SlideShare a Scribd company logo
1 of 17
Download to read offline
MT-UDA: Towards Unsupervised Cross-modality Medical Image
Segmentation with Limited Source Labels
Ziyuan Zhao1,2, Kaixin Xu2, Shumeng Li1,2, Zeng Zeng2, Cuntai Guan1
Presenter: Zhao Ziyuan (G2104205L)
1 Nanyang Technological University 2 Institute for Infocomm Research, A*STAR
Th-S2: Image Segmentation + Domain Adaptation # 678
Introduction – Medical Image Segmentation
- Segmentation in medical physics plays a crucial role in medical image analysis (MedIA)
- For instance, left atrium (LA) segmentation can provide a pre-operative assessment of its anatomy,
which is essential for treating various cardiovascular diseases, such as atrial fibrillation
- Deep learning has been widely used for medical image segmentation
Left Atrial Cavity 3D LA Visualization
2018 Atrial Segmentation Challenge. https://atriaseg2018.cardiacatlas.org/
Challenge (1) – Label Scarcity
- DCNNs are data-hungry and require large amounts of well-annotated data.
- Annotating medical images is laborious, expensive, and requires human expertise → Label Scarcity
Time & money
consuming
Knowledge-driven
Labor-intensive
Image DCNNs Segmentation map
Challenge (2) – Domain Shift
- In real-world clinical scenarios, medical images are acquired with different physical principles and
modalities, e.g., MRI & CT→ different visual appearance & distribution (Domain Gap)
- DCNNs suffer from severe performance degradation when domain shift (e.g., CT → MRI)
Cardiac Label
Cardiac CT
Source Domain
Annotate
DCNNs
Transfer
Cardiac MR
Feed
Domain Gap
Target Domain
Existing Work – Unsupervised Domain Adaptation
- Image adaptation – Cycle GAN (2017)
- Feature adaptation – ADDA (2017)
- Sequentially combine two adaptive strategies – CyCADA (2018)
- Synergistic Image and Feature Adaptation – SIFA (2019, 2020)
Cardiac CT Cardiac MR
Domain Gap
CycleGAN [1]
ADDA [2]
Cycada [3]
SIFA [4]
[1] Zhu, Jun-Yan, et al. "Unpaired image-to-image translation using cycle-consistent adversarial networks." ICCV 2017
[2] Tzeng, Eric, et al. "Adversarial discriminative domain adaptation." CVPR 2017.
[3] Hoffman, Judy, et al. "Cycada: Cycle-consistent adversarial domain adaptation.“ ICML 2018
[4] Chen, Cheng, et al. "Unsupervised bidirectional cross-modality adaptation via deeply synergistic image and feature alignment for medical image segmentation." TMI 2020
Source Domain Target Domain
Problem – Source Label Scarcity
- Despite the success of adversarial learning in UDA, these methods heavily rely on abundant source
labels.
- Become sub-optimal when only limited source labels are available in clinical deployment.
- Motivates us to study a challenging UDA scenario – source label scarcity
Source Label Scarcity
Cardiac CT Cardiac MR
Domain Gap
Source Domain Target Domain
Less
Annotations
Lower
Performance
Motivation – SSL + UDA
- Image-level adaptation → generates a lot of synthetic images with abundant information, which can be
leveraged for semi-supervised learning
- Appearance consistency → synthetic and real images from the same domain maintain a similar visual
appearance
- Structural consistency → transformed images should have the same structural information as the
original ones
Zhao, Ziyuan, et al. "MT-UDA: Towards Unsupervised Cross-modality Medical Image Segmentation with Limited Source Labels." MICCAI 2021
SSL
Labeled data
Performance
Number of labeled data
DCNNs
Source Domain
Target Domain
Style Transfer
Method – MT-UDA
- Investigate the feasibility of integrating SSL into UDA under source label scarcity
- Develop a label-efficient UDA framework based on mean teacher (MT) to explore the knowledge from
both domains
Zhao, Ziyuan, et al. "MT-UDA: Towards Unsupervised Cross-modality Medical Image Segmentation with Limited Source Labels." MICCAI 2021
Method (1)– Dual Cycle Alignment Module
- Generate synthetic samples for two domains using generative adversarial networks
- Synthesize source-like domain images and target-like domain images via adversarial learning
Zhao, Ziyuan, et al. "MT-UDA: Towards Unsupervised Cross-modality Medical Image Segmentation with Limited Source Labels." MICCAI 2021
Method (2)– Semantic Knowledge Transfer
- Appearance consistency → synthetic and real images from the same domain maintain a similar visual
appearance
- Employ the mean teacher (MT) model to distill the intra-domain semantic knowledge by forcing the
prediction consistency
Zhao, Ziyuan, et al. "MT-UDA: Towards Unsupervised Cross-modality Medical Image Segmentation with Limited Source Labels." MICCAI 2021
Method (3)– Structural Knowledge Transfer
- Structural consistency → transformed images should have the same structural information as the
original ones
- Propose a teacher model for keeping structural consistency between predictions of source images and
corresponding synthetic target images
Zhao, Ziyuan, et al. "MT-UDA: Towards Unsupervised Cross-modality Medical Image Segmentation with Limited Source Labels." MICCAI 2021
Experiments
- Dataset
- Multi-Modality Whole Heart Segmentation (MM-WHS) 2017 dataset
- Unpaired 20 MR and 20 CT volumes with ground truth masks
- Data preprocessing
- MR → source domain, CT → target domain
- SIFA setting (-16) → 16: 4 random split for train / val
- Our setting (-4)→ 4 MR volumes are labelled for UDA under source label scarcity
- Images were cropped into the size of 256 x 256
- Implementation details
- Test on fake MR images generated from CT
- Backbone: U-Net
- Supervised loss: Dice + Cross-entropy
- Total loss:
Zhao, Ziyuan, et al. "MT-UDA: Towards Unsupervised Cross-modality Medical Image Segmentation with Limited Source Labels." MICCAI 2021
Results (1) – Quantitative Comparison
- Degraded performance on target domain when using 4 labeled source domain scans
- MT and UA-MT can help improve the segmentation performance on target domain
- Demonstrate the feasibility of integrating SSL into UDA for label-efficient UDA
suffix −4 or −16
# labelled source scans
used for training
[1] Dou, Qi, et al. "Unsupervised cross-modality domain adaptation of convnets for biomedical image segmentations with adversarial loss." IJCAI 2018
[2] Chen, Cheng, et al. "Synergistic image and feature adaptation: Towards cross-modality domain adaptation for medical image segmentation." AAAI 2019
[3] Chen, Cheng, et al. "Unsupervised bidirectional cross-modality adaptation via deeply synergistic image and feature alignment for medical image segmentation." TMI 2020
[4] Tarvainen, Antti, and Harri Valpola. "Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results.“NIPS 2017
[5] Yu, Lequan, et al. "Uncertainty-aware self-ensembling model for semi-supervised 3D left atrium segmentation.“ MICCAI 2019
Results (2) – Qualitative Comparison
- It is observed that our method can generate more reliable masks with fewer false positives
Zhao, Ziyuan, et al. "MT-UDA: Towards Unsupervised Cross-modality Medical Image Segmentation with Limited Source Labels." MICCAI 2021
Results (3) – Ablation Study
- Remove one of the teacher models, separately
- W/o semantic knowledge transfer (MT-UDA-NS)
- W/o structural knowledge transfer (MTUDA-NT)
- Replace structural consistency loss with MSE loss (MT-UDA-NS-MSE)
Zhao, Ziyuan, et al. "MT-UDA: Towards Unsupervised Cross-modality Medical Image Segmentation with Limited Source Labels." MICCAI 2021
Conclusions
- Study a practical, challenging, and different UDA setting from the past, where only limited source labels
are accessible → Source Label Scarcity
- Investigate the feasibility of integrating SSL into UDA under source label scarcity
- Propose a label-efficient UDA framework for cross-modality medical image segmentation
- Leverage intra-domain semantic knowledge and exploit inter-domain structural knowledge
concurrently, thereby mitigating both the domain discrepancy and source label scarcity.
Zhao, Ziyuan, et al. "MT-UDA: Towards Unsupervised Cross-modality Medical Image Segmentation with Limited Source Labels." MICCAI 2021
Thanks
Zhao_Ziyuan@i2r.a-star.edu.sg

