Noisy Image Segmentation With Soft-Dice
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Image SegmentationMedical Image SegmentationSegmentationSemantic SegmentationSimilar Papers 제목 키워드 기반
Marginal Thresholding in Noisy Image Segmentation
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+1The Impact Label Noise and Choice of Threshold has on Cross-Entropy and Soft-Dice in Image Segmentation
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 SegmentationOn 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 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 SegmentationOptimization with soft Dice can lead to a volumetric bias
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 AnalysisSegmentationOptimizing the Dice Score and Jaccard Index for Medical Image Segmentation: Theory & Practice
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