Reflection-equivariant convolutional neural networks improve segmentation over reflection augmentation

Shuo Han, Jerry L. Prince, Aaron Carass

Research output: Chapter in Book/Report/Conference proceedingConference contribution

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.

Original languageEnglish (US)
Title of host publicationMedical Imaging 2020
Subtitle of host publicationImage Processing
EditorsIvana Isgum, Bennett A. Landman
PublisherSPIE
ISBN (Electronic)9781510633933
DOIs
StatePublished - 2020
EventMedical Imaging 2020: Image Processing - Houston, United States
Duration: Feb 17 2020Feb 20 2020

Publication series

NameProgress in Biomedical Optics and Imaging - Proceedings of SPIE
Volume11313
ISSN (Print)1605-7422

Conference

ConferenceMedical Imaging 2020: Image Processing
CountryUnited States
CityHouston
Period2/17/202/20/20

Keywords

  • Brain
  • Convolutional neural networks
  • Equivariance
  • Segmentation

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Biomaterials
  • Atomic and Molecular Physics, and Optics
  • Radiology Nuclear Medicine and imaging

Fingerprint Dive into the research topics of 'Reflection-equivariant convolutional neural networks improve segmentation over reflection augmentation'. Together they form a unique fingerprint.

Cite this