Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
102 tokens/sec
GPT-4o
59 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
6 tokens/sec
GPT-4.1 Pro
50 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Unsupervised Federated Domain Adaptation for Segmentation of MRI Images (2401.02941v2)

Published 2 Jan 2024 in cs.CV and cs.AI

Abstract: Automatic semantic segmentation of magnetic resonance imaging (MRI) images using deep neural networks greatly assists in evaluating and planning treatments for various clinical applications. However, training these models is conditioned on the availability of abundant annotated data to implement the end-to-end supervised learning procedure. Even if we annotate enough data, MRI images display considerable variability due to factors such as differences in patients, MRI scanners, and imaging protocols. This variability necessitates retraining neural networks for each specific application domain, which, in turn, requires manual annotation by expert radiologists for all new domains. To relax the need for persistent data annotation, we develop a method for unsupervised federated domain adaptation using multiple annotated source domains. Our approach enables the transfer of knowledge from several annotated source domains to adapt a model for effective use in an unannotated target domain. Initially, we ensure that the target domain data shares similar representations with each source domain in a latent embedding space, modeled as the output of a deep encoder, by minimizing the pair-wise distances of the distributions for the target domain and the source domains. We then employ an ensemble approach to leverage the knowledge obtained from all domains. We provide theoretical analysis and perform experiments on the MICCAI 2016 multi-site dataset to demonstrate our method is effective.

PDF HTML Abstract
Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Bookmark Chat Bubble Oval Streamline Icon: https://streamlinehq.com Chat (Pro)
Definition Search Book Streamline Icon: https://streamlinehq.com
References (74)
  1. Unsupervised domain adaptation with optimal transport in multi-site segmentation of multiple sclerosis lesions from mri data. Frontiers in computational neuroscience, 14:19, 2020.
  2. Context aware 3d unet for brain tumor segmentation. In Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries: 6th International Workshop, BrainLes 2020, Held in Conjunction with MICCAI 2020, Lima, Peru, October 4, 2020, Revised Selected Papers, Part I 6, pp.  207–218. Springer, 2021.
  3. Olva: O ptimal l atent v ector a lignment for unsupervised domain adaptation in medical image segmentation. In International Conference on Medical Image Computing and Computer-Assisted Intervention, pp.  261–271. Springer, 2021.
  4. Aiding the diagnosis of diabetic and hypertensive retinopathy using artificial intelligence-based semantic segmentation. Journal of clinical medicine, 8(9):1446, 2019.
  5. Deepjdot: Deep joint distribution optimal transport for unsupervised domain adaptation. In Proceedings of the European Conference on Computer Vision (ECCV), pp.  447–463, 2018.
  6. Unsupervised domain adaptation for semantic segmentation of urban scenes. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp.  0–0, 2019.
  7. Semantic segmentation with second-order pooling. In Computer Vision–ECCV 2012: 12th European Conference on Computer Vision, Florence, Italy, October 7-13, 2012, Proceedings, Part VII 12, pp.  430–443. Springer, 2012.
  8. Multiple sclerosis lesions segmentation from multiple experts: The miccai 2016 challenge dataset. Neuroimage, 244:118589, 2021.
  9. An optimized blockwise nonlocal means denoising filter for 3-d magnetic resonance images. IEEE transactions on medical imaging, 27(4):425–441, 2008.
  10. Bidirectional cross-modality unsupervised domain adaptation using generative adversarial networks for cardiac image segmentation. Computers in Biology and Medicine, 136:104726, 2021.
  11. Margin-aware adversarial domain adaptation with optimal transport. In Thirty-seventh International Conference on Machine Learning, 2020.
  12. Medical image segmentation based on u-net: A review. Journal of Imaging Science & Technology, 64(2), 2020.
  13. mdalu: Multi-source domain adaptation and label unification with partial datasets. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pp.  8876–8885, 2021.
  14. Generative adversarial nets. In Advances in Neural Information Processing Systems, pp. 2672–2680, 2014.
  15. Multi-source domain adaptation with mixture of experts. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pp.  4694–4703, 2018.
  16. Swin unetr: Swin transformers for semantic segmentation of brain tumors in mri images. In International MICCAI Brainlesion Workshop, pp.  272–284. Springer, 2021.
  17. Multi-source domain adaptation with collaborative learning for semantic segmentation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp.  11008–11017, 2021.
  18. Cycada: Cycle-consistent adversarial domain adaptation. In International conference on machine learning, pp. 1989–1998. PMLR, 2018.