More Related Content

Similar to [MICCAI 2021] MT-UDA: Towards unsupervised cross-modality medical image segmentation with limited source labels

Development and Comparison of Image Fusion Techniques for CT&MRI Images
Development and Comparison of Image Fusion Techniques for CT&MRI ImagesDevelopment and Comparison of Image Fusion Techniques for CT&MRI Images
Development and Comparison of Image Fusion Techniques for CT&MRI ImagesIJERA Editor
 
IRJET - Fusion of CT and MRI for the Detection of Brain Tumor by SWT and Prob...
IRJET - Fusion of CT and MRI for the Detection of Brain Tumor by SWT and Prob...IRJET - Fusion of CT and MRI for the Detection of Brain Tumor by SWT and Prob...
IRJET - Fusion of CT and MRI for the Detection of Brain Tumor by SWT and Prob...IRJET Journal
 
TL-DTC_Michael Ravoo.pdf
TL-DTC_Michael Ravoo.pdfTL-DTC_Michael Ravoo.pdf
TL-DTC_Michael Ravoo.pdfFlorinSpainhour
 
MRI Image Segmentation Using Gradient Based Watershed Transform In Level Set ...
MRI Image Segmentation Using Gradient Based Watershed Transform In Level Set ...MRI Image Segmentation Using Gradient Based Watershed Transform In Level Set ...
MRI Image Segmentation Using Gradient Based Watershed Transform In Level Set ...IJERA Editor
 
Literature Survey on Detection of Brain Tumor from MRI Images
Literature Survey on Detection of Brain Tumor from MRI Images Literature Survey on Detection of Brain Tumor from MRI Images
Literature Survey on Detection of Brain Tumor from MRI Images IOSR Journals
 
Fuzzy k c-means clustering algorithm for medical image
Fuzzy k c-means clustering algorithm for medical imageFuzzy k c-means clustering algorithm for medical image
Fuzzy k c-means clustering algorithm for medical imageAlexander Decker
 
IRJET- Segmentation and Visualization in Medical Image Processing: A Review
IRJET- Segmentation and Visualization in Medical Image Processing: A ReviewIRJET- Segmentation and Visualization in Medical Image Processing: A Review
IRJET- Segmentation and Visualization in Medical Image Processing: A ReviewIRJET Journal
 
Classification of MR medical images Based Rough-Fuzzy KMeans
Classification of MR medical images Based Rough-Fuzzy KMeansClassification of MR medical images Based Rough-Fuzzy KMeans
Classification of MR medical images Based Rough-Fuzzy KMeansIOSRJM
 
3D Segmentation of Brain Tumor Imaging
3D Segmentation of Brain Tumor Imaging3D Segmentation of Brain Tumor Imaging
3D Segmentation of Brain Tumor ImagingIJAEMSJORNAL
 
IRJET- A Novel Segmentation Technique for MRI Brain Tumor Images
IRJET- A Novel Segmentation Technique for MRI Brain Tumor ImagesIRJET- A Novel Segmentation Technique for MRI Brain Tumor Images
IRJET- A Novel Segmentation Technique for MRI Brain Tumor ImagesIRJET Journal
 
Alzheimer S Disease Brain MRI Classification Challenges And Insights
Alzheimer S Disease Brain MRI Classification  Challenges And InsightsAlzheimer S Disease Brain MRI Classification  Challenges And Insights
Alzheimer S Disease Brain MRI Classification Challenges And InsightsJoe Andelija
 
IRJET- Fusion based Brain Tumor Detection
IRJET- Fusion based Brain Tumor DetectionIRJET- Fusion based Brain Tumor Detection
IRJET- Fusion based Brain Tumor DetectionIRJET Journal
 
IRJET- Brain MRI Image Processing & Prediction of Cancer Stage Including ...
IRJET-  	  Brain MRI Image Processing & Prediction of Cancer Stage Including ...IRJET-  	  Brain MRI Image Processing & Prediction of Cancer Stage Including ...
IRJET- Brain MRI Image Processing & Prediction of Cancer Stage Including ...IRJET Journal
 
