Automatic size and pose homogenization with spatial transformer network to improve and accelerate pediatric segmentation

TL;DR

This paper introduces a CNN with Spatial Transformer Networks for pediatric image segmentation that normalizes pose and size, leading to faster and more accurate segmentation results.

Contribution

The novel architecture integrates pose and scale normalization into the segmentation process, reducing training time and improving segmentation accuracy in pediatric CT images.

Findings

Homogenization accelerates segmentation by 25 hours versus data augmentation.

Achieves 88.01% Dice score for kidney segmentation.

Improves renal tumor delineation from 85.52% to 87.12%.

Abstract

Due to a high heterogeneity in pose and size and to a limited number of available data, segmentation of pediatric images is challenging for deep learning methods. In this work, we propose a new CNN architecture that is pose and scale invariant thanks to the use of Spatial Transformer Network (STN). Our architecture is composed of three sequential modules that are estimated together during training: (i) a regression module to estimate a similarity matrix to normalize the input image to a reference one; (ii) a differentiable module to find the region of interest to segment; (iii) a segmentation module, based on the popular UNet architecture, to delineate the object. Unlike the original UNet, which strives to learn a complex mapping, including pose and scale variations, from a finite training dataset, our segmentation module learns a simpler mapping focusing on images with normalized pose and size. Furthermore, the use of an automatic bounding box detection through STN allows saving time and especially memory, while keeping similar performance. We test the proposed method in kidney and renal tumor segmentation on abdominal pediatric CT scanners. Results indicate that the estimated STN homogenization of size and pose accelerates the segmentation (25h), compared to standard data-augmentation (33h), while obtaining a similar quality for the kidney (88.01\% of Dice score) and improving the renal tumor delineation (from 85.52\% to 87.12\%).