MATEX: 医疗视觉-语言模型的多尺度注意力与文本引导可解释性
MATEX: Multi-scale Attention and Text-guided Explainability of Medical Vision-Language Models
AI总结：
MATEX通过多尺度注意力与文本引导方法提升医疗视觉-语言模型的可解释性，实现更精确和临床相关的梯度归因图。
摘要：
我们介绍了MATEX（多尺度注意力与文本引导可解释性），一种新的框架，通过结合解剖学指导的空间推理，推动医疗视觉-语言模型的可解释性。MATEX协同结合多层注意力展开、文本引导的空间先验和层一致性分析，产生精确、稳定且具有临床意义的梯度归因图。通过解决先前方法的关键限制，如空间不精确、缺乏解剖学基础和注意力粒度有限，MATEX实现了更忠实和可解释的模型解释。在MS-CXR数据集上评估，MATEX在空间精度和与专家注释发现的一致性上均优于最先进的M2IB方法。这些结果突显了MATEX在增强放射学AI应用信任和透明度方面的潜力。
英文摘要：
We introduce MATEX (Multi-scale Attention and Text-guided Explainability), a novel framework that advances interpretability in medical vision-language models by incorporating anatomically informed spatial reasoning. MATEX synergistically combines multi-layer attention rollout, text-guided spatial priors, and layer consistency analysis to produce precise, stable, and clinically meaningful gradient attribution maps. By addressing key limitations of prior methods, such as spatial imprecision, lack of anatomical grounding, and limited attention granularity, MATEX enables more faithful and interpretable model explanations. Evaluated on the MS-CXR dataset, MATEX outperforms the state-of-the-art M2IB approach in both spatial precision and alignment with expert-annotated findings. These results highlight MATEX's potential to enhance trust and transparency in radiological AI applications.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
