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

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. (C) 2020 The Author(s). Published by Elsevier B.V.

Automated summary

This study introduces a framework for achieving translation and rotation equivariance in convolutional networks, enhancing the rotation invariance of machine-learning models for medical image analysis. By encoding the special Euclidean motion group SE(2) and introducing SE(2)-group convolution layers, the framework shows significant performance improvement in histopathology image analysis tasks.