mlsanityData to 7 Oct 2026

Enhancing AI Diagnostics: Autonomous Lesion Masking via Semi-Supervised Deep Learning

arXiv 2404.12450 ↗First posted 18 Apr 2024cs.CV cs.AI cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

This study presents an unsupervised domain adaptation method aimed at autonomously generating image masks outlining regions of interest (ROIs) for differentiating breast lesions in breast ultrasound (US) imaging. Our semi-supervised learning approach utilizes a primitive model trained on a small public breast US dataset with true annotations. This model is then iteratively refined for the domain adaptation task, generating pseudo-masks for our private, unannotated breast US dataset. The dataset, twice the size of the public one, exhibits considerable variability in image acquisition perspectives and demographic representation, posing a domain-shift challenge. Unlike typical domain adversarial training, we employ downstream classification outcomes as a benchmark to guide the updating of pseudo-masks in subsequent iterations. We found the classification precision to be highly correlated with the completeness of the generated ROIs, which promotes the explainability of the deep learning classification model. Preliminary findings demonstrate the efficacy and reliability of this approach in streamlining the ROI annotation process, thereby enhancing the classification and localization of breast lesions for more precise and interpretable diagnoses.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 37 of its 48 references that are in the map. First posted on arXiv 18 Apr 2024.

Builds on

37 of 48 references.

References · 37

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  2. 2016Densely Connected Convolutional Networkscited by 6,691
  3. 2019Self-training with Noisy Student improves ImageNet classificationcited by 1,304
  4. 2016Playing for Data: Ground Truth from Computer Gamescited by 816
  5. 2018ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentationcited by 623
  6. 2020FDA: Fourier Domain Adaptation for Semantic Segmentationcited by 540
  7. 2019Bidirectional Learning for Domain Adaptation of Semantic Segmentationcited by 308
  8. 2022Semi-Supervised Semantic Segmentation Using Unreliable Pseudo-Labelscited by 218
  9. 2020Semi-supervised Medical Image Segmentation through Dual-task Consistencycited by 215
  10. 2020Unsupervised Intra-domain Adaptation for Semantic Segmentation through Self-Supervisioncited by 198
  11. 2021ST++: Make Self-training Work Better for Semi-supervised Semantic Segmentationcited by 184
  12. 2020Instance Adaptive Self-Training for Unsupervised Domain Adaptationcited by 177
25 more
  1. 2018Adversarial Learning for Semi-Supervised Semantic Segmentationcited by 173
  2. 2021Source-Free Domain Adaptation for Semantic Segmentationcited by 168
  3. 2019FickleNet: Weakly and Semi-supervised Semantic Image Segmentation using Stochastic Inferencecited by 162
  4. 2019Category Anchor-Guided Unsupervised Domain Adaptation for Semantic Segmentationcited by 151
  5. 2018Revisiting Dilated Convolution: A Simple Approach for Weakly- and Semi- Supervised Semantic Segmentationcited by 145
  6. 2021Semantic Segmentation with Generative Models: Semi-Supervised Learning and Strong Out-of-Domain Generalizationcited by 141
  7. 2019Domain Adaptation for Semantic Segmentation with Maximum Squares Losscited by 138
  8. 2021Anti-Adversarially Manipulated Attributions for Weakly and Semi-Supervised Semantic Segmentationcited by 134
  9. 2019Self-Ensembling with GAN-based Data Augmentation for Domain Adaptation in Semantic Segmentationcited by 126
  10. 2021Perturbed and Strict Mean Teachers for Semi-supervised Semantic Segmentationcited by 113
  11. 2021Pixel Contrastive-Consistent Semi-Supervised Semantic Segmentationcited by 101
  12. 2021Semi-Supervised Semantic Segmentation via Adaptive Equalization Learningcited by 101
  13. 2018Unsupervised domain adaptation for medical imaging segmentation with self-ensemblingcited by 94
  14. 2019Multi-source Domain Adaptation for Semantic Segmentationcited by 74
  15. 2019Semi-Supervised Medical Image Segmentation via Learning Consistency under Transformationscited by 71
  16. 2020Contextual-Relation Consistent Domain Adaptation for Semantic Segmentationcited by 70
  17. 2022Semi-supervised Semantic Segmentation with Error Localization Networkcited by 57
  18. 2019Multi-Task Attention-Based Semi-Supervised Learning for Medical Image Segmentationcited by 55
  19. 2021Semi-supervised Contrastive Learning for Label-efficient Medical Image Segmentationcited by 52
  20. 2018Universal Semi-Supervised Semantic Segmentationcited by 50
  21. 2021Multi-Source Domain Adaptation with Collaborative Learning for Semantic Segmentationcited by 44
  22. 2020Learning from Scale-Invariant Examples for Domain Adaptation in Semantic Segmentationcited by 41
  23. 2020Context-Aware Domain Adaptation in Semantic Segmentationcited by 36
  24. 2021Geometric Unsupervised Domain Adaptation for Semantic Segmentationcited by 33
  25. 2020Unsupervised BatchNorm Adaptation (UBNA): A Domain Adaptation Method for Semantic Segmentation Without Using Source Domain Representationscited by 24

Built on by

Not cited yet.