DIRECTIONAL CLASSIFICATION OF BRAIN TUMOR IMAGES FROM MRI USING CNN-BASED DEE...
DIRECTIONAL CLASSIFICATION OF BRAIN TUMOR IMAGES FROM MRI USING CNN-BASED DEE...DIRECTIONAL CLASSIFICATION OF BRAIN TUMOR IMAGES FROM MRI USING CNN-BASED DEE...
DIRECTIONAL CLASSIFICATION OF BRAIN TUMOR IMAGES FROM MRI USING CNN-BASED DEE...IRJET Journal
 
An efficient convolutional neural network-based classifier for an imbalanced ...
An efficient convolutional neural network-based classifier for an imbalanced ...An efficient convolutional neural network-based classifier for an imbalanced ...
An efficient convolutional neural network-based classifier for an imbalanced ...IAESIJAI
 
A Dualistic Sub-Image Histogram Equalization Based Enhancement and Segmentati...
A Dualistic Sub-Image Histogram Equalization Based Enhancement and Segmentati...A Dualistic Sub-Image Histogram Equalization Based Enhancement and Segmentati...
A Dualistic Sub-Image Histogram Equalization Based Enhancement and Segmentati...inventy
 
A Survey On Identification Of Multiple Sclerosis Lesions From Brain MRI
A Survey On Identification Of Multiple Sclerosis Lesions From Brain MRIA Survey On Identification Of Multiple Sclerosis Lesions From Brain MRI
A Survey On Identification Of Multiple Sclerosis Lesions From Brain MRIJanelle Martinez
 
Automatic whole-body bone scan image segmentation based on constrained local ...
Automatic whole-body bone scan image segmentation based on constrained local ...Automatic whole-body bone scan image segmentation based on constrained local ...
Automatic whole-body bone scan image segmentation based on constrained local ...journalBEEI
 
IRJET - An Efficient Approach for Multi-Modal Brain Tumor Classification usin...
IRJET - An Efficient Approach for Multi-Modal Brain Tumor Classification usin...IRJET - An Efficient Approach for Multi-Modal Brain Tumor Classification usin...
IRJET - An Efficient Approach for Multi-Modal Brain Tumor Classification usin...IRJET Journal
 

Similar to [MICCAI 2021] MT-UDA: Towards unsupervised cross-modality medical image segmentation with limited source labels (20)

Development and Comparison of Image Fusion Techniques for CT&MRI Images
Development and Comparison of Image Fusion Techniques for CT&MRI ImagesDevelopment and Comparison of Image Fusion Techniques for CT&MRI Images
Development and Comparison of Image Fusion Techniques for CT&MRI Images
 
IRJET - Fusion of CT and MRI for the Detection of Brain Tumor by SWT and Prob...
IRJET - Fusion of CT and MRI for the Detection of Brain Tumor by SWT and Prob...IRJET - Fusion of CT and MRI for the Detection of Brain Tumor by SWT and Prob...
IRJET - Fusion of CT and MRI for the Detection of Brain Tumor by SWT and Prob...
 
TL-DTC_Michael Ravoo.pdf
TL-DTC_Michael Ravoo.pdfTL-DTC_Michael Ravoo.pdf
TL-DTC_Michael Ravoo.pdf
 
MRI Image Segmentation Using Gradient Based Watershed Transform In Level Set ...
MRI Image Segmentation Using Gradient Based Watershed Transform In Level Set ...MRI Image Segmentation Using Gradient Based Watershed Transform In Level Set ...
MRI Image Segmentation Using Gradient Based Watershed Transform In Level Set ...
 
M010128086
M010128086M010128086
M010128086
 
Literature Survey on Detection of Brain Tumor from MRI Images
Literature Survey on Detection of Brain Tumor from MRI Images Literature Survey on Detection of Brain Tumor from MRI Images
Literature Survey on Detection of Brain Tumor from MRI Images
 
Fuzzy k c-means clustering algorithm for medical image
Fuzzy k c-means clustering algorithm for medical imageFuzzy k c-means clustering algorithm for medical image
Fuzzy k c-means clustering algorithm for medical image
 
IRJET- Segmentation and Visualization in Medical Image Processing: A Review
IRJET- Segmentation and Visualization in Medical Image Processing: A ReviewIRJET- Segmentation and Visualization in Medical Image Processing: A Review
IRJET- Segmentation and Visualization in Medical Image Processing: A Review
 
Classification of MR medical images Based Rough-Fuzzy KMeans
Classification of MR medical images Based Rough-Fuzzy KMeansClassification of MR medical images Based Rough-Fuzzy KMeans
Classification of MR medical images Based Rough-Fuzzy KMeans
 
3D Segmentation of Brain Tumor Imaging
3D Segmentation of Brain Tumor Imaging3D Segmentation of Brain Tumor Imaging
3D Segmentation of Brain Tumor Imaging
 
IRJET- A Novel Segmentation Technique for MRI Brain Tumor Images
IRJET- A Novel Segmentation Technique for MRI Brain Tumor ImagesIRJET- A Novel Segmentation Technique for MRI Brain Tumor Images
IRJET- A Novel Segmentation Technique for MRI Brain Tumor Images
 
Alzheimer S Disease Brain MRI Classification Challenges And Insights
Alzheimer S Disease Brain MRI Classification  Challenges And InsightsAlzheimer S Disease Brain MRI Classification  Challenges And Insights
Alzheimer S Disease Brain MRI Classification Challenges And Insights
 
IRJET- Fusion based Brain Tumor Detection
IRJET- Fusion based Brain Tumor DetectionIRJET- Fusion based Brain Tumor Detection
IRJET- Fusion based Brain Tumor Detection
 
IRJET- Brain MRI Image Processing & Prediction of Cancer Stage Including ...
IRJET-  	  Brain MRI Image Processing & Prediction of Cancer Stage Including ...IRJET-  	  Brain MRI Image Processing & Prediction of Cancer Stage Including ...
IRJET- Brain MRI Image Processing & Prediction of Cancer Stage Including ...
 
DIRECTIONAL CLASSIFICATION OF BRAIN TUMOR IMAGES FROM MRI USING CNN-BASED DEE...
DIRECTIONAL CLASSIFICATION OF BRAIN TUMOR IMAGES FROM MRI USING CNN-BASED DEE...DIRECTIONAL CLASSIFICATION OF BRAIN TUMOR IMAGES FROM MRI USING CNN-BASED DEE...
DIRECTIONAL CLASSIFICATION OF BRAIN TUMOR IMAGES FROM MRI USING CNN-BASED DEE...
 
