Automatic size and pose homogenization with Spatial Transformer Network to improve and accelerate pediatric segmentation - Archive ouverte HAL Access content directly
Conference Papers Year : 2021

Automatic size and pose homogenization with Spatial Transformer Network to improve and accelerate pediatric segmentation

(1, 2, 3) , (1, 2, 3) , (4) , (1, 2, 3) , (5, 6) , (5, 6) , (5, 6) , (4) , (1, 2, 3, 7)
1
2
3
4
5
6
7

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%).
Fichier principal
Vignette du fichier
ISBI2021_FINAL_VERSION.pdf (594.17 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03131980 , version 1 (04-02-2021)

Identifiers

Cite

Giammarco La Barbera, Pietro Gori, Haithem Boussaid, Bruno Belucci, Alessandro Delmonte, et al.. Automatic size and pose homogenization with Spatial Transformer Network to improve and accelerate pediatric segmentation. ISBI 2021 - IEEE International Symposium on Biomedical Imaging, Apr 2021, Nice, France. pp.1773-1776, ⟨10.1109/ISBI48211.2021.9434090⟩. ⟨hal-03131980⟩
387 View
172 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More