U<sup>2</sup>AD: Uncertainty-based unsupervised anomaly detection framework for detecting T2 hyperintensity in MRI spinal cord.
Authors
Affiliations (7)
Affiliations (7)
- School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, 200240, China. Electronic address: [email protected].
- Department of Spine Surgery, Renji Hospital, School of Medicine, Shanghai Jiao Tong University, Shanghai, 200127, China. Electronic address: [email protected].
- Department of Radiology, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, 200025, China. Electronic address: [email protected].
- Department of Spine Surgery, Renji Hospital, School of Medicine, Shanghai Jiao Tong University, Shanghai, 200127, China. Electronic address: [email protected].
- Department of Radiology, Renji Hospital, School of Medicine, Shanghai Jiao Tong University, Shanghai, 200127, China. Electronic address: [email protected].
- Department of Spine Surgery, Renji Hospital, School of Medicine, Shanghai Jiao Tong University, Shanghai, 200127, China. Electronic address: [email protected].
- School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, 200240, China; National Engineering Research Center of Advanced Magnetic Resonance Technologies for Diagnosis and Therapy (NERC-AMRT), Shanghai, China; Med-X Research Institute, Shanghai Jiao Tong University, Shanghai, 200030, China. Electronic address: [email protected].
Abstract
T2 hyperintensities in spinal cord MR images are crucial biomarkers for conditions such as degenerative cervical myelopathy (DCM). However, current clinical diagnoses primarily rely on manual evaluation. Deep learning methods have shown promise in lesion detection, but most supervised approaches are heavily dependent on large, annotated datasets. Unsupervised anomaly detection (UAD) offers a compelling alternative by eliminating the need for abnormal data annotations. However, existing UAD methods face challenges of domain shifts and task conflict. We propose an Uncertainty-based Unsupervised Anomaly Detection framework, termed U<sup>2</sup>AD, to address these limitations. Unlike traditional methods, U<sup>2</sup>AD is designed to be trained and tested within the same clinical dataset, following a "mask-and-reconstruction" paradigm built on a Vision Transformer-based architecture. We introduce an uncertainty-guided masking strategy to resolve task conflicts between normal reconstruction and anomaly detection to achieve an optimal balance. Specifically, we employ a Monte-Carlo inference technique to estimate reconstruction uncertainty mappings during training. By iteratively optimizing reconstruction training under the guidance of both epistemic and aleatoric uncertainty, U<sup>2</sup>AD improves the normal representation learning while maintaining the sensitivity to anomalies. Experimental results demonstrate that U<sup>2</sup>AD outperforms existing UAD methods in patient-level identification and segment-level localization of spinal cord T2 hyperintensities. This framework establishes a new benchmark for incorporating uncertainty guidance into UAD. Our code is available at: https://github.com/zhibaishouheilab/U2AD.