An efficient convolutional neural network-based classifier for an imbalanced ...
An efficient convolutional neural network-based classifier for an imbalanced ...An efficient convolutional neural network-based classifier for an imbalanced ...
An efficient convolutional neural network-based classifier for an imbalanced ...
 
A Dualistic Sub-Image Histogram Equalization Based Enhancement and Segmentati...
A Dualistic Sub-Image Histogram Equalization Based Enhancement and Segmentati...A Dualistic Sub-Image Histogram Equalization Based Enhancement and Segmentati...
A Dualistic Sub-Image Histogram Equalization Based Enhancement and Segmentati...
 
A Survey On Identification Of Multiple Sclerosis Lesions From Brain MRI
A Survey On Identification Of Multiple Sclerosis Lesions From Brain MRIA Survey On Identification Of Multiple Sclerosis Lesions From Brain MRI
A Survey On Identification Of Multiple Sclerosis Lesions From Brain MRI
 
Automatic whole-body bone scan image segmentation based on constrained local ...
Automatic whole-body bone scan image segmentation based on constrained local ...Automatic whole-body bone scan image segmentation based on constrained local ...
Automatic whole-body bone scan image segmentation based on constrained local ...
 
IRJET - An Efficient Approach for Multi-Modal Brain Tumor Classification usin...
IRJET - An Efficient Approach for Multi-Modal Brain Tumor Classification usin...IRJET - An Efficient Approach for Multi-Modal Brain Tumor Classification usin...
IRJET - An Efficient Approach for Multi-Modal Brain Tumor Classification usin...
 

More from Ziyuan Zhao

[IJCAI 2023] SemiGNN-PPI: Self-Ensembling Multi-Graph Neural Network for Effi...
[IJCAI 2023] SemiGNN-PPI: Self-Ensembling Multi-Graph Neural Network for Effi...[IJCAI 2023] SemiGNN-PPI: Self-Ensembling Multi-Graph Neural Network for Effi...
[IJCAI 2023] SemiGNN-PPI: Self-Ensembling Multi-Graph Neural Network for Effi...Ziyuan Zhao
 
[IJCAI 2023 - Poster] SemiGNN-PPI: Self-Ensembling Multi-Graph Neural Network...
[IJCAI 2023 - Poster] SemiGNN-PPI: Self-Ensembling Multi-Graph Neural Network...[IJCAI 2023 - Poster] SemiGNN-PPI: Self-Ensembling Multi-Graph Neural Network...
[IJCAI 2023 - Poster] SemiGNN-PPI: Self-Ensembling Multi-Graph Neural Network...Ziyuan Zhao
 
[BMVC 2022 - Spotlight] DA-CIL: Towards Domain Adaptive Class-Incremental 3D ...
[BMVC 2022 - Spotlight] DA-CIL: Towards Domain Adaptive Class-Incremental 3D ...[BMVC 2022 - Spotlight] DA-CIL: Towards Domain Adaptive Class-Incremental 3D ...
[BMVC 2022 - Spotlight] DA-CIL: Towards Domain Adaptive Class-Incremental 3D ...Ziyuan Zhao
 
[BMVC 2022] DA-CIL: Towards Domain Adaptive Class-Incremental 3D Object Detec...
[BMVC 2022] DA-CIL: Towards Domain Adaptive Class-Incremental 3D Object Detec...[BMVC 2022] DA-CIL: Towards Domain Adaptive Class-Incremental 3D Object Detec...
[BMVC 2022] DA-CIL: Towards Domain Adaptive Class-Incremental 3D Object Detec...Ziyuan Zhao
 
[ICIP 2022] ACT-NET: Asymmetric Co-Teacher Network for Semi-Supervised Memory...
[ICIP 2022] ACT-NET: Asymmetric Co-Teacher Network for Semi-Supervised Memory...[ICIP 2022] ACT-NET: Asymmetric Co-Teacher Network for Semi-Supervised Memory...
[ICIP 2022] ACT-NET: Asymmetric Co-Teacher Network for Semi-Supervised Memory...Ziyuan Zhao
 
[ICIP 2022] MMGL: Multi-Scale Multi-View Global-Local Contrastive learning fo...
[ICIP 2022] MMGL: Multi-Scale Multi-View Global-Local Contrastive learning fo...[ICIP 2022] MMGL: Multi-Scale Multi-View Global-Local Contrastive learning fo...
[ICIP 2022] MMGL: Multi-Scale Multi-View Global-Local Contrastive learning fo...Ziyuan Zhao
 
[ICIP 2022 - Poster] MMGL: Multi-Scale Multi-View Global-Local Contrastive le...
[ICIP 2022 - Poster] MMGL: Multi-Scale Multi-View Global-Local Contrastive le...[ICIP 2022 - Poster] MMGL: Multi-Scale Multi-View Global-Local Contrastive le...
[ICIP 2022 - Poster] MMGL: Multi-Scale Multi-View Global-Local Contrastive le...Ziyuan Zhao
 
[EMBC 2022] Self-supervised Assisted Active Learning for Skin Lesion Segmenta...
[EMBC 2022] Self-supervised Assisted Active Learning for Skin Lesion Segmenta...[EMBC 2022] Self-supervised Assisted Active Learning for Skin Lesion Segmenta...
[EMBC 2022] Self-supervised Assisted Active Learning for Skin Lesion Segmenta...Ziyuan Zhao
 
[ICME 2022] Adaptive Mean-Residue Loss for Robust Facial Age Estimation
[ICME 2022] Adaptive Mean-Residue Loss for Robust Facial Age Estimation[ICME 2022] Adaptive Mean-Residue Loss for Robust Facial Age Estimation
[ICME 2022] Adaptive Mean-Residue Loss for Robust Facial Age EstimationZiyuan Zhao
 
[EMBC 2021] Hierarchical Consistency Regularized Mean Teacher for Semi-superv...
[EMBC 2021] Hierarchical Consistency Regularized Mean Teacher for Semi-superv...[EMBC 2021] Hierarchical Consistency Regularized Mean Teacher for Semi-superv...
[EMBC 2021] Hierarchical Consistency Regularized Mean Teacher for Semi-superv...Ziyuan Zhao
 
