发表机构
Center for Computational & Data Sciences, Independent University, Bangladesh; Department of Computer Science and Engineering, Independent University, Bangladesh; Graduate School of Engineering, University of Hyogo（孟加拉国独立大学计算与数据科学中心; 孟加拉国独立大学计算机科学与工程系; 兵库大学工程研究生院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
SecondOpinion是一种医学图像分析框架，通过训练为二元正确性分类器的门控机制按需调用解剖引导流，在保持性能的同时降低计算量，激活率与任务难度直接相关。
AI 中文摘要
用于医学图像分析的深度学习模型通常会对每个输入应用固定的计算量，而不考虑病例的难度。解剖引导的双流架构已被证明可提升诊断性能，但它们会无条件评估两个流，即使是单一流已能自信解决的病例也是如此。我们提出SecondOpinion框架，其中快速主处理流对每个病例进行处理，而仅当GateKeeper（一种专门训练为二元正确性分类器的门控机制）判定主流的预测需要额外审查时，才会调用第二个解剖引导流，这类似临床医生对疑难病例寻求第二意见的做法。当被激活时，两个流通过轻量交叉注意力融合模块进行组合。我们在统一的五类胸部X光数据集和骨盆骨折数据集上评估SecondOpinion，后者包含一个保留的、难度更高的骨折子集，这些骨折在X光上不可见但经CT确认。SecondOpinion在两个任务上的性能与现有最先进方法相当或更优，同时其解剖引导流仅在9.23%的胸部X光病例上激活，在可见骨折病例上的激活率升至24.12%，在不可见骨折病例上的激活率达45.71%，该激活率直接与任务难度相关。这些结果表明，监督门控信号朝向正确性（而非依赖无监督置信度），可让模型将解剖推理分配到真正需要的地方。
英文摘要
Deep learning models for medical image analysis typically apply a fixed amount of computation to every input, regardless of case difficulty. Anatomy-guided dual-stream architectures have been shown to improve diagnostic performance, but they evaluate both streams unconditionally, even on cases a single stream could already resolve confidently. We propose SecondOpinion, a framework in which a fast primary stream processes every case, while a second, anatomy-guided stream is invoked only when GateKeeper, a gating mechanism trained explicitly as a binary correctness classifier, judges that the primary stream's prediction needs additional scrutiny, much as a clinician might seek a second opinion on a difficult case. When activated, the two streams are combined through a lightweight cross-attention fusion module. We evaluate SecondOpinion on a unified five-class chest X-ray dataset and a pelvic fracture dataset, the latter including a held-out, harder subset of fractures that are invisible on X-ray but confirmed via CT. SecondOpinion matches or exceeds prior state-of-the-art performance on both tasks, while activating its anatomy-guided stream on only 9.23% of chest X-ray cases, rising to 24.12% on visible fractures and 45.71% on invisible fractures, an activation rate that tracks task difficulty directly. These results suggest that supervising a gating signal toward correctness, rather than relying on unsupervised confidence, allows a model to allocate anatomical reasoning where it is actually needed.
CommentsAccepted at EMA4MICCAI 2026 (MICCAI Workshop)
