M-GenSeg: Domain Adaptation For Target Modality Tumor Segmentation With Annotation-Efficient Supervision
Not on the map. Why?
Abstract (arXiv)
Automated medical image segmentation using deep neural networks typically requires substantial supervised training. However, these models fail to generalize well across different imaging modalities. This shortcoming, amplified by the limited availability of expert annotated data, has been hampering the deployment of such methods at a larger scale across modalities. To address these issues, we propose M-GenSeg, a new semi-supervised generative training strategy for cross-modality tumor segmentation on unpaired bi-modal datasets. With the addition of known healthy images, an unsupervised objective encourages the model to disentangling tumors from the background, which parallels the segmentation task. Then, by teaching the model to convert images across modalities, we leverage available pixel-level annotations from the source modality to enable segmentation in the unannotated target modality. We evaluated the performance on a brain tumor segmentation dataset composed of four different contrast sequences from the public BraTS 2020 challenge data. We report consistent improvement in Dice scores over state-of-the-art domain-adaptive baselines on the unannotated target modality. Unlike the prior art, M-GenSeg also introduces the ability to train with a partially annotated source modality.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 18 of its 31 references that are in the map. First posted on arXiv 14 Dec 2022.
Builds on
18 of 31 references.
References · 18
- 2021TransUNet: Transformers Make Strong Encoders for Medical Image Segmentationcited by 1,552
- 2018Attention U-Net: Learning Where to Look for the Pancreascited by 1,420
- 2017CyCADA: Cycle-Consistent Adversarial Domain Adaptationcited by 1,079
- 2017Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networkscited by 707
- 2018Identifying the Best Machine Learning Algorithms for Brain Tumor Segmentation, Progression Assessment, and Overall Survival Prediction in the BRATS Challengecited by 508
- 2021Domain Adaptation for Medical Image Analysis: A Surveycited by 351
- 2018Medical Image Synthesis for Data Augmentation and Anonymization using Generative Adversarial Networkscited by 146
- 2016The Importance of Skip Connections in Biomedical Image Segmentationcited by 126
- 2019Synergistic Image and Feature Adaptation: Towards Cross-Modality Domain Adaptation for Medical Image Segmentationcited by 121
- 2018SynSeg-Net: Synthetic Segmentation Without Target Modality Ground Truthcited by 68
- 2022CrossMoDA 2021 challenge: Benchmark of Cross-Modality Domain Adaptation techniques for Vestibular Schwannoma and Cochlea Segmentationcited by 58
- 2018Task Driven Generative Modeling for Unsupervised Domain Adaptation: Application to X-ray Image Segmentationcited by 49
6 more
- 2018Learning Data Augmentation for Brain Tumor Segmentation with Coarse-to-Fine Generative Adversarial Networkscited by 15
- 2021Anatomy-Constrained Contrastive Learning for Synthetic Segmentation without Ground-truthcited by 9
- 2019Unified Attentional Generative Adversarial Network for Brain Tumor Segmentation From Multimodal Unpaired Imagescited by 7
- 2019Towards annotation-efficient segmentation via image-to-image translationcited by 6
- 2019Unsupervised Multi-Domain Multimodal Image-to-Image Translation with Explicit Domain-Constrained Disentanglementcited by 4
- 2021Multi-Slice Low-Rank Tensor Decomposition Based Multi-Atlas Segmentation: Application to Automatic Pathological Liver CT Segmentationcited by 4
Built on by
Citing papers per year: 2025: 1.
1 paper.