发表机构
Ewha Womans University; Ewha Medical Artificial Intelligence Research Institute; REMEDI Inc.; Ewha Womans University Seoul Hospital（梨花女子大学; 梨花女子大学医学人工智能研究所; 瑞美迪公司; 梨花女子大学首尔医院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出ASH-MIL框架，通过解剖结构分支和分层多实例学习，在无边界框监督下改进胸部X光片弱监督疾病检测的定位精度，实验验证优于现有方法。
AI 中文摘要
胸部X光片（CXR）中的弱监督胸科疾病检测因病灶外观细微和复杂的解剖结构重叠而具有挑战性，这促使了面向解剖结构感知的建模以改进定位。然而，先前的解剖结构感知方法通常依赖于粗略的区域代理或静态空间先验，这可能限制动态实例发现并限制对小异常的精确定位。我们提出解剖结构分层多实例学习（ASH-MIL），该框架引入平行的解剖结构观测分支（心脏、肺部和不可知）并结合分层多实例学习聚合。解剖先验作为软空间偏置注入解码器交叉注意力中，使得在无疾病边界框监督的情况下生成基于解剖结构的证据图。实例定位直接由多实例学习加权的交叉注意力图导出，无需边界框监督。在CXR8和跨域MIMIC-CXR留出集上的实验表明，该方法在更严格的定位标准下，相较于先前的弱监督和解剖结构感知方法取得了一致的改进。我们的代码可在该https URL获取。
英文摘要
Weakly-supervised thoracic disease detection in chest X-rays (CXR) is challenging due to subtle appearances and complex anatomical overlap, motivating anatomy-aware modeling for improved localization. However, prior anatomy-aware methods typically rely on coarse region proxies or static spatial priors, which may restrict dynamic instance discovery and limit precise localization of small abnormalities. We propose Anatomy-Structured Hierarchical Multiple Instance Learning (ASH-MIL), a framework that introduces parallel anatomy-structured observation branches (cardiac, pulmonary, and agnostic) combined with hierarchical MIL aggregation. Anatomical priors are injected as soft spatial biases into decoder cross-attention, enabling anatomically grounded evidence maps without disease bounding-box supervision. Instance localization is derived directly from MIL-weighted cross-attention maps without bounding box supervision. Experiments on CXR8 and cross-domain MIMIC-CXR held-out sets demonstrate consistent improvements over prior weakly-supervised and anatomy-aware approaches, particularly under stricter localization criteria. Our code is available at https://github.com/jn-kim/ash-mil.
CommentsAccepted at MICCAI 2026
