TY  - JOUR
AU  - Zenk, Maximilian
AU  - Zimmerer, David
AU  - Isensee, Fabian
AU  - Traub, Jeremias
AU  - Norajitra, Tobias
AU  - Jäger, Paul F
AU  - Maier-Hein, Klaus
TI  - Comparative benchmarking of failure detection methods in medical image segmentation: Unveiling the role of confidence aggregation.
JO  - Medical image analysis
VL  - 101
SN  - 1361-8415
CY  - Amsterdam [u.a.]
PB  - Elsevier Science
M1  - DKFZ-2024-02629
SP  - 103392
PY  - 2025
N1  - #EA:E230#LA:E230# / Available online 30 November 2024
AB  - Semantic segmentation is an essential component of medical image analysis research, with recent deep learning algorithms offering out-of-the-box applicability across diverse datasets. Despite these advancements, segmentation failures remain a significant concern for real-world clinical applications, necessitating reliable detection mechanisms. This paper introduces a comprehensive benchmarking framework aimed at evaluating failure detection methodologies within medical image segmentation. Through our analysis, we identify the strengths and limitations of current failure detection metrics, advocating for the risk-coverage analysis as a holistic evaluation approach. Utilizing a collective dataset comprising five public 3D medical image collections, we assess the efficacy of various failure detection strategies under realistic test-time distribution shifts. Our findings highlight the importance of pixel confidence aggregation and we observe superior performance of the pairwise Dice score (Roy et al., 2019) between ensemble predictions, positioning it as a simple and robust baseline for failure detection in medical image segmentation. To promote ongoing research, we make the benchmarking framework available to the community.
KW  - Distribution shift (Other)
KW  - Failure detection (Other)
KW  - Quality control (Other)
KW  - Semantic segmentation (Other)
KW  - Uncertainty estimation (Other)
LB  - PUB:(DE-HGF)16
C6  - pmid:39657400
DO  - DOI:10.1016/j.media.2024.103392
UR  - https://inrepo02.dkfz.de/record/294922
ER  -