发表机构
Monash University; Airdoc-Monash Research, Monash University（莫纳什大学; 艾医智-莫纳什研究中心（莫纳什大学））
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对医学图像异常检测难题，提出CFR-Net，结合解码前后的特征细化与跨空间一致性，利用多路径特征细化模块及相关策略减轻域差异并建模多特征，实验显示该网络在正常数据训练下有良好的异常分类和定位性能。
AI 中文摘要
医学图像异常检测具有挑战性，因为在自然图像上预训练的网络对医学图像适应性有限。异常模式表现为细粒度局部偏移、多尺度上下文不匹配和方向敏感结构偏差。为此，我们提出协作特征细化网络（CFR-Net），它在解码前结合共享师生特征细化，解码后结合跨空间一致性。通过多路径特征细化模块（MPFRM）细化冻结教师特征和可训练学生特征，施加通用多路径细化规则，减轻域差异，同时建模局部、多尺度和方向敏感特征。方差敏感目标和动态“作业集”重组支持层自适应一致性学习。医学基准实验表明，CFR-Net在正常数据上训练时，实现了有竞争力的异常分类和强大的异常定位性能。
英文摘要
Medical image anomaly detection is central to timely diagnosis and clinical decision support, yet abnormal samples are costly to collect because of disease rarity, privacy concerns, and expert workload. This motivates unsupervised learning from normal images, where abnormalities are detected as deviations from learned normal patterns. However, medical anomalies are often subtle, local, and intertwined with normal anatomical variations, which complicates reliable normality modeling. Distillation-based methods support normality modeling by using frozen pretrained teachers as stable feature references, yet mismatches between generic teacher priors and student representations adapted to medical images can produce residuals unrelated to abnormalities in conventional distillation pipelines. To address this limitation, we propose the Collaborative Feature Refinement Network, which learns normality through a coupled process of shared feature conditioning before decoding and cross-space consistency after decoding. Shared feature conditioning performs medical-aware conditioning on teacher and student features under common rules, while cross-space consistency constrains each decoded stream with the complementary encoder representation for reciprocal normal reconstruction. The coupled process is further stabilized by the homework set reorganization strategy, which periodically refreshes normal training subsets. Experiments on six medical image benchmarks show competitive anomaly classification and strong anomaly localization performance.
