文献类型：期刊文献

英文题名：Unsupervised Brain Anomaly Detection Using Structure-Preserving Noise Generation and Multi-Scale Dual-Expert Ensembles

作者：Yang, Qianyi[1,2]; Huang, Bingcang[3]; Zhou, Qin[4]; Wang, Zhe[4]; Chen, Kai[3]; Tang, Xiu[2,5]; Yao, Chang[2,5]; Wu, Sai[2,5]

机构：[1] Zhejiang University, Hangzhou, 310058, China; [2] Zhejiang University, Hangzhou High-Tech Zone [Binjiang] Institute of Blockchain and Data Security, Hangzhou, 310058, China; [3] Gongli Hospital of Shanghai Pudong New Area, Department of Radiology, Shanghai, 200135, China; [4] East China University of Science and Technology, Department of Computer Science and Engineering, Shanghai, 200237, China; [5] Zhejiang University, State Key Laboratory of Blockchain and Data Security, Hangzhou, 310058, China

年份：2025

外文期刊名：IEEE Journal of Biomedical and Health Informatics

收录：EI(收录号：20254819595891)

语种：英文

外文关键词：Anomaly detection - Brain - Diagnosis - Errors - Knowledge transfer - Learning systems - Pattern recognition

摘要：Detecting early brain anomalies is crucial for patient prognosis and recovery, but obtaining expert-annotated data is challenging, especially for clinically silent early brain anomalies. Unsupervised brain anomaly detection, which identifies anomalous regions by modeling normal brain patterns, has gained interest for its label efficiency. However, the inherent variability in normal brains and subtle anomalies that closely resemble normal tissue pose challenges for traditional autoencoders in distinguishing anomalies. Denoising AutoEncoder (DAE) methods have been explored to enhance the model's ability, while their success hinges on effective noise generation strategies. In this paper, we introduce a novel, structure-preserving noise generation scheme based on cross-modal CutMix, aiming to enhance the diversity of noise patterns while preserving the anatomical structure of the brain. To enhance the robustness of DAE learning, we propose an ensemble approach featuring dual experts, each incorporating distinct scale of noise. This dual-expert scheme effectively amplifies reconstruction errors in anomalous regions and suppresses false alarms in healthy areas. Additionally, we propose an anatomically-aware bidirectional consistency loss to ensure high-fidelity reconstruction at the regional level, using superpixels for anatomy perception and bidirectional distillation for reliable knowledge transfer. Extensive experiments across two different settings demonstrate the effectiveness and generalization ability of our proposed method. ? 2013 IEEE.