Unsupervised Domain Adaptation for MRI Volume Segmentation and Classification Using Image-to-Image Translation

TL;DR

This paper presents an unsupervised domain adaptation approach using image-to-image translation for MRI segmentation and classification, achieving competitive results on the crossMoDA2022 challenge.

Contribution

It introduces a novel combination of image-to-image translation with residual U-Net and SVM for MRI domain adaptation and segmentation/classification tasks.

Findings

Segmentation mean DSC of 0.614 and ASSD of 2.936.

Classification MA-MAE of 0.84.

Effective unsupervised adaptation for cross-modality MRI data.

Abstract

Unsupervised domain adaptation is a type of domain adaptation and exploits labeled data from the source domain and unlabeled data from the target one. In the Cross-Modality Domain Adaptation for Medical Image Segmenta-tion challenge (crossMoDA2022), contrast enhanced T1 MRI volumes for brain are provided as the source domain data, and high-resolution T2 MRI volumes are provided as the target domain data. The crossMoDA2022 challenge contains two tasks, segmentation of vestibular schwannoma (VS) and cochlea, and clas-sification of VS with Koos grade. In this report, we presented our solution for the crossMoDA2022 challenge. We employ an image-to-image translation method for unsupervised domain adaptation and residual U-Net the segmenta-tion task. We use SVM for the classification task. The experimental results show that the mean DSC and ASSD are 0.614 and 2.936 for the segmentation task and MA-MAE is 0.84 for the classification task.