UniBiomed: A Universal Foundation Model for Grounded Biomedical Image Interpretation

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Wu, Linshan, Nie, Yuxiang, He, Sunan, Zhuang, Jiaxin, Luo, Luyang, Li, Tao, Xie, Zhuoyao, Chen, Dexuan, Zhao, Yinghua, Mahboobani, Neeraj, Vardhanabhuti, Varut, Chan, Ronald Cheong Kin, Peng, Yifan, Rajpurkar, Pranav, Chen, Hao
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908704607043584
author Wu, Linshan
Nie, Yuxiang
He, Sunan
Zhuang, Jiaxin
Luo, Luyang
Li, Tao
Xie, Zhuoyao
Chen, Dexuan
Zhao, Yinghua
Mahboobani, Neeraj
Vardhanabhuti, Varut
Chan, Ronald Cheong Kin
Peng, Yifan
Rajpurkar, Pranav
Chen, Hao
author_facet Wu, Linshan
Nie, Yuxiang
He, Sunan
Zhuang, Jiaxin
Luo, Luyang
Li, Tao
Xie, Zhuoyao
Chen, Dexuan
Zhao, Yinghua
Mahboobani, Neeraj
Vardhanabhuti, Varut
Chan, Ronald Cheong Kin
Peng, Yifan
Rajpurkar, Pranav
Chen, Hao
contents The integration of AI-assisted biomedical image analysis into clinical practice demands AI-generated findings that are not only accurate but also interpretable to clinicians. However, existing biomedical AI models generally lack the ability to simultaneously generate diagnostic findings and localize corresponding biomedical objects. This limitation makes it challenging for clinicians to correlate AI-generated findings with visual evidence (e.g., tiny lesions) in images and interpret the results of AI models. To address this challenge, we introduce UniBiomed, the first universal foundation model for grounded biomedical image interpretation, which is capable of generating accurate diagnostic findings and simultaneously segmenting the corresponding biomedical targets. UniBiomed is based on a novel integration of Multi-modal Large Language Model and Segment Anything Model, which can effectively unify diverse biomedical tasks in universal training for advancing grounded interpretation. To develop UniBiomed, we curate a large-scale dataset comprising over 27 million triplets of images, region annotations, and text descriptions across ten biomedical imaging modalities. Extensive validation on 70 internal and 14 external datasets demonstrated the state-of-the-art performance of UniBiomed in diverse biomedical tasks, including image segmentation, disease recognition, region-aware diagnosis, vision question answering, and report generation. In summary, UniBiomed is a powerful and versatile biomedical foundation model, unlocking the untapped grounded interpretation capability for optimizing AI-assisted biomedical image analysis.
format Preprint
id arxiv_https___arxiv_org_abs_2504_21336
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle UniBiomed: A Universal Foundation Model for Grounded Biomedical Image Interpretation
Wu, Linshan
Nie, Yuxiang
He, Sunan
Zhuang, Jiaxin
Luo, Luyang
Li, Tao
Xie, Zhuoyao
Chen, Dexuan
Zhao, Yinghua
Mahboobani, Neeraj
Vardhanabhuti, Varut
Chan, Ronald Cheong Kin
Peng, Yifan
Rajpurkar, Pranav
Chen, Hao
Computer Vision and Pattern Recognition
The integration of AI-assisted biomedical image analysis into clinical practice demands AI-generated findings that are not only accurate but also interpretable to clinicians. However, existing biomedical AI models generally lack the ability to simultaneously generate diagnostic findings and localize corresponding biomedical objects. This limitation makes it challenging for clinicians to correlate AI-generated findings with visual evidence (e.g., tiny lesions) in images and interpret the results of AI models. To address this challenge, we introduce UniBiomed, the first universal foundation model for grounded biomedical image interpretation, which is capable of generating accurate diagnostic findings and simultaneously segmenting the corresponding biomedical targets. UniBiomed is based on a novel integration of Multi-modal Large Language Model and Segment Anything Model, which can effectively unify diverse biomedical tasks in universal training for advancing grounded interpretation. To develop UniBiomed, we curate a large-scale dataset comprising over 27 million triplets of images, region annotations, and text descriptions across ten biomedical imaging modalities. Extensive validation on 70 internal and 14 external datasets demonstrated the state-of-the-art performance of UniBiomed in diverse biomedical tasks, including image segmentation, disease recognition, region-aware diagnosis, vision question answering, and report generation. In summary, UniBiomed is a powerful and versatile biomedical foundation model, unlocking the untapped grounded interpretation capability for optimizing AI-assisted biomedical image analysis.
title UniBiomed: A Universal Foundation Model for Grounded Biomedical Image Interpretation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2504.21336