PuSH - Publication Server of Helmholtz Zentrum München

Bercea, C.-I. ; Wiestler, B.* ; Rueckert, D.* ; Schnabel, J.A.

Generalizing Unsupervised Anomaly Detection: Towards Unbiased Pathology Screening.

In: (6th International Conference on Medical Imaging with Deep Learning (MIDL), 10-12 July 2023, Vanderbilt Univ, Nashville). 1269 Law St, San Diego, Ca, United States: Jmlr-journal Machine Learning Research, 2023. 39-52 ( ; 227)
The main benefit of unsupervised anomaly detection is the ability to identify arbitrary instances of pathologies even in the absence of training labels or sufficient examples of the rare class(es). Even though much work has been done on using auto-encoders (AE) for anomaly detection, there are still two critical challenges to overcome: First, learning compact and detailed representations of the healthy distribution is cumbersome. Second, the majority of unsupervised algorithms are tailored to detect hyperintense lesions on FLAIR brain MR scans. We found that even state-of-the-art (SOTA) AEs fail to detect several classes of non-hyperintense anomalies on T1w brain MRIs, such as brain atrophy, edema, or resections. In this work, we propose reversed AEs (RA) to generate pseudo-healthy reconstructions and localize various brain pathologies. Our method outperformed SOTA methods on T1w brain MRIs, detecting more global anomalies (AUROC increased from 73.1 to 89.4) and local pathologies (detection rate increased from 52.6% to 86.0%).
Additional Metrics?
[➜Log in]
Edit extra informations Login
Publication type Article: Conference contribution
Corresponding Author
Keywords Unsupervised Anomaly Detection; Pathology Screening
ISSN (print) / ISBN 2640-3498
Conference Title 6th International Conference on Medical Imaging with Deep Learning (MIDL)
Conference Date 10-12 July 2023
Conference Location Vanderbilt Univ, Nashville
Quellenangaben Volume: 227, Issue: , Pages: 39-52 Article Number: , Supplement: ,
Publisher Jmlr-journal Machine Learning Research
Publishing Place 1269 Law St, San Diego, Ca, United States
Non-patent literature Publications
Institute(s) Institute for Machine Learning in Biomed Imaging (IML)
Helmholtz Artifical Intelligence Cooperation Unit (HAICU)
Grants Helmholtz Association under the joint research school "Munich School for Data Science -MUDS"