Keywords: Deep Learning, Unsupervised Anomaly Detection, MRI, Diffusion Models
TL;DR: We approach unsupervised anomaly detection in brain MRI scans with patch-based diffusion models, utilizing global spatial context to improve the local estimation of anatomically consistent anatomy in MRI scans of healthy brains.
Abstract: 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.
Community Implementations: [![CatalyzeX](/images/catalyzex_icon.svg) 1 code implementation](https://www.catalyzex.com/paper/arxiv:2303.03758/code)