Multi-view Cross-Modality MR Image Translation for Vestibular Schwannoma and Cochlea Segmentation
This work addresses a domain-specific medical imaging problem for vestibular schwannoma and cochlea segmentation, with incremental improvements.
The authors tackled the problem of segmenting vestibular schwannoma and cochlea in MR images by proposing a multi-view image translation framework that translates contrast-enhanced T1 to high-resolution T2 imaging, achieving enhanced performance in the CrossMoDA challenge.
In this work, we propose a multi-view image translation framework, which can translate contrast-enhanced T1 (ceT1) MR imaging to high-resolution T2 (hrT2) MR imaging for unsupervised vestibular schwannoma and cochlea segmentation. We adopt two image translation models in parallel that use a pixel-level consistent constraint and a patch-level contrastive constraint, respectively. Thereby, we can augment pseudo-hrT2 images reflecting different perspectives, which eventually lead to a high-performing segmentation model. Our experimental results on the CrossMoDA challenge show that the proposed method achieved enhanced performance on the vestibular schwannoma and cochlea segmentation.