mlsanityData to 14 Oct 2026

Unsupervised Federated Domain Adaptation for Segmentation of MRI Images

arXiv 2401.02941 ↗First posted 2 Jan 2024cs.CV cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 34 of its 72 references that are in the map. First posted on arXiv 2 Jan 2024.

Builds on

34 of 72 references.

References · 34

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  2. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,859
  3. 2018Moment Matching for Multi-Source Domain Adaptationcited by 1,331
  4. 2015Learning Transferable Features with Deep Adaptation Networkscited by 1,329
  5. 2017Adversarial Discriminative Domain Adaptationcited by 1,311
  6. 2017CyCADA: Cycle-Consistent Adversarial Domain Adaptationcited by 1,082
  7. 2022Swin UNETR: Swin Transformers for Semantic Segmentation of Brain Tumors in MRI Imagescited by 830
  8. 2016Deep Transfer Learning with Joint Adaptation Networkscited by 612
  9. 2018Characterizing and Avoiding Negative Transfercited by 229
  10. 2018DeepJDOT: Deep Joint Distribution Optimal Transport for Unsupervised Domain Adaptationcited by 214
  11. 2017Generate To Adapt: Aligning Domains using Generative Adversarial Networkscited by 183
  12. 2018Adversarial Learning for Semi-Supervised Semantic Segmentationcited by 173
22 more
  1. 2018Deep Cocktail Network: Multi-source Unsupervised Domain Adaptation with Category Shiftcited by 109
  2. 2016Theoretical Analysis of Domain Adaptation with Optimal Transportcited by 105
  3. 2019Multi-source Domain Adaptation for Semantic Segmentationcited by 74
  4. 2016Semantic Segmentation using Adversarial Networkscited by 73
  5. 2019Multi-source Distilling Domain Adaptationcited by 73
  6. 2017Minimal-Entropy Correlation Alignment for Unsupervised Deep Domain Adaptationcited by 71
  7. 2018Multi-Source Domain Adaptation with Mixture of Expertscited by 62
  8. 2018Brain Tumor Segmentation and Radiomics Survival Prediction: Contribution to the BRATS 2017 Challengecited by 56
  9. 2019Complementary Learning for Overcoming Catastrophic Forgetting Using Experience Replaycited by 51
  10. 2021Multi-Source Domain Adaptation with Collaborative Learning for Semantic Segmentationcited by 44
  11. 2020Unsupervised Model Adaptation for Continual Semantic Segmentationcited by 42
  12. 2021Your Classifier can Secretly Suffice Multi-Source Domain Adaptationcited by 42
  13. 2022Aligning Domain-specific Distribution and Classifier for Cross-domain Classification from Multiple Sourcescited by 42
  14. 2019Domain Aggregation Networks for Multi-Source Domain Adaptationcited by 37
  15. 2019Generative Continual Concept Learningcited by 26
  16. 2020StandardGAN: Multi-source Domain Adaptation for Semantic Segmentation of Very High Resolution Satellite Images by Data Standardizationcited by 23
  17. 2020Overcoming Concept Shift in Domain-Aware Settings through Consolidated Internal Distributionscited by 21
  18. 2020mDALU: Multi-Source Domain Adaptation and Label Unification with Partial Datasetscited by 19
  19. 2021Cognitively Inspired Learning of Incremental Drifting Conceptscited by 16
  20. 2023Unsupervised Domain Adaptation for Training Event-Based Networks Using Contrastive Learning and Uncorrelated Conditioningcited by 14
  21. 2021Secure Domain Adaptation with Multiple Sourcescited by 12
  22. 2020Context Aware 3D UNet for Brain Tumor Segmentationcited by 4

Built on by

Not cited yet.