[EMBC 2021] Multi Slice Dense Sparse Learning for Efficient Liver and Tumor S...
[EMBC 2021] Multi Slice Dense Sparse Learning for Efficient Liver and Tumor S...[EMBC 2021] Multi Slice Dense Sparse Learning for Efficient Liver and Tumor S...
[EMBC 2021] Multi Slice Dense Sparse Learning for Efficient Liver and Tumor S...Ziyuan Zhao
 
[ICIP 2020] SEA-Net: Squeeze-and-Excitation Attention Net for Diabetic Retino...
[ICIP 2020] SEA-Net: Squeeze-and-Excitation Attention Net for Diabetic Retino...[ICIP 2020] SEA-Net: Squeeze-and-Excitation Attention Net for Diabetic Retino...
[ICIP 2020] SEA-Net: Squeeze-and-Excitation Attention Net for Diabetic Retino...Ziyuan Zhao
 
[MICCAI 2021 - Poster] MT-UDA: Towards unsupervised cross-modality medical im...
[MICCAI 2021 - Poster] MT-UDA: Towards unsupervised cross-modality medical im...[MICCAI 2021 - Poster] MT-UDA: Towards unsupervised cross-modality medical im...
[MICCAI 2021 - Poster] MT-UDA: Towards unsupervised cross-modality medical im...Ziyuan Zhao
 

More from Ziyuan Zhao (13)

[IJCAI 2023] SemiGNN-PPI: Self-Ensembling Multi-Graph Neural Network for Effi...
[IJCAI 2023] SemiGNN-PPI: Self-Ensembling Multi-Graph Neural Network for Effi...[IJCAI 2023] SemiGNN-PPI: Self-Ensembling Multi-Graph Neural Network for Effi...
[IJCAI 2023] SemiGNN-PPI: Self-Ensembling Multi-Graph Neural Network for Effi...
 
[IJCAI 2023 - Poster] SemiGNN-PPI: Self-Ensembling Multi-Graph Neural Network...
[IJCAI 2023 - Poster] SemiGNN-PPI: Self-Ensembling Multi-Graph Neural Network...[IJCAI 2023 - Poster] SemiGNN-PPI: Self-Ensembling Multi-Graph Neural Network...
[IJCAI 2023 - Poster] SemiGNN-PPI: Self-Ensembling Multi-Graph Neural Network...
 
[BMVC 2022 - Spotlight] DA-CIL: Towards Domain Adaptive Class-Incremental 3D ...
[BMVC 2022 - Spotlight] DA-CIL: Towards Domain Adaptive Class-Incremental 3D ...[BMVC 2022 - Spotlight] DA-CIL: Towards Domain Adaptive Class-Incremental 3D ...
[BMVC 2022 - Spotlight] DA-CIL: Towards Domain Adaptive Class-Incremental 3D ...
 
[BMVC 2022] DA-CIL: Towards Domain Adaptive Class-Incremental 3D Object Detec...
[BMVC 2022] DA-CIL: Towards Domain Adaptive Class-Incremental 3D Object Detec...[BMVC 2022] DA-CIL: Towards Domain Adaptive Class-Incremental 3D Object Detec...
[BMVC 2022] DA-CIL: Towards Domain Adaptive Class-Incremental 3D Object Detec...
 
[ICIP 2022] ACT-NET: Asymmetric Co-Teacher Network for Semi-Supervised Memory...
[ICIP 2022] ACT-NET: Asymmetric Co-Teacher Network for Semi-Supervised Memory...[ICIP 2022] ACT-NET: Asymmetric Co-Teacher Network for Semi-Supervised Memory...
[ICIP 2022] ACT-NET: Asymmetric Co-Teacher Network for Semi-Supervised Memory...
 
[ICIP 2022] MMGL: Multi-Scale Multi-View Global-Local Contrastive learning fo...
[ICIP 2022] MMGL: Multi-Scale Multi-View Global-Local Contrastive learning fo...[ICIP 2022] MMGL: Multi-Scale Multi-View Global-Local Contrastive learning fo...
[ICIP 2022] MMGL: Multi-Scale Multi-View Global-Local Contrastive learning fo...
 
[ICIP 2022 - Poster] MMGL: Multi-Scale Multi-View Global-Local Contrastive le...
[ICIP 2022 - Poster] MMGL: Multi-Scale Multi-View Global-Local Contrastive le...[ICIP 2022 - Poster] MMGL: Multi-Scale Multi-View Global-Local Contrastive le...
[ICIP 2022 - Poster] MMGL: Multi-Scale Multi-View Global-Local Contrastive le...
 
[EMBC 2022] Self-supervised Assisted Active Learning for Skin Lesion Segmenta...
[EMBC 2022] Self-supervised Assisted Active Learning for Skin Lesion Segmenta...[EMBC 2022] Self-supervised Assisted Active Learning for Skin Lesion Segmenta...
[EMBC 2022] Self-supervised Assisted Active Learning for Skin Lesion Segmenta...
 
[ICME 2022] Adaptive Mean-Residue Loss for Robust Facial Age Estimation
[ICME 2022] Adaptive Mean-Residue Loss for Robust Facial Age Estimation[ICME 2022] Adaptive Mean-Residue Loss for Robust Facial Age Estimation
[ICME 2022] Adaptive Mean-Residue Loss for Robust Facial Age Estimation
 
[EMBC 2021] Hierarchical Consistency Regularized Mean Teacher for Semi-superv...
[EMBC 2021] Hierarchical Consistency Regularized Mean Teacher for Semi-superv...[EMBC 2021] Hierarchical Consistency Regularized Mean Teacher for Semi-superv...
[EMBC 2021] Hierarchical Consistency Regularized Mean Teacher for Semi-superv...
 
[EMBC 2021] Multi Slice Dense Sparse Learning for Efficient Liver and Tumor S...
[EMBC 2021] Multi Slice Dense Sparse Learning for Efficient Liver and Tumor S...[EMBC 2021] Multi Slice Dense Sparse Learning for Efficient Liver and Tumor S...
[EMBC 2021] Multi Slice Dense Sparse Learning for Efficient Liver and Tumor S...
 