  19. Adversarial learning for semi-supervised semantic segmentation. arXiv preprint arXiv:1802.07934, 2018.
  20. Brain tumor segmentation and radiomics survival prediction: Contribution to the brats 2017 challenge. In Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries: Third International Workshop, BrainLes 2017, Held in Conjunction with MICCAI 2017, Quebec City, QC, Canada, September 14, 2017, Revised Selected Papers 3, pp.  287–297. Springer, 2018.
  21. Review of mri-based brain tumor image segmentation using deep learning methods. Procedia Computer Science, 102:317–324, 2016.
  22. Domain adaptation for biomedical image segmentation using adversarial training. In 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018), pp.  554–558. IEEE, 2018.
  23. Unsupervised domain adaptation for training event-based networks using contrastive learning and uncorrelated conditioning. In Proceedings of the IEEE/CVF international conference on computer vision, 2023.
  24. Integration of interventional mri with computer-assisted surgery. Journal of Magnetic Resonance Imaging, 13(1):69–77, 2001.
  25. Brain tumor prediction on mr images with semantic segmentation by using deep learning network and 3d imaging of tumor region. Biomedical Signal Processing and Control, 66:102458, 2021.
  26. Automated quantitative tumour response assessment of mri in neuro-oncology with artificial neural networks: a multicentre, retrospective study. The Lancet Oncology, 20(5):728–740, 2019.
  27. Impact of scanner hardware and imaging protocol on image quality and compartment volume precision in the adni cohort. Neuroimage, 49(3):2123–2133, 2010.
  28. Interactive surface-guided segmentation of brain mri data. Computers in Biology and Medicine, 39(12):1153–1160, 2009.
  29. Extracting relationships by multi-domain matching. In S. Bengio, H. Wallach, H. Larochelle, K. Grauman, N. Cesa-Bianchi, and R. Garnett (eds.), Advances in Neural Information Processing Systems, volume 31. Curran Associates, Inc., 2018. URL https://proceedings.neurips.cc/paper/2018/file/2fd0fd3efa7c4cfb034317b21f3c2d93-Paper.pdf.
  30. A new brain mri image segmentation strategy based on wavelet transform and k-means clustering. In 2015 IEEE International Conference on Signal Processing, Communications and Computing (ICSPCC), pp.  1–4. IEEE, 2015.
  31. Fully convolutional networks for semantic segmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp.  3431–3440, 2015a.
  32. Learning transferable features with deep adaptation networks. In Proceedings of International Conference on Machine Learning, pp.  97–105, 2015b.
  33. Deep transfer learning with joint adaptation networks. In Doina Precup and Yee Whye Teh (eds.), Proceedings of the 34th International Conference on Machine Learning, volume 70 of Proceedings of Machine Learning Research, pp.  2208–2217. PMLR, 06–11 Aug 2017. URL http://proceedings.mlr.press/v70/long17a.html.
  34. Semantic segmentation using adversarial networks. In NIPS Workshop on Adversarial Training, 2016.
  35. Attention res-unet with guided decoder for semantic segmentation of brain tumors. Biomedical Signal Processing and Control, 71:103077, 2022.
  36. UMAP: Uniform manifold approximation and projection. Journal of Open Source Software, 3(29):861, 2018.
  37. Minimal-entropy correlation alignment for unsupervised deep domain adaptation. In ICLR, 2018.
  38. Moment matching for multi-source domain adaptation. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pp.  1406–1415, 2019.
  39. Unet-vgg16 with transfer learning for mri-based brain tumor segmentation. TELKOMNIKA (Telecommunication Computing Electronics and Control), 18(3):1310–1318, 2020.
  40. Wasserstein barycenter and its application to texture mixing. In International Conference on Scale Space and Variational Methods in Computer Vision, pp.  435–446. Springer, 2011.
  41. A. Redko, I.and Habrard and M. Sebban. Theoretical analysis of domain adaptation with optimal transport. In Joint European Conference on Machine Learning and Knowledge Discovery in Databases, pp.  737–753. Springer, 2017.
  42. U-net: Convolutional networks for biomedical image segmentation. In Medical Image Computing and Computer-Assisted Intervention–MICCAI 2015: 18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part III 18, pp.  234–241. Springer, 2015a.
  43. U-net: Convolutional networks for biomedical image segmentation, 2015b.
  44. Mohammad Rostami. Lifelong domain adaptation via consolidated internal distribution. Advances in neural information processing systems, 34:11172–11183, 2021a.
