paper-with-me

홈 › Papers

Dice Semimetric Losses: Optimizing the Dice Score with Soft Labels

2023-03-28 · Zifu Wang, Teodora Popordanoska, Jeroen Bertels, Robin Lemmens, Matthew B. Blaschko

The soft Dice loss (SDL) has taken a pivotal role in numerous automated segmentation pipelines in the medical imaging community. Over the last years, some reasons behind its superior functioning have been uncovered and further optimizations have been explored. However, there is currently no implementation that supports its direct utilization in scenarios involving soft labels. Hence, a synergy between the use of SDL and research leveraging the use of soft labels, also in the context of model calibration, is still missing. In this work, we introduce Dice semimetric losses (DMLs), which (i) are by design identical to SDL in a standard setting with hard labels, but (ii) can be employed in settings with soft labels. Our experiments on the public QUBIQ, LiTS and KiTS benchmarks confirm the potential synergy of DMLs with soft labels (e.g. averaging, label smoothing, and knowledge distillation) over hard labels (e.g. majority voting and random selection). As a result, we obtain superior Dice scores and model calibration, which supports the wider adoption of DMLs in practice. The code is available at https://github.com/zifuwanggg/JDTLosses

📄 PDF Abstract BibTeX arXiv:2303.16296

Code (1)

zifuwanggg/jdtlosses 공식 구현 pytorch

Tasks

Knowledge Distillation

Methods 이 논문이 사용한 방법론

Dice Loss \begin{equation} DiceLoss\left( y, \overline{p} \right) = 1 - \dfrac{\left( 2y\overline{p} + 1 \right)} {\left( y+\overline{p } + 1 \right)} \end{equation}

Similar Papers 제목 키워드 기반

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

2020-10-26 · Tom Eelbode, Jeroen Bertels, Maxim Berman, Dirk Vandermeulen 외

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 losse…

Image SegmentationMedical Image SegmentationSegmentationSemantic Segmentation

Multimodal HIE Lesion Segmentation in Neonates: A Comparative Study of Loss Functions

2025-02-13 · Annayah Usman, Abdul Haseeb, Tahir Syed

Segmentation of Hypoxic-Ischemic Encephalopathy (HIE) lesions in neonatal MRI is a crucial but challenging task due to diffuse multifocal lesions with varying volumes and the limited availability of annotated HIE lesion …

Lesion SegmentationSegmentation

Contour Dice loss for structures with Fuzzy and Complex Boundaries in Fetal MRI

2022-09-25 · Bella Specktor Fadida, Bossmat Yehuda, Daphna Link Sourani, Liat Ben Sira 외

Volumetric measurements of fetal structures in MRI are time consuming and error prone and therefore require automatic segmentation. Placenta segmentation and accurate fetal brain segmentation for gyrification assessment …

Brain SegmentationPlacenta SegmentationSegmentation

Do We Really Need Dice? The Hidden Region-Size Biases of Segmentation Losses

2021-04-18 · Bingyuan Liu, Jose Dolz, Adrian Galdran, Riadh Kobbi 외

Most segmentation losses are arguably variants of the Cross-Entropy (CE) or Dice losses. On the surface, these two categories of losses seem unrelated, and there is no clear consensus as to which category is a better cho…

On the dice loss gradient and the ways to mimic it

2023-04-09 · Hoel Kervadec, Marleen de Bruijne

In the past few years, in the context of fully-supervised semantic segmentation, several losses -- such as cross-entropy and dice -- have emerged as de facto standards to supervise neural networks. The Dice loss is an in…

Semantic Segmentation