@inproceedings{cd82f5c9b842492a934f5a27ed4a08b4,
title = "Reflection-equivariant convolutional neural networks improve segmentation over reflection augmentation",
abstract = "Convolutional neural networks (CNNs) have been successfully applied to human brain segmentation. To incorporate the left and right symmetry property of the brain into a network architecture, we propose a 3D left-right-reflection equivariant network to segment the anatomical structures of the brain. We extended previous group convolutions to account for left-right paired labels in the delineation. The proposed networks were compared with conventional networks trained with left-right reflection data augmentation in several tasks, showing improved performance. This is also the first work to extend reflection-equivariant CNNs to left-right paired labels in the human brain.",
keywords = "Brain, Convolutional neural networks, Equivariance, Segmentation",
author = "Shuo Han and Prince, {Jerry L.} and Aaron Carass",
note = "Publisher Copyright: {\textcopyright} 2020 SPIE. All rights reserved.; Medical Imaging 2020: Image Processing ; Conference date: 17-02-2020 Through 20-02-2020",
year = "2020",
doi = "10.1117/12.2549399",
language = "English (US)",
series = "Progress in Biomedical Optics and Imaging - Proceedings of SPIE",
publisher = "SPIE",
editor = "Ivana Isgum and Landman, {Bennett A.}",
booktitle = "Medical Imaging 2020",
}