发表机构
Sorbonne Université; Institut du Cerveau - Paris Brain Institute - ICM; CNRS; Inria; Inserm; AP-HP; Hôpital de la Pitié Salpêtrière(索邦大学; 巴黎大脑研究所; 法国国家科学研究中心; 法国国家信息与自动化研究所; 法国国家健康与医学研究院; 巴黎公立医院集团; 皮提耶-萨尔佩特里埃医院)
机构由 AI 辅助整理,请以论文原文为准。AI 中文总结
本文提出将无监督脑部异常检测建模为扩散先验下的贝叶斯逆问题,通过潜在异常掩码和退火后验采样联合推断伪健康图像与异常区域,在PET和MRI上提升了定位性能。
AI 中文摘要
无监督异常检测(UAD)旨在无需像素级标注的情况下定位医学扫描中的异常区域。一种典型策略是重建保留受试者特定解剖结构的伪健康图像。近期,扩散模型已被提出用于执行UAD。然而,这些方法依赖启发式噪声调度或合成损坏来平衡受试者特异性和异常去除。在本工作中,我们提出将UAD表述为扩散先验下的贝叶斯逆问题的替代方案。首先,我们引入一个潜在空间异常掩码,用于建模测试图像与其潜在对应的伪健康图像之间的像素级一致性。然后,我们提出对连接健康解剖结构、异常和观测图像的未知生成过程的近似,从而在贝叶斯框架内实现定义良好的似然。基于扩散逆问题方法的最新进展,我们通过退火后验采样联合推断伪健康图像和异常掩码。我们在FDG PET(ADNI)和FLAIR MRI(BraTS 2021)上评估了我们的方法,展示了与其他基于扩散的方法相比改进的异常定位性能,并验证了我们引入模型的贡献。我们的代码可在以下网址获取:此https URL。
英文摘要
Unsupervised anomaly detection (UAD) aims to localize abnormal regions in medical scans without pixel-level annotations. A typical strategy seeks to reconstruct a pseudo-healthy image that preserves subject-specific anatomy. Recently, diffusion models have been proposed to perform UAD. However, these methods rely on heuristic noise schedules or synthetic corruptions to balance subject-specificity and anomaly removal. In this work, we propose an alternative formulation of UAD as a Bayesian inverse problem under a diffusion prior. First, we introduce a latent spatial anomaly mask that models pixel-wise consistency between a test image and its latent corresponding pseudo-healthy image. Then, we propose an approximation of the unknown generation process that links healthy anatomy, anomalies, and the observed image, enabling a well-defined likelihood within the Bayesian framework. Building on recent advances in diffusion-based inverse problem methods, we jointly infer the pseudo-healthy image and the anomaly mask via annealed posterior sampling. We evaluate our approach on FDG PET (ADNI) and FLAIR MRI (BraTS 2021), demonstrating improved anomaly localization performance compared to other diffusion-based approaches and validating the contribution of our introduced model. Our code is available at https://github.com/HuguesRoy/UAD_DAPS.