  45. Mohammad Rostami. Transfer Learning Through Embedding Spaces. CRC Press, 2021b.
  46. Mohammad Rostami. Increasing model generalizability for unsupervised visual domain adaptation. In Conference on Lifelong Learning Agents, pp.  281–293. PMLR, 2022.
  47. Cognitively inspired learning of incremental drifting concepts. In IJCAI, 2022.
  48. Overcoming concept shift in domain-aware settings through consolidated internal distributions. In Proceedings of the AAAI conference on artificial intelligence, volume 37, pp.  9623–9631, 2023.
  49. A crowdsourcing triage algorithm for geopolitical event forecasting. In Proceedings of the 12th ACM Conference on Recommender Systems, pp.  377–381, 2018.
  50. Deep transfer learning for few-shot sar image classification. Remote Sensing, 11(11):1374, 2019a.
  51. Sar image classification using few-shot cross-domain transfer learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp.  0–0, 2019b.
  52. Complementary learning for overcoming catastrophic forgetting using experience replay. In Proceedings of the 28th International Joint Conference on Artificial Intelligence, pp.  3339–3345. AAAI Press, 2019c.
  53. Generative continual concept learning. In AAAI, pp.  5545–5552, 2020.
  54. Domain adaptation for sentiment analysis using robust internal representations. In Findings of the Association for Computational Linguistics: EMNLP 2023, pp.  11484–11498, 2023.
  55. Generate to adapt: Aligning domains using generative adversarial networks. In CVPR, 2018a.
  56. Learning from synthetic data: Addressing domain shift for semantic segmentation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.  3752–3761, 2018b.
  57. Segmentation of mri brain data using a haptic device. In Proceedings of the 10th IEEE International Conference on Information Technology and Applications in Biomedicine, pp.  1–4. IEEE, 2010.
  58. Unsupervised model adaptation for continual semantic segmentation. In Proceedings of the AAAI conference on artificial intelligence, volume 35, pp.  2593–2601, 2021.
  59. Privacy preserving domain adaptation for semantic segmentation of medical images. In BMVC, 2022a.
  60. Secure domain adaptation with multiple sources. Transactions on Machine Learning Research, 2022b.
  61. Rethinking adversarial domain adaptation: Orthogonal decomposition for unsupervised domain adaptation in medical image segmentation. Medical Image Analysis, 82:102623, 2022.
  62. Standardgan: Multi-source domain adaptation for semantic segmentation of very high resolution satellite images by data standardization. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp.  192–193, 2020.
  63. Adversarial discriminative domain adaptation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.  7167–7176, 2017.
  64. Your classifier can secretly suffice multi-source domain adaptation. In NeurIPS, 2020.
  65. Characterizing and avoiding negative transfer. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp.  11293–11302, 2019.
  66. Semantic segmentation guided detector for segmentation, classification, and lesion mapping of acute ischemic stroke in mri images. NeuroImage: Clinical, 35:103044, 2022.
  67. Domain aggregation networks for multi-source domain adaptation. In Hal Daumé III and Aarti Singh (eds.), Proceedings of the 37th International Conference on Machine Learning, volume 119 of Proceedings of Machine Learning Research, pp.  10214–10224. PMLR, 13–18 Jul 2020. URL http://proceedings.mlr.press/v119/wen20b.html.
  68. Reliable weighted optimal transport for unsupervised domain adaptation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp.  4394–4403, 2020.
  69. Deep cocktail network: Multi-source unsupervised domain adaptation with category shift. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.  3964–3973, 2018.
  70. Self-ensembling attention networks: Addressing domain shift for semantic segmentation. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 33, pp.  5581–5588, 2019.
  71. Multi-source domain adaptation for semantic segmentation. Advances in neural information processing systems, 32, 2019.
  72. Multi-source distilling domain adaptation. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 34, pp.  12975–12983, 2020.
  73. Aligning domain-specific distribution and classifier for cross-domain classification from multiple sources. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 33, pp.  5989–5996, 2019.
  74. Unsupervised domain adaptation for semantic segmentation via class-balanced self-training. In Proceedings of the European conference on computer vision (ECCV), pp.  289–305, 2018.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (3)
  1. Navapat Nananukul (4 papers)
  2. Hamid Soltanian-zadeh (18 papers)
  3. Mohammad Rostami (64 papers)