[ICIP 2020] SEA-Net: Squeeze-and-Excitation Attention Net for Diabetic Retino...
[ICIP 2020] SEA-Net: Squeeze-and-Excitation Attention Net for Diabetic Retino...[ICIP 2020] SEA-Net: Squeeze-and-Excitation Attention Net for Diabetic Retino...
[ICIP 2020] SEA-Net: Squeeze-and-Excitation Attention Net for Diabetic Retino...
 
[MICCAI 2021 - Poster] MT-UDA: Towards unsupervised cross-modality medical im...
[MICCAI 2021 - Poster] MT-UDA: Towards unsupervised cross-modality medical im...[MICCAI 2021 - Poster] MT-UDA: Towards unsupervised cross-modality medical im...
[MICCAI 2021 - Poster] MT-UDA: Towards unsupervised cross-modality medical im...
 

Recently uploaded

Platformless Horizons for Digital Adaptability
Platformless Horizons for Digital AdaptabilityPlatformless Horizons for Digital Adaptability
Platformless Horizons for Digital AdaptabilityWSO2
 
Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...
Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...
Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...Jeffrey Haguewood
 
Design and Development of a Provenance Capture Platform for Data Science
Design and Development of a Provenance Capture Platform for Data ScienceDesign and Development of a Provenance Capture Platform for Data Science
Design and Development of a Provenance Capture Platform for Data SciencePaolo Missier
 
Event-Driven Architecture Masterclass: Challenges in Stream Processing
Event-Driven Architecture Masterclass: Challenges in Stream ProcessingEvent-Driven Architecture Masterclass: Challenges in Stream Processing
Event-Driven Architecture Masterclass: Challenges in Stream ProcessingScyllaDB
 
Observability Concepts EVERY Developer Should Know (DevOpsDays Seattle)
Observability Concepts EVERY Developer Should Know (DevOpsDays Seattle)Observability Concepts EVERY Developer Should Know (DevOpsDays Seattle)
Observability Concepts EVERY Developer Should Know (DevOpsDays Seattle)Paige Cruz
 
Quantum Leap in Next-Generation Computing
Quantum Leap in Next-Generation ComputingQuantum Leap in Next-Generation Computing
Quantum Leap in Next-Generation ComputingWSO2
 
Design Guidelines for Passkeys 2024.pptx
Design Guidelines for Passkeys 2024.pptxDesign Guidelines for Passkeys 2024.pptx
Design Guidelines for Passkeys 2024.pptxFIDO Alliance
 
TrustArc Webinar - Unified Trust Center for Privacy, Security, Compliance, an...
TrustArc Webinar - Unified Trust Center for Privacy, Security, Compliance, an...TrustArc Webinar - Unified Trust Center for Privacy, Security, Compliance, an...
TrustArc Webinar - Unified Trust Center for Privacy, Security, Compliance, an...TrustArc
 
Simplifying Mobile A11y Presentation.pptx
Simplifying Mobile A11y Presentation.pptxSimplifying Mobile A11y Presentation.pptx
Simplifying Mobile A11y Presentation.pptxMarkSteadman7
 
Portal Kombat : extension du réseau de propagande russe
Portal Kombat : extension du réseau de propagande russePortal Kombat : extension du réseau de propagande russe
Portal Kombat : extension du réseau de propagande russe中 央社
 
Finding Java's Hidden Performance Traps @ DevoxxUK 2024
Finding Java's Hidden Performance Traps @ DevoxxUK 2024Finding Java's Hidden Performance Traps @ DevoxxUK 2024
Finding Java's Hidden Performance Traps @ DevoxxUK 2024Victor Rentea
 
WebRTC and SIP not just audio and video @ OpenSIPS 2024
WebRTC and SIP not just audio and video @ OpenSIPS 2024WebRTC and SIP not just audio and video @ OpenSIPS 2024
WebRTC and SIP not just audio and video @ OpenSIPS 2024Lorenzo Miniero
 
ChatGPT and Beyond - Elevating DevOps Productivity
ChatGPT and Beyond - Elevating DevOps ProductivityChatGPT and Beyond - Elevating DevOps Productivity
ChatGPT and Beyond - Elevating DevOps ProductivityVictorSzoltysek
 
API Governance and Monetization - The evolution of API governance
API Governance and Monetization -  The evolution of API governanceAPI Governance and Monetization -  The evolution of API governance
API Governance and Monetization - The evolution of API governanceWSO2
 
WSO2 Micro Integrator for Enterprise Integration in a Decentralized, Microser...
WSO2 Micro Integrator for Enterprise Integration in a Decentralized, Microser...WSO2 Micro Integrator for Enterprise Integration in a Decentralized, Microser...
WSO2 Micro Integrator for Enterprise Integration in a Decentralized, Microser...WSO2
 
AI+A11Y 11MAY2024 HYDERBAD GAAD 2024 - HelloA11Y (11 May 2024)
AI+A11Y 11MAY2024 HYDERBAD GAAD 2024 - HelloA11Y (11 May 2024)AI+A11Y 11MAY2024 HYDERBAD GAAD 2024 - HelloA11Y (11 May 2024)
AI+A11Y 11MAY2024 HYDERBAD GAAD 2024 - HelloA11Y (11 May 2024)Samir Dash
 
Intro to Passkeys and the State of Passwordless.pptx
Intro to Passkeys and the State of Passwordless.pptxIntro to Passkeys and the State of Passwordless.pptx
Intro to Passkeys and the State of Passwordless.pptxFIDO Alliance
 
Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024
Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024
Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024Victor Rentea
 
Navigating Identity and Access Management in the Modern Enterprise
Navigating Identity and Access Management in the Modern EnterpriseNavigating Identity and Access Management in the Modern Enterprise
Navigating Identity and Access Management in the Modern EnterpriseWSO2
 

Recently uploaded (20)

Platformless Horizons for Digital Adaptability
Platformless Horizons for Digital AdaptabilityPlatformless Horizons for Digital Adaptability
Platformless Horizons for Digital Adaptability
 
Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...
Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...
Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...
 
