Unsupervised Cross-Modality Domain Adaptation for Vestibular Schwannoma Segmentation and Koos Grade Prediction based on Semi-Supervised Contrastive Learning
This work addresses domain adaptation for medical imaging in vestibular schwannoma analysis, which is incremental as it builds on existing methods like nnU-Net and contrastive learning.
The paper tackled unsupervised domain adaptation for cross-modality segmentation and grade prediction of vestibular schwannoma, achieving a mean Dice score of 0.8394 for segmentation and a Macro-Average Mean Square Error of 0.3941 for grade prediction.
Domain adaptation has been widely adopted to transfer styles across multi-vendors and multi-centers, as well as to complement the missing modalities. In this challenge, we proposed an unsupervised domain adaptation framework for cross-modality vestibular schwannoma (VS) and cochlea segmentation and Koos grade prediction. We learn the shared representation from both ceT1 and hrT2 images and recover another modality from the latent representation, and we also utilize proxy tasks of VS segmentation and brain parcellation to restrict the consistency of image structures in domain adaptation. After generating missing modalities, the nnU-Net model is utilized for VS and cochlea segmentation, while a semi-supervised contrastive learning pre-train approach is employed to improve the model performance for Koos grade prediction. On CrossMoDA validation phase Leaderboard, our method received rank 4 in task1 with a mean Dice score of 0.8394 and rank 2 in task2 with Macro-Average Mean Square Error of 0.3941. Our code is available at https://github.com/fiy2W/cmda2022.superpolymerization.