Journal
MEDICAL IMAGE ANALYSIS
Volume 67, Issue -, Pages -Publisher
ELSEVIER
DOI: 10.1016/j.media.2020.101833
Keywords
CNN; Segmentation; Volume; Uncertainty; Cross-entropy; Soft dice
Categories
Funding
- European Union's Horizon 2020 Research and Innovations Programme [780026]
- innovation mandate of Flanders Innovation and Entrepreneurship (VLAIO)
Ask authors/readers for more resources
This study discusses the method of deriving volume estimates from uncertain or ambiguous segmentations. It identifies that soft Dice optimization may introduce volume bias in tasks with high inherent uncertainty. The study suggests a closer volume analysis and optional recalibration for better results.
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. (C) 2020 Elsevier B.V. All rights reserved.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available