Overview of Hyperledger Foundation
Overview of Hyperledger FoundationOverview of Hyperledger Foundation
Overview of Hyperledger Foundation
 
Design and Development of a Provenance Capture Platform for Data Science
Design and Development of a Provenance Capture Platform for Data ScienceDesign and Development of a Provenance Capture Platform for Data Science
Design and Development of a Provenance Capture Platform for Data Science
 
Event-Driven Architecture Masterclass: Challenges in Stream Processing
Event-Driven Architecture Masterclass: Challenges in Stream ProcessingEvent-Driven Architecture Masterclass: Challenges in Stream Processing
Event-Driven Architecture Masterclass: Challenges in Stream Processing
 
Observability Concepts EVERY Developer Should Know (DevOpsDays Seattle)
Observability Concepts EVERY Developer Should Know (DevOpsDays Seattle)Observability Concepts EVERY Developer Should Know (DevOpsDays Seattle)
Observability Concepts EVERY Developer Should Know (DevOpsDays Seattle)
 
Quantum Leap in Next-Generation Computing
Quantum Leap in Next-Generation ComputingQuantum Leap in Next-Generation Computing
Quantum Leap in Next-Generation Computing
 
Design Guidelines for Passkeys 2024.pptx
Design Guidelines for Passkeys 2024.pptxDesign Guidelines for Passkeys 2024.pptx
Design Guidelines for Passkeys 2024.pptx
 
TrustArc Webinar - Unified Trust Center for Privacy, Security, Compliance, an...
TrustArc Webinar - Unified Trust Center for Privacy, Security, Compliance, an...TrustArc Webinar - Unified Trust Center for Privacy, Security, Compliance, an...
TrustArc Webinar - Unified Trust Center for Privacy, Security, Compliance, an...
 
Simplifying Mobile A11y Presentation.pptx
Simplifying Mobile A11y Presentation.pptxSimplifying Mobile A11y Presentation.pptx
Simplifying Mobile A11y Presentation.pptx
 
Portal Kombat : extension du réseau de propagande russe
Portal Kombat : extension du réseau de propagande russePortal Kombat : extension du réseau de propagande russe
Portal Kombat : extension du réseau de propagande russe
 
Finding Java's Hidden Performance Traps @ DevoxxUK 2024
Finding Java's Hidden Performance Traps @ DevoxxUK 2024Finding Java's Hidden Performance Traps @ DevoxxUK 2024
Finding Java's Hidden Performance Traps @ DevoxxUK 2024
 
WebRTC and SIP not just audio and video @ OpenSIPS 2024
WebRTC and SIP not just audio and video @ OpenSIPS 2024WebRTC and SIP not just audio and video @ OpenSIPS 2024
WebRTC and SIP not just audio and video @ OpenSIPS 2024
 
ChatGPT and Beyond - Elevating DevOps Productivity
ChatGPT and Beyond - Elevating DevOps ProductivityChatGPT and Beyond - Elevating DevOps Productivity
ChatGPT and Beyond - Elevating DevOps Productivity
 
API Governance and Monetization - The evolution of API governance
API Governance and Monetization -  The evolution of API governanceAPI Governance and Monetization -  The evolution of API governance
API Governance and Monetization - The evolution of API governance
 
WSO2 Micro Integrator for Enterprise Integration in a Decentralized, Microser...
WSO2 Micro Integrator for Enterprise Integration in a Decentralized, Microser...WSO2 Micro Integrator for Enterprise Integration in a Decentralized, Microser...
WSO2 Micro Integrator for Enterprise Integration in a Decentralized, Microser...
 
AI+A11Y 11MAY2024 HYDERBAD GAAD 2024 - HelloA11Y (11 May 2024)
AI+A11Y 11MAY2024 HYDERBAD GAAD 2024 - HelloA11Y (11 May 2024)AI+A11Y 11MAY2024 HYDERBAD GAAD 2024 - HelloA11Y (11 May 2024)
AI+A11Y 11MAY2024 HYDERBAD GAAD 2024 - HelloA11Y (11 May 2024)
 
Intro to Passkeys and the State of Passwordless.pptx
Intro to Passkeys and the State of Passwordless.pptxIntro to Passkeys and the State of Passwordless.pptx
Intro to Passkeys and the State of Passwordless.pptx
 
Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024
Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024
Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024
 
Navigating Identity and Access Management in the Modern Enterprise
Navigating Identity and Access Management in the Modern EnterpriseNavigating Identity and Access Management in the Modern Enterprise
Navigating Identity and Access Management in the Modern Enterprise
 

[MICCAI 2021] MT-UDA: Towards unsupervised cross-modality medical image segmentation with limited source labels

