Abstract #0831

Spherical U-Net for Infant Cortical Surface Parcellation

Fenqiang Zhao^1,2, Shunren Xia¹, Zhengwang Wu², Li Wang², Weili Lin², John H Gilmore³, Dinggang Shen², and Gang Li²

¹Key Laboratory of Biomedical Engineering of Ministry of Education, Zhejiang University, Hangzhou, China, ²Department of Radiology and BRIC, University of North Carolina at Chapel Hill, Chapel Hill, NC, United States, ³Department of Psychiatry, University of North Carolina at Chapel Hill, Chapel Hill, NC, United States

In neuroimaging studies, it is of great importance to accurately parcellate cortical surfaces (with a spherical topology) into meaningful regions. In this work, we propose a novel end-to-end deep learning method by formulating surface parcellation as a semantic segmentation task on the spherical space. To extend the convolutional neural networks (CNNs) to the spherical space, a set of corresponding operations are first developed, and then spherical CNNs are constructed accordingly. Specifically, the U-Net and SegNet architectures are transformed to parcellate infant cortical surfaces. Experiments on 90 neonates indicate the superiority of our proposed spherical U-Net in comparison with other methods.

This abstract and the presentation materials are available to members only; a login is required.

Join Here