_version_ 1866911759072231424
author Fidon, Lucas
Aertsen, Michael
Kofler, Florian
Bink, Andrea
David, Anna L.
Deprest, Thomas
Emam, Doaa
Guffens, Frédéric
Jakab, András
Kasprian, Gregor
Kienast, Patric
Melbourne, Andrew
Menze, Bjoern
Mufti, Nada
Pogledic, Ivana
Prayer, Daniela
Stuempflen, Marlene
Van Elslander, Esther
Ourselin, Sébastien
Deprest, Jan
Vercauteren, Tom
author_facet Fidon, Lucas
Aertsen, Michael
Kofler, Florian
Bink, Andrea
David, Anna L.
Deprest, Thomas
Emam, Doaa
Guffens, Frédéric
Jakab, András
Kasprian, Gregor
Kienast, Patric
Melbourne, Andrew
Menze, Bjoern
Mufti, Nada
Pogledic, Ivana
Prayer, Daniela
Stuempflen, Marlene
Van Elslander, Esther
Ourselin, Sébastien
Deprest, Jan
Vercauteren, Tom
contents 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 a state-of-the-art backbone AI for fetal brain MRIs acquired across various centers and for fetuses with various brain abnormalities.
format Preprint
id arxiv_https___arxiv_org_abs_2204_02779
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle A Dempster-Shafer approach to trustworthy AI with application to fetal brain MRI segmentation
Fidon, Lucas
Aertsen, Michael
Kofler, Florian
Bink, Andrea
David, Anna L.
Deprest, Thomas
Emam, Doaa
Guffens, Frédéric
Jakab, András
Kasprian, Gregor
Kienast, Patric
Melbourne, Andrew
Menze, Bjoern
Mufti, Nada
Pogledic, Ivana
Prayer, Daniela
Stuempflen, Marlene
Van Elslander, Esther
Ourselin, Sébastien
Deprest, Jan
Vercauteren, Tom
Image and Video Processing
Artificial Intelligence
Computer Vision and Pattern Recognition
Machine Learning
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 a state-of-the-art backbone AI for fetal brain MRIs acquired across various centers and for fetuses with various brain abnormalities.
title A Dempster-Shafer approach to trustworthy AI with application to fetal brain MRI segmentation
topic Image and Video Processing
Artificial Intelligence
Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2204.02779