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

11/08/2022
by   Jeroen Bertels, et al.
0

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.

READ FULL TEXT

page 5

page 12

research
11/06/2019

Optimization with soft Dice can lead to a volumetric bias

Segmentation is a fundamental task in medical image analysis. The clinic...
research
11/14/2019

Give me (un)certainty – An exploration of parameters that affect segmentation uncertainty

Segmentation tasks in medical imaging are inherently ambiguous: the boun...
research
04/03/2023

Noisy Image Segmentation With Soft-Dice

This paper presents a study on the soft-Dice loss, one of the most popul...
research
04/18/2021

The hidden label-marginal biases of segmentation losses

Most segmentation losses are arguably variants of the Cross-Entropy (CE)...
research
06/27/2022

RankSEG: A Consistent Ranking-based Framework for Segmentation

Segmentation has emerged as a fundamental field of computer vision and n...
research
06/13/2022

On Image Segmentation With Noisy Labels: Characterization and Volume Properties of the Optimal Solutions to Accuracy and Dice

We study two of the most popular performance metrics in medical image se...
research
06/26/2019

Continuous Dice Coefficient: a Method for Evaluating Probabilistic Segmentations

Objective: Overlapping measures are often utilized to quantify the simil...

Please sign up or login with your details

Forgot password? Click here to reset