文献类型：期刊文献

英文题名：Vision-Core Guided Contrastive Learning for Balanced Multi-modal Prognosis Prediction of Stroke

作者：Chen, Liren[1]; Sun, Lidong[1]; Huang, Mingyan[1]; Tang, Junzhe[1]; Zhu, Yinghui[1]; Wang, Guanjie[1]; Xia, Yiqing[1]; Xiao, Ting[1]

机构：[1] School of Information Science and Engineering, East China University of Science and Technology, Shanghai, 200237, China

年份：2026

外文期刊名：arXiv

收录：EI(收录号：20260270013)

语种：英文

外文关键词：Alignment - Brain - Computer vision - Deep learning - Diagnosis - Information fusion - Learning systems - Medical image processing - Modal analysis - Visual languages

摘要：Deep learning and multi-modal fusion have demonstrated transformative potential in medical diagnosis by integrating diverse data sources. However, accurate prognosis for ischemic stroke remains challenging due to limitations in existing multi-modal approaches. First, current methods are predominantly confined to dual-modal fusion, lacking a framework that effectively integrates the trifecta of medical images, structured clinical data, and unstructured text. Second, they often fail to establish deep bidirectional interactions between modalities; To address these critical gaps, this paper proposes a novel tri-modal fusion model for ischemic stroke prognosis. Our approach first enriches the data representation by employing a Large Language Model (LLM) to automatically generate semi-structured diagnostic text from brain MRIs. This process not only addresses the scarcity of expert annotations but also serves as a regularized semantic enhancement, improving multimodal fusion robustness. Furthermore, we design a core component termed the Vision-Conditioned Dual Alignment Fusion Module (VDAFM), which strategically uses visual features as a conditional prior to guide fine-grained interaction with the generated text. This module achieves a dynamic and profound fusion through a dual semantic alignment loss, effectively mitigating modal heterogeneity. Extensive experiments on a real-world clinical dataset demonstrate that our model achieves state-of-the-art performance. Copyright ? 2026, The Authors. All rights reserved.