mlsanityData to 14 Oct 2026

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

arXiv 2206.06484 ↗First posted 13 Jun 2022cs.CV cs.LGcited by 6

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 22 of its 50 references that are in the map. First posted on arXiv 13 Jun 2022.

Builds on

22 of 50 references.

References · 22

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  2. 20163D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotationcited by 1,476
  3. 2017A Survey on Deep Learning in Medical Image Analysiscited by 1,186
  4. 2017Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentationscited by 620
  5. 2019Embracing Imperfect Datasets: A Review of Deep Learning Solutions for Medical Image Segmentationcited by 260
  6. 2016Data Programming: Creating Large Training Sets, Quicklycited by 246
  7. 2019Deep learning with noisy labels: exploring techniques and remedies in medical image analysiscited by 173
  8. 2016The Importance of Skip Connections in Biomedical Image Segmentationcited by 126
  9. 2016Deep Label Distribution Learning with Label Ambiguitycited by 104
  10. 2019Optimizing the Dice Score and Jaccard Index for Medical Image Segmentation: Theory & Practicecited by 71
  11. 2017Deep Learning from Noisy Image Labels with Quality Embeddingcited by 46
  12. 2020Deep Convolutional Neural Networks with Spatial Regularization, Volume and Star-shape Priori for Image Segmentationcited by 31
10 more
  1. 2020SoftSeg: Advantages of soft versus binary training for image segmentationcited by 26
  2. 2019Learning to Segment Skin Lesions from Noisy Annotationscited by 25
  3. 2019Pick-and-Learn: Automatic Quality Evaluation for Noisy-Labeled Image Segmentationcited by 25
  4. 2020Post Training Uncertainty Calibration of Deep Networks For Medical Image Segmentationcited by 19
  5. 2021Using Soft Labels to Model Uncertainty in Medical Image Segmentationcited by 18
  6. 2022Label fusion and training methods for reliable representation of inter-rater uncertaintycited by 13
  7. 2019Soft labeling by Distilling Anatomical knowledge for Improved MS Lesion Segmentationcited by 11
  8. 2021On the relationship between calibrated predictors and unbiased volume estimationcited by 11
  9. 2020Robustness study of noisy annotation in deep learning based medical image segmentationcited by 9
  10. 2020Superpixel-Guided Label Softening for Medical Image Segmentationcited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 2; 2024: 2; 2025: 1; 2026: 1.

6 papers.

  1. 2024Label-Noise Robust Diffusion Modelscited by 16
  2. 2024Noisy Annotations in Semantic Segmentationcited by 5
  3. 2023Noisy Image Segmentation With Soft-Dicecited by 1
  4. 2023Marginal Thresholding in Noisy Image Segmentationcited by 0
  5. 2025Modality-AGnostic Image Cascade (MAGIC) for Multi-Modality Cardiac Substructure Segmentationcited by 0
  6. 2026A Novel Method to Evaluate Models on Unreliable, Noisy and Inconsistent Labels: Adaptive Resolution Label Aggregation (ARLA)cited by 0