用流形先验蒸馏提升医学图像异常检测精度
PDD: Manifold-Prior Diverse Distillation for Medical Anomaly Detection
- 构建双教师流形先验，融合全局与局部特征
- 在多个数据集上实现最高11.8%的AUROC提升
- 适合医学影像分析、异常检测研究者参考
医学图像异常检测因病灶细微且结构复杂而面临挑战。通过系统性Grad-CAM分析发现，工业数据中表现良好的判别激活图在医学数据上失效，亟需流形级建模。本文提出PDD（Manifold-Prior Diverse Distillation），将两个冻结的教师模型——VMamba-Tiny（全局上下文）与wide-ResNet50（局部结构）——的特征统一到高维流形中。通过流形匹配与统一（MMU）模块和跨层特征适配（InA）模块增强表示能力。该统一流形分别蒸馏至两个学生模型：一个通过InA进行逐层蒸馏以保持局部一致性，另一个通过流形先验仿射（MPA）模块接收跳跃投影表示以捕捉跨层依赖。多样性损失防止表征坍缩，同时维持检测敏感性。在多个医学数据集上的实验表明，PDD显著优于现有方法，在HeadCT、BrainMRI和ZhangLab数据集上分别取得最高11.8%、5.1%、8.5%的AUROC提升，并在Uni-Medical数据集上实现3.4%的F1 max提升，建立新基准。代码将开源于https://github.com/OxygenLu/PDD。
原文摘要 · Abstract (English)
Medical image anomaly detection faces unique challenges due to subtle, heterogeneous anomalies embedded in complex anatomical structures. Through systematic Grad-CAM analysis, we reveal that discriminative activation maps fail on medical data, unlike their success on industrial datasets, motivating the need for manifold-level modeling. We propose PDD (Manifold-Prior Diverse Distillation), a framework that unifies dual-teacher priors into a shared high-dimensional manifold and distills this knowledge into dual students with complementary behaviors. Specifically, frozen VMamba-Tiny and wide-ResNet50 encoders provide global contextual and local structural priors, respectively. Their features are unified through a Manifold Matching and Unification (MMU) module, while an Inter-Level Feature Adaption (InA) module enriches intermediate representations. The unified manifold is distilled into two students: one performs layer-wise distillation via InA for local consistency, while the other receives skip-projected representations through a Manifold Prior Affine (MPA) module to capture cross-layer dependencies. A diversity loss prevents representation collapse while maintaining detection sensitivity. Extensive experiments on multiple medical datasets demonstrate that PDD significantly outperforms existing state-of-the-art methods, achieving improvements of up to 11.8%, 5.1%, and 8.5% in AUROC on HeadCT, BrainMRI, and ZhangLab datasets, respectively, and 3.4% in F1 max on the Uni-Medical dataset, establishing new state-of-the-art performance in medical image anomaly detection. The implementation will be released at https://github.com/OxygenLu/PDD
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。