Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
149 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Constructing and Exploring Intermediate Domains in Mixed Domain Semi-supervised Medical Image Segmentation (2404.08951v1)

Published 13 Apr 2024 in cs.CV and cs.LG

Abstract: Both limited annotation and domain shift are prevalent challenges in medical image segmentation. Traditional semi-supervised segmentation and unsupervised domain adaptation methods address one of these issues separately. However, the coexistence of limited annotation and domain shift is quite common, which motivates us to introduce a novel and challenging scenario: Mixed Domain Semi-supervised medical image Segmentation (MiDSS). In this scenario, we handle data from multiple medical centers, with limited annotations available for a single domain and a large amount of unlabeled data from multiple domains. We found that the key to solving the problem lies in how to generate reliable pseudo labels for the unlabeled data in the presence of domain shift with labeled data. To tackle this issue, we employ Unified Copy-Paste (UCP) between images to construct intermediate domains, facilitating the knowledge transfer from the domain of labeled data to the domains of unlabeled data. To fully utilize the information within the intermediate domain, we propose a symmetric Guidance training strategy (SymGD), which additionally offers direct guidance to unlabeled data by merging pseudo labels from intermediate samples. Subsequently, we introduce a Training Process aware Random Amplitude MixUp (TP-RAM) to progressively incorporate style-transition components into intermediate samples. Compared with existing state-of-the-art approaches, our method achieves a notable 13.57% improvement in Dice score on Prostate dataset, as demonstrated on three public datasets. Our code is available at https://github.com/MQinghe/MiDSS .

