Towards Reliable Deep Learning: Feature-Based Out-Of-Distribution Detection for Brain Morphometry
Tommaso Di Noto, Lina Bacha, Keerthi Prabhu M, Vincent Dunet, Attapon Jantarato, Manuela Vaněčková, Emmanuelle Le Bars, Nicolas Menjot de Champfleur, Punith B. Venkategowda, Bénédicte Maréchal · Proceedings on CD-ROM - International Society for Magnetic Resonance in Medicine. Scientific Meeting and Exhibition/Proceedings of the International Society for Magnetic Resonance in Medicine, Scientific Meeting and Exhibition · 2025
Motivation: Despite recent advancements in image segmentation, supervised deep learning algorithms struggle to generalize to Out-Of-Distribution data. Goal(s): Explore Out-of-Distribution Detection (OODD) in the context of volume-based morphometry for 3D-T1w brain images. Approach: We estimate a training distribution through a patch-based Convolutional-Neural-Network designed for skull-stripping, which extracts essential features from In-Distribution (ID) data. Then, we classify patients (ID vs. OOD) by calculating the distance in feature space between test patches and this established training distribution. Results: Our OODD method correctly classifies 98% of Test-ID subjects and 86% Far-OOD. However, it misclassifies most Near-OOD scans suggesting that the skull-stripping-network alone is insufficient for all use-cases. Impact: We experiment feature-based Out-Of-Distribution (OOD) detection to identify problematic scans for which segmentation results might be unreliable. While Near-OOD remains an area of future improvement, our approach is effective for the majority of use cases and adds negligible computation time.