  • 1. MT-UDA: Towards Unsupervised Cross-modality Medical Image Segmentation with Limited Source Labels Ziyuan Zhao1,2, Kaixin Xu2, Shumeng Li1,2, Zeng Zeng2, Cuntai Guan1 Presenter: Zhao Ziyuan (G2104205L) 1 Nanyang Technological University 2 Institute for Infocomm Research, A*STAR Th-S2: Image Segmentation + Domain Adaptation # 678
  • 2. Introduction – Medical Image Segmentation - Segmentation in medical physics plays a crucial role in medical image analysis (MedIA) - For instance, left atrium (LA) segmentation can provide a pre-operative assessment of its anatomy, which is essential for treating various cardiovascular diseases, such as atrial fibrillation - Deep learning has been widely used for medical image segmentation Left Atrial Cavity 3D LA Visualization 2018 Atrial Segmentation Challenge. https://atriaseg2018.cardiacatlas.org/
  • 3. Challenge (1) – Label Scarcity - DCNNs are data-hungry and require large amounts of well-annotated data. - Annotating medical images is laborious, expensive, and requires human expertise → Label Scarcity Time & money consuming Knowledge-driven Labor-intensive Image DCNNs Segmentation map
  • 4. Challenge (2) – Domain Shift - In real-world clinical scenarios, medical images are acquired with different physical principles and modalities, e.g., MRI & CT→ different visual appearance & distribution (Domain Gap) - DCNNs suffer from severe performance degradation when domain shift (e.g., CT → MRI) Cardiac Label Cardiac CT Source Domain Annotate DCNNs Transfer Cardiac MR Feed Domain Gap Target Domain
  • 5. Existing Work – Unsupervised Domain Adaptation - Image adaptation – Cycle GAN (2017) - Feature adaptation – ADDA (2017) - Sequentially combine two adaptive strategies – CyCADA (2018) - Synergistic Image and Feature Adaptation – SIFA (2019, 2020) Cardiac CT Cardiac MR Domain Gap CycleGAN [1] ADDA [2] Cycada [3] SIFA [4] [1] Zhu, Jun-Yan, et al. "Unpaired image-to-image translation using cycle-consistent adversarial networks." ICCV 2017 [2] Tzeng, Eric, et al. "Adversarial discriminative domain adaptation." CVPR 2017. [3] Hoffman, Judy, et al. "Cycada: Cycle-consistent adversarial domain adaptation.“ ICML 2018 [4] Chen, Cheng, et al. "Unsupervised bidirectional cross-modality adaptation via deeply synergistic image and feature alignment for medical image segmentation." TMI 2020 Source Domain Target Domain
  • 6. Problem – Source Label Scarcity - Despite the success of adversarial learning in UDA, these methods heavily rely on abundant source labels. - Become sub-optimal when only limited source labels are available in clinical deployment. - Motivates us to study a challenging UDA scenario – source label scarcity Source Label Scarcity Cardiac CT Cardiac MR Domain Gap Source Domain Target Domain Less Annotations Lower Performance
  • 7. Motivation – SSL + UDA - Image-level adaptation → generates a lot of synthetic images with abundant information, which can be leveraged for semi-supervised learning - Appearance consistency → synthetic and real images from the same domain maintain a similar visual appearance - Structural consistency → transformed images should have the same structural information as the original ones Zhao, Ziyuan, et al. "MT-UDA: Towards Unsupervised Cross-modality Medical Image Segmentation with Limited Source Labels." MICCAI 2021 SSL Labeled data Performance Number of labeled data DCNNs Source Domain Target Domain Style Transfer
  • 8. Method – MT-UDA - Investigate the feasibility of integrating SSL into UDA under source label scarcity - Develop a label-efficient UDA framework based on mean teacher (MT) to explore the knowledge from both domains Zhao, Ziyuan, et al. "MT-UDA: Towards Unsupervised Cross-modality Medical Image Segmentation with Limited Source Labels." MICCAI 2021
  • 9. Method (1)– Dual Cycle Alignment Module - Generate synthetic samples for two domains using generative adversarial networks - Synthesize source-like domain images and target-like domain images via adversarial learning Zhao, Ziyuan, et al. "MT-UDA: Towards Unsupervised Cross-modality Medical Image Segmentation with Limited Source Labels." MICCAI 2021
  • 10. Method (2)– Semantic Knowledge Transfer - Appearance consistency → synthetic and real images from the same domain maintain a similar visual appearance - Employ the mean teacher (MT) model to distill the intra-domain semantic knowledge by forcing the prediction consistency Zhao, Ziyuan, et al. "MT-UDA: Towards Unsupervised Cross-modality Medical Image Segmentation with Limited Source Labels." MICCAI 2021
  • 11. Method (3)– Structural Knowledge Transfer - Structural consistency → transformed images should have the same structural information as the original ones - Propose a teacher model for keeping structural consistency between predictions of source images and corresponding synthetic target images Zhao, Ziyuan, et al. "MT-UDA: Towards Unsupervised Cross-modality Medical Image Segmentation with Limited Source Labels." MICCAI 2021
  • 12. Experiments - Dataset - Multi-Modality Whole Heart Segmentation (MM-WHS) 2017 dataset - Unpaired 20 MR and 20 CT volumes with ground truth masks - Data preprocessing - MR → source domain, CT → target domain - SIFA setting (-16) → 16: 4 random split for train / val - Our setting (-4)→ 4 MR volumes are labelled for UDA under source label scarcity - Images were cropped into the size of 256 x 256 - Implementation details - Test on fake MR images generated from CT - Backbone: U-Net - Supervised loss: Dice + Cross-entropy - Total loss: Zhao, Ziyuan, et al. "MT-UDA: Towards Unsupervised Cross-modality Medical Image Segmentation with Limited Source Labels." MICCAI 2021
  • 13. Results (1) – Quantitative Comparison - Degraded performance on target domain when using 4 labeled source domain scans - MT and UA-MT can help improve the segmentation performance on target domain - Demonstrate the feasibility of integrating SSL into UDA for label-efficient UDA suffix −4 or −16 # labelled source scans used for training [1] Dou, Qi, et al. "Unsupervised cross-modality domain adaptation of convnets for biomedical image segmentations with adversarial loss." IJCAI 2018 [2] Chen, Cheng, et al. "Synergistic image and feature adaptation: Towards cross-modality domain adaptation for medical image segmentation." AAAI 2019 [3] Chen, Cheng, et al. "Unsupervised bidirectional cross-modality adaptation via deeply synergistic image and feature alignment for medical image segmentation." TMI 2020 [4] Tarvainen, Antti, and Harri Valpola. "Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results.“NIPS 2017 [5] Yu, Lequan, et al. "Uncertainty-aware self-ensembling model for semi-supervised 3D left atrium segmentation.“ MICCAI 2019
  • 14. Results (2) – Qualitative Comparison - It is observed that our method can generate more reliable masks with fewer false positives Zhao, Ziyuan, et al. "MT-UDA: Towards Unsupervised Cross-modality Medical Image Segmentation with Limited Source Labels." MICCAI 2021
  • 15. Results (3) – Ablation Study - Remove one of the teacher models, separately - W/o semantic knowledge transfer (MT-UDA-NS) - W/o structural knowledge transfer (MTUDA-NT) - Replace structural consistency loss with MSE loss (MT-UDA-NS-MSE) Zhao, Ziyuan, et al. "MT-UDA: Towards Unsupervised Cross-modality Medical Image Segmentation with Limited Source Labels." MICCAI 2021
  • 16. Conclusions - Study a practical, challenging, and different UDA setting from the past, where only limited source labels are accessible → Source Label Scarcity - Investigate the feasibility of integrating SSL into UDA under source label scarcity - Propose a label-efficient UDA framework for cross-modality medical image segmentation - Leverage intra-domain semantic knowledge and exploit inter-domain structural knowledge concurrently, thereby mitigating both the domain discrepancy and source label scarcity. Zhao, Ziyuan, et al. "MT-UDA: Towards Unsupervised Cross-modality Medical Image Segmentation with Limited Source Labels." MICCAI 2021