# Optimization with soft Dice can lead to a volumetric bias

arXiv: https://arxiv.org/abs/1911.02278 · HTML: https://mlsanity.com/paper/1911.02278/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Nov 2019.

## Built on by (most cited first, 9 of 9)

- [Unified Focal loss: Generalising Dice and cross entropy-based losses to handle class imbalanced medical image segmentation](https://mlsanity.com/paper/2102.04525/) (2021)
- [Calibrating the Dice loss to handle neural network overconfidence for biomedical image segmentation](https://mlsanity.com/paper/2111.00528/) (2021)
- [RankSEG: A Consistent Ranking-based Framework for Segmentation](https://mlsanity.com/paper/2206.13086/) (2022)
- [Theoretical analysis and experimental validation of volume bias of soft Dice optimized segmentation maps in the context of inherent uncertainty](https://mlsanity.com/paper/2211.04161/) (2022)
- [Differentiable Deconvolution for Improved Stroke Perfusion Analysis](https://mlsanity.com/paper/2103.17111/) (2021)
- [Hypernet-Ensemble Learning of Segmentation Probability for Medical Image Segmentation with Ambiguous Labels](https://mlsanity.com/paper/2112.06693/) (2021)
- [Weakly Supervised Medical Image Segmentation With Soft Labels and Noise Robust Loss](https://mlsanity.com/paper/2209.08172/) (2022)
- [Towards contrast-agnostic soft segmentation of the spinal cord](https://mlsanity.com/paper/2310.15402/) (2023)
- [Beyond scalar losses: calibrating segmentation models via gradient vector field surgery](https://mlsanity.com/paper/2607.14338/) (2026)

## Abstract (arXiv)

Segmentation is a fundamental task in medical image analysis. The clinical interest is often to measure the volume of a structure. To evaluate and compare segmentation methods, the similarity between a segmentation and a predefined ground truth is measured using metrics such as the Dice score. Recent segmentation methods based on convolutional neural networks use a differentiable surrogate of the Dice score, such as soft Dice, explicitly as the loss function during the learning phase. Even though this approach leads to improved Dice scores, we find that, both theoretically and empirically on four medical tasks, it can introduce a volumetric bias for tasks with high inherent uncertainty. As such, this may limit the method's clinical applicability.