Template Transformer Networks for Image Segmentation

Matthew Chung Hai Lee, Kersten Petersen, Nick Pawlowski, Ben Glocker, Michiel Schaap

Keywords: Image Segmentation, Shape Priors, Neural Networks, Template Deformation, Image Registration

TL;DR: Image segmentations by deforming shape priors, using a spatial transformer network.

Abstract: In this paper we introduce and compare different approaches for incorporating shape prior information into neural network based image segmentation. Specifically, we introduce the concept of template transformer networks where a shape template is deformed to match the underlying structure of interest through an end-to-end trained spatial transformer network. This has the advantage of explicitly enforcing shape priors and is free of discretisation artefacts by providing a soft partial volume segmentation. We also introduce a simple yet effective way of incorporating priors in state-of-the-art pixel-wise binary classification methods such as fully convolutional networks and U-net. Here, the template shape is given as an additional input channel, incorporating this information significantly reduces false positives. We report results on sub-voxel segmentation of coronary lumen structures in cardiac computed tomography showing the benefit of incorporating priors in neural network based image segmentation.

Code Of Conduct: I have read and accept the code of conduct.

Link: https://ieeexplore.ieee.org/abstract/document/8672808