mlsanityData to 14 Oct 2026

Self and Mixed Supervision to Improve Training Labels for Multi-Class Medical Image Segmentation

arXiv 2403.03882 ↗First posted 6 Mar 2024cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Accurate training labels are a key component for multi-class medical image segmentation. Their annotation is costly and time-consuming because it requires domain expertise. This work aims to develop a dual-branch network and automatically improve training labels for multi-class image segmentation. Transfer learning is used to train the network and improve inaccurate weak labels sequentially. The dual-branch network is first trained by weak labels alone to initialize model parameters. After the network is stabilized, the shared encoder is frozen, and strong and weak decoders are fine-tuned by strong and weak labels together. The accuracy of weak labels is iteratively improved in the fine-tuning process. The proposed method was applied to a three-class segmentation of muscle, subcutaneous and visceral adipose tissue on abdominal CT scans. Validation results on 11 patients showed that the accuracy of training labels was statistically significantly improved, with the Dice similarity coefficient of muscle, subcutaneous and visceral adipose tissue increased from 74.2% to 91.5%, 91.2% to 95.6%, and 77.6% to 88.5%, respectively (p<0.05). In comparison with our earlier method, the label accuracy was also significantly improved (p<0.05). These experimental results suggested that the combination of the dual-branch network and transfer learning is an efficient means to improve training labels for multi-class segmentation.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 15 of its 29 references that are in the map. First posted on arXiv 6 Mar 2024.

Builds on

15 of 29 references.

References · 15

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2017A Survey on Deep Learning in Medical Image Analysiscited by 1,186
  3. 2018ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentationcited by 623
  4. 2017Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentationscited by 620
  5. 2022TotalSegmentator: robust segmentation of 104 anatomical structures in CT imagescited by 613
  6. 2021Semi-Supervised Semantic Segmentation with Cross Pseudo Supervisioncited by 463
  7. 2020Semi-Supervised Semantic Segmentation with Cross-Consistency Trainingcited by 376
  8. 2022Learning with Limited Annotations: A Survey on Deep Semi-Supervised Learning for Medical Image Segmentationcited by 76
  9. 2022BoostMIS: Boosting Medical Image Semi-supervised Learning with Adaptive Pseudo Labeling and Informative Active Annotationcited by 54
  10. 2021Diminishing Uncertainty within the Training Pool: Active Learning for Medical Image Segmentationcited by 45
  11. 2020Self-Loop Uncertainty: A Novel Pseudo-Label for Semi-Supervised Medical Image Segmentationcited by 42
  12. 2020Revisiting Rubik's Cube: Self-supervised Learning with Volume-wise Transformation for 3D Medical Image Segmentationcited by 40
3 more
  1. 2023Towards Generic Semi-Supervised Framework for Volumetric Medical Image Segmentationcited by 35
  2. 2022CUTS: A Deep Learning and Topological Framework for Multigranular Unsupervised Medical Image Segmentationcited by 8
  3. 2021Segmentation with mixed supervision: Confidence maximization helps knowledge distillationcited by 6

Built on by

Not cited yet.