Roto-translation covariant convolutional networks for medical image analysis

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

11 Citations (Scopus)

Abstract

We propose a framework for rotation and translation covariant deep learning using SE(2) group convolutions. The group product of the special Euclidean motion group SE(2) describes how a concatenation of two roto-translations results in a net roto-translation. We encode this geometric structure into convolutional neural networks (CNNs) via SE(2) group convolutional layers, which fit into the standard 2D CNN framework, and which allow to generically deal with rotated input samples without the need for data augmentation. We introduce three layers: a lifting layer which lifts a 2D (vector valued) image to an SE(2)-image, i.e., 3D (vector valued) data whose domain is SE(2); a group convolution layer from and to an SE(2)-image; and a projection layer from an SE(2)-image to a 2D image. The lifting and group convolution layers are SE(2) covariant (the output roto-translates with the input). The final projection layer, a maximum intensity projection over rotations, makes the full CNN rotation invariant. We show with three different problems in histopathology, retinal imaging, and electron microscopy that with the proposed group CNNs, state-of-the-art performance can be achieved, without the need for data augmentation by rotation and with increased performance compared to standard CNNs that do rely on augmentation.

Original languageEnglish
Title of host publicationMedical Image Computing and Computer Assisted Intervention – MICCAI 2018 - 21st International Conference, 2018, Proceedings
EditorsJulia A. Schnabel, Christos Davatzikos, Carlos Alberola-López, Gabor Fichtinger, Alejandro F. Frangi
Place of PublicationCham
PublisherSpringer
Pages440-448
Number of pages9
ISBN (Electronic)978-3-030-00928-1
ISBN (Print)978-3-030-00927-4
DOIs
Publication statusPublished - 1 Jan 2018
Event21st International Conference on Medical Image Computing and Computer Assisted Intervention, MICCAI 2018 - Granada, Spain
Duration: 16 Sep 201820 Sep 2018

Publication series

NameLecture Notes in Computer Science
Volume11070
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

Conference21st International Conference on Medical Image Computing and Computer Assisted Intervention, MICCAI 2018
CountrySpain
CityGranada
Period16/09/1820/09/18

Keywords

  • Cell boundary segmentation
  • Group convolutional network
  • Mitosis detection
  • Roto-translation group
  • Vessel segmentation

Fingerprint Dive into the research topics of 'Roto-translation covariant convolutional networks for medical image analysis'. Together they form a unique fingerprint.

  • Cite this

    Bekkers, E. J., Lafarge, M. W., Veta, M., Eppenhof, K. A. J., Pluim, J. P. W., & Duits, R. (2018). Roto-translation covariant convolutional networks for medical image analysis. In J. A. Schnabel, C. Davatzikos, C. Alberola-López, G. Fichtinger, & A. F. Frangi (Eds.), Medical Image Computing and Computer Assisted Intervention – MICCAI 2018 - 21st International Conference, 2018, Proceedings (pp. 440-448). (Lecture Notes in Computer Science; Vol. 11070). Springer. https://doi.org/10.1007/978-3-030-00928-1_50