paper-with-me

Papers

Noisy Image Segmentation With Soft-Dice

2023-04-03 · Marcus Nordström, Henrik Hult, Atsuto Maki, Fredrik Löfman

This paper presents a study on the soft-Dice loss, one of the most popular loss functions in medical image segmentation, for situations where noise is present in target labels. In particular, the set of optimal solutions are characterized and sharp bounds on the volume bias of these solutions are provided. It is further shown that a sequence of soft segmentations converging to optimal soft-Dice also converges to optimal Dice when converted to hard segmentations using thresholding. This is an important result because soft-Dice is often used as a proxy for maximizing the Dice metric. Finally, experiments confirming the theoretical results are provided.

📄 PDF Abstract BibTeX arXiv:2304.00801

Code (0)

등록된 구현이 없습니다.

Tasks

Image SegmentationMedical Image SegmentationSegmentationSemantic Segmentation

Similar Papers 제목 키워드 기반

Marginal Thresholding in Noisy Image Segmentation

2023-04-08 · Marcus Nordström, Henrik Hult, Atsuto Maki

This work presents a study on label noise in medical image segmentation by considering a noise model based on Gaussian field deformations. Such noise is of interest because it yields realistic looking segmentations and b…

Image SegmentationMedical Image SegmentationOrgan SegmentationSegmentation+1

The Impact Label Noise and Choice of Threshold has on Cross-Entropy and Soft-Dice in Image Segmentation

2025-01-01 · CVPR 2025 1 · Marcus Nordström, Atsuto Maki, Henrik Hult

In image segmentation and specifically in medical image segmentation, the soft-Dice loss is often chosen instead of the more traditional cross-entropy loss to improve performance with respect to the Dice metric.Exper…

Image SegmentationMedical Image SegmentationSegmentationSemantic Segmentation

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

2022-06-13 · Marcus Nordström, Henrik Hult, Jonas Söderberg, Fredrik Löfman

We study two of the most popular performance metrics in medical image segmentation, Accuracy and Dice, when the target labels are noisy. For both metrics, several statements related to characterization and volume propert…

Image SegmentationMedical Image SegmentationSemantic Segmentation

Optimization with soft Dice can lead to a volumetric bias

2019-11-06 · Jeroen Bertels, David Robben, Dirk Vandermeulen, Paul Suetens

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…

Medical Image AnalysisSegmentation

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

2019-11-05 · Jeroen Bertels, Tom Eelbode, Maxim Berman, Dirk Vandermeulen 외

The Dice score and Jaccard index are commonly used metrics for the evaluation of segmentation tasks in medical imaging. Convolutional neural networks trained for image segmentation tasks are usually optimized for (weight…

Image SegmentationMedical Image SegmentationSegmentationSemantic Segmentation