On 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 properties of the set of optimal segmentations are proved, and associated experiments are provided. Our main insights are: (i) the volume of the solutions to both metrics may deviate significantly from the expected volume of the target, (ii) the volume of a solution to Accuracy is always less than or equal to the volume of a solution to Dice and (iii) the optimal solutions to both of these metrics coincide when the set of feasible segmentations is constrained to the set of segmentations with the volume equal to the expected volume of the target.
Code (1)
Tasks
Image SegmentationMedical Image SegmentationSemantic SegmentationSimilar Papers 제목 키워드 기반
Finding Nano-Ötzi: Semi-Supervised Volume Visualization for Cryo-Electron Tomography
Cryo-Electron Tomography (cryo-ET) is a new 3D imaging technique with unprecedented potential for resolving submicron structural detail. Existing volume visualization methods, however, cannot cope with its very low signa…
Electron TomographySegmentationAttention-Based 3D Seismic Fault Segmentation Training by a Few 2D Slice Labels
Detection faults in seismic data is a crucial step for seismic structural interpretation, reservoir characterization and well placement. Some recent works regard it as an image segmentation task. The task of image segmen…
Fault DetectionImage SegmentationSegmentationSemantic SegmentationFederated Medical Image Segmentation under Real-World Label Noise: A Benchmark Suite for Noisy Label Learning Method Selection
While federated learning (FL) enables collaborative medical image segmentation without centralizing sensitive data, real-world deployment is frequently complicated by cross-site label imperfections such as contour disagr…
Medical Image SegmentationFederated LearningNoisy 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…
Image SegmentationMedical Image SegmentationSegmentationSemantic SegmentationRethinking Barely-Supervised Volumetric Medical Image Segmentation from an Unsupervised Domain Adaptation Perspective
This paper investigates an extremely challenging problem: barely-supervised volumetric medical image segmentation (BSS). A BSS training dataset consists of two parts: 1) a barely-annotated labeled set, where each labeled…
Domain AdaptationImage RegistrationImage SegmentationMedical Image Segmentation+3