3D Modality-Aware Pre-training for Vision-Language Model in MRI Multi-organ Abnormality Detection

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhu, Haowen, Yin, Ning, Zhou, Xiaogen
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917307964456960
author Zhu, Haowen
Yin, Ning
Zhou, Xiaogen
author_facet Zhu, Haowen
Yin, Ning
Zhou, Xiaogen
contents Vision-language models (VLMs) show strong potential for complex diagnostic tasks in medical imaging. However, applying VLMs to multi-organ medical imaging introduces two principal challenges: (1) modality-specific vision-language alignment and (2) cross-modal feature fusion. In this work, we propose MedMAP, a Medical Modality-Aware Pretraining framework that enhances vision-language representation learning in 3D MRI. MedMAP comprises a modality-aware vision-language alignment stage and a fine-tuning stage for multi-organ abnormality detection. During the pre-training stage, the modality-aware encoders implicitly capture the joint modality distribution and improve alignment between visual and textual representations. We then fine-tune the pre-trained vision encoders (while keeping the text encoder frozen) for downstream tasks. To this end, we curated MedMoM-MRI3D, comprising 7,392 3D MRI volume-report pairs spanning twelve MRI modalities and nine abnormalities tailored for various 3D medical analysis tasks. Extensive experiments on MedMoM-MRI3D demonstrate that MedMAP significantly outperforms existing VLMs in 3D MRI-based multi-organ abnormality detection. Our code is available at https://github.com/RomantiDr/MedMAP.
format Preprint
id arxiv_https___arxiv_org_abs_2602_23652
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle 3D Modality-Aware Pre-training for Vision-Language Model in MRI Multi-organ Abnormality Detection
Zhu, Haowen
Yin, Ning
Zhou, Xiaogen
Computer Vision and Pattern Recognition
Artificial Intelligence
Vision-language models (VLMs) show strong potential for complex diagnostic tasks in medical imaging. However, applying VLMs to multi-organ medical imaging introduces two principal challenges: (1) modality-specific vision-language alignment and (2) cross-modal feature fusion. In this work, we propose MedMAP, a Medical Modality-Aware Pretraining framework that enhances vision-language representation learning in 3D MRI. MedMAP comprises a modality-aware vision-language alignment stage and a fine-tuning stage for multi-organ abnormality detection. During the pre-training stage, the modality-aware encoders implicitly capture the joint modality distribution and improve alignment between visual and textual representations. We then fine-tune the pre-trained vision encoders (while keeping the text encoder frozen) for downstream tasks. To this end, we curated MedMoM-MRI3D, comprising 7,392 3D MRI volume-report pairs spanning twelve MRI modalities and nine abnormalities tailored for various 3D medical analysis tasks. Extensive experiments on MedMoM-MRI3D demonstrate that MedMAP significantly outperforms existing VLMs in 3D MRI-based multi-organ abnormality detection. Our code is available at https://github.com/RomantiDr/MedMAP.
title 3D Modality-Aware Pre-training for Vision-Language Model in MRI Multi-organ Abnormality Detection
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2602.23652