Definition Search Book Streamline Icon: https://streamlinehq.com
References (49)
  1. Semi-supervised learning for network-based cardiac mr image segmentation. In Medical Image Computing and Computer-Assisted Intervention, pages 253–260. Springer, 2017.
  2. Bidirectional copy-paste for semi-supervised medical image segmentation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 11514–11524, 2023.
  3. Orthogonal annotation benefits barely-supervised medical image segmentation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 3302–3311, 2023.
  4. Multi-centre, multi-vendor and multi-disease cardiac segmentation: the m&ms challenge. IEEE Transactions on Medical Imaging, 40(12):3543–3554, 2021.
  5. Adversarial image synthesis for unpaired multi-modal cardiac data. In Simulation and Synthesis in Medical Imaging: Second International Workshop, SASHIMI, pages 3–13. Springer, 2017.
  6. Unsupervised bidirectional cross-modality adaptation via deeply synergistic image and feature alignment for medical image segmentation. IEEE Transactions on Medical Imaging, 39(7):2494–2505, 2020.
  7. Deliberated domain bridging for domain adaptive semantic segmentation. Advances in Neural Information Processing Systems, 35:15105–15118, 2022.
  8. A deep learning-based auto-segmentation system for organs-at-risk on whole-body computed tomography images for radiation therapy. Radiotherapy and Oncology, 160:175–184, 2021a.
  9. Semi-supervised semantic segmentation with cross pseudo supervision. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 2613–2622, 2021b.
  10. Big data in healthcare: management, analysis and future prospects. Journal of Big Data, 6(1):1–25, 2019.
  11. Unsupervised cross-modality domain adaptation of convnets for biomedical image segmentations with adversarial loss. arXiv preprint arXiv:1804.10916, 2018.
  12. Towards semi-supervised learning with non-random missing labels. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 16121–16131, 2023.
  13. Inf-net: Automatic covid-19 lung infection segmentation from ct images. IEEE Transactions on Medical Imaging, 2020.
  14. Ucc: Uncertainty guided cross-head co-training for semi-supervised semantic segmentation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 9947–9956, 2022.
  15. Domain-adversarial training of neural networks. The Journal of Machine Learning Research, 17(1):2096–2030, 2016.
  16. Domain adaptation for medical image analysis: a survey. IEEE Transactions on Biomedical Engineering, 69(3):1173–1185, 2021.
  17. Deep residual learning for image recognition. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 770–778, 2016.
  18. Momentum contrast for unsupervised visual representation learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 9729–9738, 2020.
  19. Shape-aware semi-supervised 3d semantic segmentation for medical images. In Medical Image Computing and Computer-Assisted Intervention, pages 552–561. Springer, 2020a.
  20. Pln: Parasitic-like network for barely supervised medical image segmentation. IEEE Transactions on Medical Imaging, 42(3):582–593, 2022.
  21. Transformation-consistent self-ensembling model for semisupervised medical image segmentation. IEEE Transactions on Neural Networks and Learning Systems, 32(2):523–534, 2020b.
  22. Iomatch: Simplifying open-set semi-supervised learning with joint inliers and outliers utilization. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 15870–15879, 2023.
  23. Shape-aware meta-learning for generalizing prostate mri segmentation to unseen domains. In Medical Image Computing and Computer-Assisted Intervention, pages 475–485. Springer, 2020.
  24. Feddg: Federated domain generalization on medical image segmentation via episodic learning in continuous frequency space. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 1013–1023, 2021.
  25. Unsupervised domain adaptation for cardiac segmentation: Towards structure mutual information maximization. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 2588–2597, 2022.
  26. Semi-supervised medical image segmentation through dual-task consistency. In Proceedings of the AAAI Conference on Artificial Intelligence, pages 8801–8809, 2021.
  27. Caussl: Causality-inspired semi-supervised learning for medical image segmentation. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 21426–21437, 2023.
  28. U-net: Convolutional networks for biomedical image segmentation. In Medical Image Computing and Computer-Assisted Intervention, pages 234–241. Springer, 2015.
  29. Opportunities and challenges in using real-world data for health care. The Journal of Clinical Investigation, 130(2):565–574, 2020.
  30. From source to target and back: symmetric bi-directional adaptive gan. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 8099–8108, 2018.
  31. Inconsistency-aware uncertainty estimation for semi-supervised medical image segmentation. IEEE Transactions on Medical Imaging, 41(3):608–620, 2021.
  32. A clinically applicable deep-learning model for detecting intracranial aneurysm in computed tomography angiography images. Nature Communications, 11(1):6090, 2020.
  33. Fixmatch: Simplifying semi-supervised learning with consistency and confidence. Advances in Neural Information Processing Systems, 33:596–608, 2020.
  34. Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results. Advances in Neural Information Processing Systems, 30, 2017.
  35. Learning to adapt structured output space for semantic segmentation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 7472–7481, 2018.
  36. Fixmatchseg: Fixing fixmatch for semi-supervised semantic segmentation. arXiv preprint arXiv:2208.00400, 2022.
  37. Separated contrastive learning for organ-at-risk and gross-tumor-volume segmentation with limited annotation. In Proceedings of the AAAI Conference on Artificial Intelligence, pages 2459–2467, 2022.
  38. Semi-supervised learning by augmented distribution alignment. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 1466–1475, 2019.
  39. Dofe: Domain-oriented feature embedding for generalizable fundus image segmentation on unseen datasets. IEEE Transactions on Medical Imaging, 39(12):4237–4248, 2020.
  40. Exploring smoothness and class-separation for semi-supervised medical image segmentation. In Medical Image Computing and Computer-Assisted Intervention, pages 34–43. Springer, 2022.
  41. Fda: Fourier domain adaptation for semantic segmentation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 4085–4095, 2020.
  42. Simcvd: Simple contrastive voxel-wise representation distillation for semi-supervised medical image segmentation. IEEE Transactions on Medical Imaging, 41(9):2228–2237, 2022.
  43. Uncertainty-aware self-ensembling model for semi-supervised 3d left atrium segmentation. In Medical Image Computing and Computer-Assisted Intervention, pages 605–613. Springer, 2019.
  44. Cutmix: Regularization strategy to train strong classifiers with localizable features. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 6023–6032, 2019.
  45. mixup: Beyond empirical risk minimization. arXiv preprint arXiv:1710.09412, 2017.
  46. Collaborative unsupervised domain adaptation for medical image diagnosis. IEEE Transactions on Image Processing, 29:7834–7844, 2020.
  47. Le-uda: Label-efficient unsupervised domain adaptation for medical image segmentation. IEEE Transactions on Medical Imaging, 42(3):633–646, 2022.
  48. Rectifying pseudo label learning via uncertainty estimation for domain adaptive semantic segmentation. International Journal of Computer Vision, 129(4):1106–1120, 2021.
  49. Xiahai Zhuang et al. Challenges and methodologies of fully automatic whole heart segmentation: a review. Journal of Healthcare Engineering, 4:371–407, 2013.
Citations (3)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets