Share Email Print

Proceedings Paper

Reflection-equivariant convolutional neural networks improve segmentation over reflection augmentation
Author(s): Shuo Han; Jerry L. Prince; Aaron Carass
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Convolutional neural networks (CNNs) have been successfully applied to human brain segmentation. To in- corporate 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.

Paper Details

Date Published: 10 March 2020
PDF: 8 pages
Proc. SPIE 11313, Medical Imaging 2020: Image Processing, 1131337 (10 March 2020); doi: 10.1117/12.2549399
Show Author Affiliations
Shuo Han, Johns Hopkins Univ. (United States)
Jerry L. Prince, Johns Hopkins Univ. (United States)
Aaron Carass, Johns Hopkins Univ. (United States)

Published in SPIE Proceedings Vol. 11313:
Medical Imaging 2020: Image Processing
Ivana Išgum; Bennett A. Landman, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?