Patched Diffusion Models for Unsupervised Anomaly Detection in Brain MRI
This addresses the problem of detecting brain pathologies without annotated data for clinicians, though it is incremental as it builds on existing diffusion models.
The paper tackles unsupervised anomaly detection in brain MRI by proposing a patch-based diffusion model to generate healthy brain anatomy, achieving a 25.1% relative improvement over baselines in detecting tumors and multiple sclerosis lesions.
The use of supervised deep learning techniques to detect pathologies in brain MRI scans can be challenging due to the diversity of brain anatomy and the need for annotated data sets. An alternative approach is to use unsupervised anomaly detection, which only requires sample-level labels of healthy brains to create a reference representation. This reference representation can then be compared to unhealthy brain anatomy in a pixel-wise manner to identify abnormalities. To accomplish this, generative models are needed to create anatomically consistent MRI scans of healthy brains. While recent diffusion models have shown promise in this task, accurately generating the complex structure of the human brain remains a challenge. In this paper, we propose a method that reformulates the generation task of diffusion models as a patch-based estimation of healthy brain anatomy, using spatial context to guide and improve reconstruction. We evaluate our approach on data of tumors and multiple sclerosis lesions and demonstrate a relative improvement of 25.1% compared to existing baselines.