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


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
ISBN (Electronic)9781510633933
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
ISSN (Print)1605-7422


ConferenceMedical Imaging 2020: Image Processing
Country/TerritoryUnited States


  • 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


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

Cite this