Seeing Like Radiologists: Context- and Gaze-Guided Vision-Language Pretraining for Chest X-rays

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liu, Kang, Ma, Zhuoqi, Liang, Siyu, Li, Yunan, Gao, Xiyue, Liang, Chao, Xie, Kun, Miao, Qiguang
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912984891129856
author Liu, Kang
Ma, Zhuoqi
Liang, Siyu
Li, Yunan
Gao, Xiyue
Liang, Chao
Xie, Kun
Miao, Qiguang
author_facet Liu, Kang
Ma, Zhuoqi
Liang, Siyu
Li, Yunan
Gao, Xiyue
Liang, Chao
Xie, Kun
Miao, Qiguang
contents Despite recent advances in medical vision-language pretraining, existing models still struggle to capture the diagnostic workflow: radiographs are typically treated as context-agnostic images, while radiologists' gaze -- a crucial cue for visual reasoning -- remains largely underexplored by existing methods. These limitations hinder the modeling of disease-specific patterns and weaken cross-modal alignment. To bridge this gap, we introduce CoGaze, a Context- and Gaze-guided vision-language pretraining framework for chest X-rays. We first propose a context-infused vision encoder that models how radiologists integrate clinical context -- including patient history, symptoms, and diagnostic intent -- to guide diagnostic reasoning. We then present a multi-level supervision paradigm that (1) enforces intra- and inter-modal semantic alignment through hybrid-positive contrastive learning, (2) injects diagnostic priors via disease-aware cross-modal representation learning, and (3) leverages radiologists' gaze as probabilistic priors to guide attention toward diagnostically salient regions. Extensive experiments demonstrate that CoGaze consistently outperforms state-of-the-art methods across diverse tasks, achieving up to +2.0% CheXbertF1 and +1.2% BLEU2 for free-text and structured report generation, +23.2% AUROC for zero-shot classification, and +12.2% Precision@1 for image-text retrieval. Code is available at https://github.com/mk-runner/CoGaze.
format Preprint
id arxiv_https___arxiv_org_abs_2603_26049
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Seeing Like Radiologists: Context- and Gaze-Guided Vision-Language Pretraining for Chest X-rays
Liu, Kang
Ma, Zhuoqi
Liang, Siyu
Li, Yunan
Gao, Xiyue
Liang, Chao
Xie, Kun
Miao, Qiguang
Computer Vision and Pattern Recognition
Artificial Intelligence
Despite recent advances in medical vision-language pretraining, existing models still struggle to capture the diagnostic workflow: radiographs are typically treated as context-agnostic images, while radiologists' gaze -- a crucial cue for visual reasoning -- remains largely underexplored by existing methods. These limitations hinder the modeling of disease-specific patterns and weaken cross-modal alignment. To bridge this gap, we introduce CoGaze, a Context- and Gaze-guided vision-language pretraining framework for chest X-rays. We first propose a context-infused vision encoder that models how radiologists integrate clinical context -- including patient history, symptoms, and diagnostic intent -- to guide diagnostic reasoning. We then present a multi-level supervision paradigm that (1) enforces intra- and inter-modal semantic alignment through hybrid-positive contrastive learning, (2) injects diagnostic priors via disease-aware cross-modal representation learning, and (3) leverages radiologists' gaze as probabilistic priors to guide attention toward diagnostically salient regions. Extensive experiments demonstrate that CoGaze consistently outperforms state-of-the-art methods across diverse tasks, achieving up to +2.0% CheXbertF1 and +1.2% BLEU2 for free-text and structured report generation, +23.2% AUROC for zero-shot classification, and +12.2% Precision@1 for image-text retrieval. Code is available at https://github.com/mk-runner/CoGaze.
title Seeing Like Radiologists: Context- and Gaze-Guided Vision-Language Pretraining for Chest X-rays
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2603.26049