Patched Diffusion Models for Unsupervised Anomaly Detection in Brain MRI

Finn Behrendt, Debayan Bhattacharya, Julia Krüger, Roland Opfer, Alexander Schlaefer

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: [ 1 code implementation](https://www.catalyzex.com/paper/arxiv:2303.03758/code)