Cross-Modality Domain Adaptation for Vestibular Schwannoma and Cochlea Segmentation

TL;DR

This paper presents an unsupervised domain adaptation approach for segmenting vestibular schwannoma tumors and cochlea in MRI scans, reducing the need for expert annotations while maintaining high accuracy.

Contribution

It introduces a novel method combining image-level domain alignment, semi-supervised training, and noisy label correction for improved segmentation without full supervision.

Findings

Achieved a mean dice score of 0.8261 for VS and cochlea segmentation.

Performance is comparable to weakly-supervised methods.

Demonstrated effectiveness on challenge validation data.

Abstract

Automatic methods to segment the vestibular schwannoma (VS) tumors and the cochlea from magnetic resonance imaging (MRI) are critical to VS treatment planning. Although supervised methods have achieved satisfactory performance in VS segmentation, they require full annotations by experts, which is laborious and time-consuming. In this work, we aim to tackle the VS and cochlea segmentation problem in an unsupervised domain adaptation setting. Our proposed method leverages both the image-level domain alignment to minimize the domain divergence and semi-supervised training to further boost the performance. Furthermore, we propose to fuse the labels predicted from multiple models via noisy label correction. Our results on the challenge validation leaderboard showed that our unsupervised method has achieved promising VS and cochlea segmentation performance with mean dice score of 0.8261 $\pm$ 0.0416; The mean dice value for the tumor is 0.8302 $\pm$ 0.0772. This is comparable to the weakly-supervised based method.