< Terug naar vorige pagina

Publicatie

Theoretical analysis and experimental validation of volume bias of soft Dice optimized segmentation maps in the context of inherent uncertainty

Tijdschriftbijdrage - Tijdschriftartikel

The clinical interest is often to measure the volume of a structure, which is typically derived from a segmentation. In order to evaluate and compare segmentation methods, the similarity between a segmentation and a predefined ground truth is measured using popular discrete metrics, such as the Dice score. Recent segmentation methods use a differentiable surrogate metric, such as soft Dice, as part of the loss function during the learning phase. In this work, we first briefly describe how to derive volume estimates from a segmentation that is, potentially, inherently uncertain or ambiguous. This is followed by a theoretical analysis and an experimental validation linking the inherent uncertainty to common loss functions for training CNNs, namely cross-entropy and soft Dice. We find that, even though soft Dice optimization leads to an improved performance with respect to the Dice score and other measures, it may introduce a volume bias for tasks with high inherent uncertainty. These findings indicate some of the method's clinical limitations and suggest doing a closer ad-hoc volume analysis with an optional re-calibration step.
Tijdschrift: Medical Image Analysis
ISSN: 1361-8415
Volume: 67
Jaar van publicatie:2021
BOF-keylabel:ja
IOF-keylabel:ja
BOF-publication weight:10
CSS-citation score:2
Auteurs:International
Authors from:Private, Higher Education
Toegankelijkheid:Open