MOOD 2020: A Public Benchmark for Out-of-Distribution Detection and Localization on Medical Images

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 prediction...

Full description

Saved in:

Bibliographic Details
Published in:	IEEE transactions on medical imaging Vol. 41; no. 10; pp. 2728 - 2738
Main Authors:	Zimmerer, David, Full, Peter M., Isensee, Fabian, Jager, Paul, Adler, Tim, Petersen, Jens, Kohler, Gregor, Ross, Tobias, Reinke, Annika, Kascenas, Antanas, Jensen, Bjorn Sand, O'Neil, Alison Q., Tan, Jeremy, Hou, Benjamin, Batten, James, Qiu, Huaqi, Kainz, Bernhard, Shvetsova, Nina, Fedulova, Irina, Dylov, Dmitry V., Yu, Baolun, Zhai, Jianyang, Hu, Jingtao, Si, Runxuan, Zhou, Sihang, Wang, Siqi, Li, Xinyang, Chen, Xuerun, Zhao, Yang, Marimont, Sergio Naval, Tarroni, Giacomo, Saase, Victor, Maier-Hein, Lena, Maier-Hein, Klaus
Format:	Journal Article
Language:	English
Published:	United States IEEE 01-10-2022 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:	Algorithms Annotations Anomalies Anomaly detection anomaly localization Benchmark testing Benchmarks biomedical challenge Biomedical imaging Domains Failure analysis Localization Machine learning Medical imaging Mood out-of-distribution analysis Prediction algorithms Predictions Task analysis Training
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	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.
Bibliography:	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23
ISSN:	0278-0062 1558-254X
DOI:	10.1109/TMI.2022.3170077