Optimization for Medical Image Segmentation: Theory and Practice when evaluating with Dice Score or Jaccard Index

by   Tom Eelbode, et al.

In many medical imaging and classical computer vision tasks, the Dice score and Jaccard index are used to evaluate the segmentation performance. Despite the existence and great empirical success of metric-sensitive losses, i.e. relaxations of these metrics such as soft Dice, soft Jaccard and Lovasz-Softmax, many researchers still use per-pixel losses, such as (weighted) cross-entropy to train CNNs for segmentation. Therefore, the target metric is in many cases not directly optimized. We investigate from a theoretical perspective, the relation within the group of metric-sensitive loss functions and question the existence of an optimal weighting scheme for weighted cross-entropy to optimize the Dice score and Jaccard index at test time. We find that the Dice score and Jaccard index approximate each other relatively and absolutely, but we find no such approximation for a weighted Hamming similarity. For the Tversky loss, the approximation gets monotonically worse when deviating from the trivial weight setting where soft Tversky equals soft Dice. We verify these results empirically in an extensive validation on six medical segmentation tasks and can confirm that metric-sensitive losses are superior to cross-entropy based loss functions in case of evaluation with Dice Score or Jaccard Index. This further holds in a multi-class setting, and across different object sizes and foreground/background ratios. These results encourage a wider adoption of metric-sensitive loss functions for medical segmentation tasks where the performance measure of interest is the Dice score or Jaccard index.


page 1

page 6

page 8

page 9

page 11

page 13

page 14

page 15


Optimizing the Dice Score and Jaccard Index for Medical Image Segmentation: Theory Practice

The Dice score and Jaccard index are commonly used metrics for the evalu...

A Mixed Focal Loss Function for Handling Class Imbalanced Medical Image Segmentation

Automatic segmentation methods are an important advancement in medical i...

Comparing Deep Learning strategies for paired but unregistered multimodal segmentation of the liver in T1 and T2-weighted MRI

We address the problem of multimodal liver segmentation in paired but un...

The Dice loss in the context of missing or empty labels: Introducing Φ and ε

Albeit the Dice loss is one of the dominant loss functions in medical im...

The hidden label-marginal biases of segmentation losses

Most segmentation losses are arguably variants of the Cross-Entropy (CE)...

Comparing ML based Segmentation Models on Jet Fire Radiation Zone

Risk assessment is relevant in any workplace, however there is a degree ...

Boundary loss for highly unbalanced segmentation

Widely used loss functions for convolutional neural network (CNN) segmen...