crossMoDA Challenge: Evolution of Cross-Modality Domain Adaptation Techniques for Vestibular Schwannoma and Cochlea Segmentation from 2021 to 2023
Not on the map. Why?
Abstract (arXiv)
The cross-Modality Domain Adaptation (crossMoDA) challenge series, initiated in 2021 in conjunction with the International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), focuses on unsupervised cross-modality segmentation, learning from contrast-enhanced T1 (ceT1) and transferring to T2 MRI. The task is an extreme example of domain shift chosen to serve as a meaningful and illustrative benchmark. From a clinical application perspective, it aims to automate Vestibular Schwannoma (VS) and cochlea segmentation on T2 scans for more cost-effective VS management. Over time, the challenge objectives have evolved to enhance its clinical relevance. The challenge evolved from using single-institutional data and basic segmentation in 2021 to incorporating multi-institutional data and Koos grading in 2022, and by 2023, it included heterogeneous routine data and sub-segmentation of intra- and extra-meatal tumour components. In this work, we report the findings of the 2022 and 2023 editions and perform a retrospective analysis of the challenge progression over the years. The observations from the successive challenge contributions indicate that the number of outliers decreases with an expanding dataset. This is notable since the diversity of scanning protocols of the datasets concurrently increased. The winning approach of the 2023 edition reduced the number of outliers on the 2021 and 2022 testing data, demonstrating how increased data heterogeneity can enhance segmentation performance even on homogeneous data. However, the cochlea Dice score declined in 2023, likely due to the added complexity from tumour sub-annotations affecting overall segmentation performance. While progress is still needed for clinically acceptable VS segmentation, the plateauing performance suggests that a more challenging cross-modal task may better serve future benchmarking.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 34 of its 59 references that are in the map. First posted on arXiv 13 Jun 2025.
Builds on
34 of 59 references.
References · 34
- 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,588
- 2020Supervised Contrastive Learningcited by 2,829
- 2020Contrastive Learning for Unpaired Image-to-Image Translationcited by 639
- 2018Identifying the Best Machine Learning Algorithms for Brain Tumor Segmentation, Progression Assessment, and Overall Survival Prediction in the BRATS Challengecited by 511
- 2021Domain Adaptation for Medical Image Analysis: A Surveycited by 352
- 2019SinGAN: Learning a Generative Model from a Single Natural Imagecited by 348
- 2019ResUNet-a: a deep learning framework for semantic segmentation of remotely sensed datacited by 261
- 2020Unsupervised Bidirectional Cross-Modality Adaptation via Deeply Synergistic Image and Feature Alignment for Medical Image Segmentationcited by 134
- 2016Unsupervised domain adaptation in brain lesion segmentation with adversarial networkscited by 125
- 2018Unsupervised domain adaptation for medical imaging segmentation with self-ensemblingcited by 94
- 2018Why rankings of biomedical image analysis competitions should be interpreted with carecited by 91
- 2021Dual Contrastive Learning for Unsupervised Image-to-Image Translationcited by 66
22 more
- 2019Methods and open-source toolkit for analyzing and visualizing challenge resultscited by 60
- 2022CrossMoDA 2021 challenge: Benchmark of Cross-Modality Domain Adaptation techniques for Vestibular Schwannoma and Cochlea Segmentationcited by 58
- 2019BIAS: Transparent reporting of biomedical image analysis challengescited by 57
- 2021Optimized U-Net for Brain Tumor Segmentationcited by 40
- 2022QS-Attn: Query-Selected Attention for Contrastive Learning in I2I Translationcited by 39
- 2022LE-UDA: Label-efficient unsupervised domain adaptation for medical image segmentationcited by 27
- 2022ModDrop++: A Dynamic Filter Network with Intra-subject Co-training for Multiple Sclerosis Lesion Segmentation with Missing Modalitiescited by 22
- 2021Hierarchical Consistency Regularized Mean Teacher for Semi-supervised 3D Left Atrium Segmentationcited by 21
- 2022COSMOS: Cross-Modality Unsupervised Domain Adaptation for 3D Medical Image Segmentation based on Target-aware Domain Translation and Iterative Self-Trainingcited by 20
- 2021Unsupervised Domain Adaptation in Semantic Segmentation Based on Pixel Alignment and Self-Trainingcited by 16
- 2023Synthesis-based Imaging-Differentiation Representation Learning for Multi-Sequence 3D/4D MRIcited by 11
- 2022Adaptive t-vMF Dice Loss for Multi-class Medical Image Segmentationcited by 7
- 2023Cross-modal tumor segmentation using generative blending augmentation and self trainingcited by 6
- 2022Unsupervised Cross-Modality Domain Adaptation for Vestibular Schwannoma Segmentation and Koos Grade Prediction based on Semi-Supervised Contrastive Learningcited by 5
- 2023Multi-view Cross-Modality MR Image Translation for Vestibular Schwannoma and Cochlea Segmentationcited by 5
- 2022Enhancing Data Diversity for Self-training Based Unsupervised Cross-modality Vestibular Schwannoma and Cochlea Segmentationcited by 4
- 2023MS-MT: Multi-Scale Mean Teacher with Contrastive Unpaired Translation for Cross-Modality Vestibular Schwannoma and Cochlea Segmentationcited by 4
- 2023Learning Site-specific Styles for Multi-institutional Unsupervised Cross-modality Domain Adaptationcited by 3
- 2022An Unpaired Cross-modality Segmentation Framework Using Data Augmentation and Hybrid Convolutional Networks for Segmenting Vestibular Schwannoma and Cochleacited by 1
- 2023Unsupervised Domain Adaptation for MRI Volume Segmentation and Classification Using Image-to-Image Translationcited by 1
- 2023Weakly Unsupervised Domain Adaptation for Vestibular Schwannoma Segmentationcited by 1
- 2025Image Translation-Based Unsupervised Cross-Modality Domain Adaptation for Medical Image Segmentationcited by 1
Built on by
Citing papers per year: 2026: 1.
1 paper.