Roto-translation equivariant convolutional networks: Application to histopathology image analysis

Maxime W Lafarge (Corresponding author), Erik J Bekkers, Josien P W Pluim, Remco Duits, Mitko Veta

Research output: Contribution to journalArticleAcademicpeer-review

42 Citations (Scopus)


Rotation-invariance is a desired property of machine-learning models for medical image analysis and in particular for computational pathology applications. We propose a framework to encode the geometric structure of the special Euclidean motion group SE(2) in convolutional networks to yield translation and rotation equivariance via the introduction of SE(2)-group convolution layers. This structure enables models to learn feature representations with a discretized orientation dimension that guarantees that their outputs are invariant under a discrete set of rotations. Conventional approaches for rotation invariance rely mostly on data augmentation, but this does not guarantee the robustness of the output when the input is rotated. At that, trained conventional CNNs may require test-time rotation augmentation to reach their full capability. This study is focused on histopathology image analysis applications for which it is desirable that the arbitrary global orientation information of the imaged tissues is not captured by the machine learning models. The proposed framework is evaluated on three different histopathology image analysis tasks (mitosis detection, nuclei segmentation and tumor detection). We present a comparative analysis for each problem and show that consistent increase of performances can be achieved when using the proposed framework.

Original languageEnglish
Article number101849
Pages (from-to)101849
Number of pages12
JournalMedical Image Analysis
Early online date31 Oct 2020
Publication statusPublished - 1 Feb 2021


  • Computational pathology
  • Group convolutional neural network
  • Mitosis detection
  • Nuclei segmentation
  • Roto-translation equivariance
  • Tumor detection


Dive into the research topics of 'Roto-translation equivariant convolutional networks: Application to histopathology image analysis'. Together they form a unique fingerprint.

Cite this