Patched diffusion models for unsupervised anomaly detection in brain MRI

First published in
Proceedings of machine learning research  
Number in series
227
Start Page
1019
End Page
1032
Citation
Proceedings of Machine Learning Research 227: 1019-1032 (2023)
Contribution to Conference
6th International Conference on Medical Imaging with Deep Learning, MIDL 2023  
Publisher DOI
10.48550/arXiv.2303.03758
Scopus ID
2-s2.0-85189362922
ArXiv ID
2303.03758
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
Subjects
MLE@TUHH
DDC Class
004: Computer Sciences
610: Medicine, Health
621: Applied Physics