MOOD 2020: a public benchmark for out-of-distribution detection and localization on medical images

Zimmerer, D. et al. (2022) MOOD 2020: a public benchmark for out-of-distribution detection and localization on medical images. IEEE Transactions on Medical Imaging, 41(10), pp. 2728-2738. (doi: 10.1109/tmi.2022.3170077)

[img] Text
282155.pdf - Published Version
Available under License Creative Commons Attribution.

6MB

Abstract

Detecting Out-of-Distribution (OoD) data is one of the greatest challenges in safe and robust deployment of machine learning algorithms in medicine. When the algorithms encounter cases that deviate from the distribution of the training data, they often produce incorrect and over-confident predictions. OoD detection algorithms aim to catch erroneous predictions in advance by analysing the data distribution and detecting potential instances of failure. Moreover, flagging OoD cases may support human readers in identifying incidental findings. Due to the increased interest in OoD algorithms, benchmarks for different domains have recently been established. In the medical imaging domain, for which reliable predictions are often essential, an open benchmark has been missing. We introduce the Medical-Out-Of-Distribution-Analysis-Challenge (MOOD) as an open, fair, and unbiased benchmark for OoD methods in the medical imaging domain. The analysis of the submitted algorithms shows that performance has a strong positive correlation with the perceived difficulty, and that all algorithms show a high variance for different anomalies, making it yet hard to recommend them for clinical practice. We also see a strong correlation between challenge ranking and performance on a simple toy test set, indicating that this might be a valuable addition as a proxy dataset during anomaly detection algorithm development.

Item Type:Articles
Additional Information:This work was supported by the Helmholtz Association under the Joint Research School “HIDSS4Health—Helmholtz Information and Data Science School for Health” and Helmholtz Imaging.
Status:Published
Refereed:Yes
Glasgow Author(s) Enlighten ID:Kascenas, Antanas and Jensen, Dr Bjorn
Authors: Zimmerer, D., Full, P. M., Isensee, F., Jager, P., Adler, T., Petersen, J., Kohler, G., Ross, T., Reinke, A., Kascenas, A., Jensen, B. S., O'Neil, A. Q., Tan, J., Hou, B., Batten, J., Qiu, H., Kainz, B., Shvetsova, N., Fedulova, I., Dylov, D. V., Yu, B., Zhai, J., Hu, J., Si, R., Zhou, S., Wang, S., Li, X., Chen, X., Zhao, Y., Marimont, S. N., Tarroni, G., Saase, V., Maier-Hein, L., and Maier-Hein, K.
College/School:College of Science and Engineering
College of Science and Engineering > School of Computing Science
Journal Name:IEEE Transactions on Medical Imaging
Publisher:Institute of Electrical and Electronics Engineers (IEEE)
ISSN:0278-0062
ISSN (Online):1558-254X
Published Online:25 April 2022
Copyright Holders:Copyright © 2022 The Authors
First Published:First published in IEEE Transactions on Medical Imaging 41(10):2728-2738
Publisher Policy:Reproduced under a Creative Commons License

University Staff: Request a correction | Enlighten Editors: Update this record