Reliable anomaly detection in brain MRI remains challenging due to the scarcity of annotated abnormal cases and the frequent absence of key imaging modalities in real clinical workflows. Existing single-class or multi-class anomaly detection (AD) models typically rely on fixed modality configurations, require repetitive training, or fail to generalize to unseen modality combinations, limiting their clinical scalability. In this work, we present a unified Any-Modality AD framework that performs robust anomaly detection and localization under arbitrary MRI modality availability. The framework integrates a dual-pathway DINOv2 encoder with a feature distribution alignment mechanism that statistically aligns incomplete-modality features with full-modality representations, enabling stable inference even with severe modality dropout. To further enhance semantic consistency, we introduce an Intrinsic Normal Prototypes (INPs) extractor and an INP-guided decoder that reconstruct only normal anatomical patterns while naturally amplifying abnormal deviations. Through randomized modality masking and indirect feature completion during training, the model learns to adapt to all modality configurations without re-training. Extensive experiments on BraTS2018, MU-Glioma-Post, and Pretreat-MetsToBrain-Masks demonstrate that our approach consistently surpasses state-of-the-art industrial and medical AD baselines across 7 modality combinations, achieving superior generalization. This study establishes a scalable paradigm for multimodal medical AD under real-world, imperfect modality conditions. Our source code is available at https://github.com/wuchangw/AnyAD.
翻译:脑部MRI的可靠异常检测仍面临挑战,这主要源于标注异常病例的稀缺以及真实临床工作流中关键成像模态的频繁缺失。现有的单类或多类异常检测模型通常依赖于固定的模态配置、需要重复训练,或无法泛化到未见过的模态组合,限制了其临床可扩展性。在本研究中,我们提出了一种统一的任意模态异常检测框架,能够在任意MRI模态可用性的条件下执行稳健的异常检测与定位。该框架集成了一个双通路DINOv2编码器与一个特征分布对齐机制,该机制在统计上将不完整模态的特征与完整模态的表征对齐,从而即使在严重模态缺失的情况下也能实现稳定的推理。为了进一步增强语义一致性,我们引入了一个内在正常原型提取器和一个INP引导的解码器,该解码器仅重建正常的解剖模式,同时自然地放大异常偏差。通过在训练期间进行随机模态掩码和间接特征补全,模型能够学会适应所有模态配置而无需重新训练。在BraTS2018、MU-Glioma-Post和Pretreat-MetsToBrain-Masks数据集上进行的大量实验表明,我们的方法在7种模态组合上持续超越了最先进的工业和医学异常检测基线,实现了卓越的泛化性能。本研究为现实世界中不完美模态条件下的多模态医学异常检测建立了一个可扩展的范式。我们的源代码可在 https://github.com/wuchangw/AnyAD 获取。