A Dempster-Shafer Approach to Trustworthy AI With Application to Fetal Brain MRI Segmentation
IEEE Transactions on Pattern Analysis and Machine Intelligence · 2024-05 · 46 (5) · 3784-3795
DOI: 10.1109/tpami.2023.3346330 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024-05. Verfasst von Lucas Fidon und 20 weiteren Autor:innen. Hauptthemen laut MEDLINE: Artificial Intelligence, Algorithms. Die Arbeit wurde bisher 39-mal zitiert (Crossref) und nennt 55 Literaturangaben.
Abstract (Originalsprache)
Deep learning models for medical image segmentation can fail unexpectedly and spectacularly for pathological cases and images acquired at different centers than training images, with labeling errors that violate expert knowledge. Such errors undermine the trustworthiness of deep learning models for medical image segmentation. Mechanisms for detecting and correcting such failures are essential for safely translating this technology into clinics and are likely to be a requirement of future regulations on artificial intelligence (AI). In this work, we propose a trustworthy AI theoretical framework and a practical system that can augment any backbone AI system using a fallback method and a fail-safe mechanism based on Dempster-Shafer theory. Our approach relies on an actionable definition of trustworthy AI. Our method automatically discards the voxel-level labeling predicted by the backbone AI that violate expert knowledge and relies on a fallback for those voxels. We demonstrate the effectiveness of the proposed trustworthy AI approach on the largest reported annotated dataset of fetal MRI consisting of 540 manually annotated fetal brain 3D T2w MRIs from 13 centers. Our trustworthy AI method improves the robustness of four backbone AI models for fetal brain MRIs acquired across various centers and for fetuses with various brain abnormalities.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Zitieren
APA
Fidon, L., Aertsen, M., Kofler, F., Bink, A., David, A. L., Deprest, T., Emam, D., Guffens, F., Jakab, A., Kasprian, G., Kienast, P., Melbourne, A., Menze, B., Mufti, N., Pogledic, I., Prayer, D., Stuempflen, M., Van Elslander, E., Ourselin, S., …, & Vercauteren, T. (2024). A Dempster-Shafer Approach to Trustworthy AI With Application to Fetal Brain MRI Segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 46(5), 3784-3795. https://doi.org/10.1109/tpami.2023.3346330
Vancouver
Fidon L, Aertsen M, Kofler F, Bink A, David AL, Deprest T, et al. A Dempster-Shafer Approach to Trustworthy AI With Application to Fetal Brain MRI Segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2024;46(5):3784-3795. doi:10.1109/tpami.2023.3346330
BibTeX
@article{Fidon2024,
author = {Fidon, Lucas and Aertsen, Michael and Kofler, Florian and Bink, Andrea and David, Anna L and Deprest, Thomas and Emam, Doaa and Guffens, Frederic and Jakab, Andras and Kasprian, Gregor and Kienast, Patric and Melbourne, Andrew and Menze, Bjoern and Mufti, Nada and Pogledic, Ivana and Prayer, Daniela and Stuempflen, Marlene and Van Elslander, Esther and Ourselin, Sebastien and Deprest, Jan and Vercauteren, Tom},
title = {A Dempster-Shafer Approach to Trustworthy AI With Application to Fetal Brain MRI Segmentation},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
year = {2024},
volume = {46},
number = {5},
pages = {3784--3795},
doi = {10.1109/tpami.2023.3346330}
}
EUVIMED