English

Distribution-Based Masked Medical Vision-Language Model Using Structured Reports

Computer Vision and Pattern Recognition 2025-07-30 v1

Abstract

Medical image-language pre-training aims to align medical images with clinically relevant text to improve model performance on various downstream tasks. However, existing models often struggle with the variability and ambiguity inherent in medical data, limiting their ability to capture nuanced clinical information and uncertainty. This work introduces an uncertainty-aware medical image-text pre-training model that enhances generalization capabilities in medical image analysis. Building on previous methods and focusing on Chest X-Rays, our approach utilizes structured text reports generated by a large language model (LLM) to augment image data with clinically relevant context. These reports begin with a definition of the disease, followed by the `appearance' section to highlight critical regions of interest, and finally `observations' and `verdicts' that ground model predictions in clinical semantics. By modeling both inter- and intra-modal uncertainty, our framework captures the inherent ambiguity in medical images and text, yielding improved representations and performance on downstream tasks. Our model demonstrates significant advances in medical image-text pre-training, obtaining state-of-the-art performance on multiple downstream tasks.

Keywords

Cite

@article{arxiv.2507.21794,
  title  = {Distribution-Based Masked Medical Vision-Language Model Using Structured Reports},
  author = {Shreyank N Gowda and Ruichi Zhang and Xiao Gu and Ying Weng and Lu Yang},
  journal= {arXiv preprint arXiv:2507.21794},
  year   = {2025}
}

Comments

Accepted in MICCAI-W 2025

R2 v1 2026-07-01T04:24:00.373Z