprising 23 million image-text-concept triplets across diverse medical modalities, where clinical concepts are derived from the Unified Medical Language System. Leveraging this dataset, we develop ConceptCLIP through a novel dual-alignment approach that simultaneously learns global image-text representations and fine-grained region-concept associations for precise and interpretable medical image analysis. We curate the most extensive evaluation benchmark for multimodal biomedical foundation models, covering 52 clinical tasks spanning 10 imaging modalities. Extensive experiments demonstrate that ConceptCLIP outperforms existing state-of-the-art multimodal biomedical foundation models. Importantly, ConceptCLIP demonstrates superior diagnostic performance while providing human-understandable explanations validated by clinical experts. As the first precise and interpretable biomedical foundation model, ConceptCLIP represents a critical milestone toward the widespread clinical adoption of AI, thereby advancing trustworthy AI in medicine.
format Preprint
id arxiv_https___arxiv_org_abs_2501_15579
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle An Explainable Biomedical Foundation Model via Large-Scale Concept-Enhanced Vision-Language Pre-training
Nie, Yuxiang
He, Sunan
Bie, Yequan
Wang, Yihui
Chen, Zhixuan
Yang, Shu
Cai, Zhiyuan
Wang, Hongmei
Wang, Xi
Luo, Luyang
Wu, Mingxiang
Wu, Xian
Chan, Ronald Cheong Kin
Lau, Yuk Ming
Zheng, Yefeng
Rajpurkar, Pranav
Chen, Hao
Computer Vision and Pattern Recognition
Computation and Language
The clinical adoption of artificial intelligence (AI) in medical imaging requires models that are both diagnostically accurate and interpretable to clinicians. While current multimodal biomedical foundation models prioritize performance, their black-box nature hinders explaining the decision-making process in clinically meaningful concepts. Here, we present ConceptCLIP, the first explainable biomedical foundation model that achieves state-of-the-art diagnostic accuracy while delivering human-interpretable explanations across diverse imaging modalities. We curate MedConcept-23M, the largest pre-training dataset comprising 23 million image-text-concept triplets across diverse medical modalities, where clinical concepts are derived from the Unified Medical Language System. Leveraging this dataset, we develop ConceptCLIP through a novel dual-alignment approach that simultaneously learns global image-text representations and fine-grained region-concept associations for precise and interpretable medical image analysis. We curate the most extensive evaluation benchmark for multimodal biomedical foundation models, covering 52 clinical tasks spanning 10 imaging modalities. Extensive experiments demonstrate that ConceptCLIP outperforms existing state-of-the-art multimodal biomedical foundation models. Importantly, ConceptCLIP demonstrates superior diagnostic performance while providing human-understandable explanations validated by clinical experts. As the first precise and interpretable biomedical foundation model, ConceptCLIP represents a critical milestone toward the widespread clinical adoption of AI, thereby advancing trustworthy AI in medicine.
title An Explainable Biomedical Foundation Model via Large-Scale Concept-Enhanced Vision-Language Pre-training
topic Computer Vision and Pattern Recognition
Computation and Language
url https://arxiv.org/abs/2501.15579