Semi-automatic segmentation of whole-body images in longitudinal studies Article - 2020

Eloïse Grossiord, Laurent Risser, Trouillard Thomas, Salim Kanoun, Aziza Richard, Chiron Harnold, Loic Ysebaert, François Malgouyres, Soleakhena Ken

Eloïse Grossiord, Laurent Risser, Trouillard Thomas, Salim Kanoun, Aziza Richard, Chiron Harnold, Loic Ysebaert, François Malgouyres, Soleakhena Ken, « Semi-automatic segmentation of whole-body images in longitudinal studies  », Biomedical Physics and Engineering Express, à paraître

Abstract

We propose a semi-automatic segmentation pipeline designed for longitudinal studies considering structures with large anatomical variability, where expert interactions are required for relevant segmentations. Our pipeline builds on the regularized Fast Marching (rFM) segmentation approach by Risser et al. (2018). It consists in transporting baseline multi-label FM seeds on follow-up images, selecting the relevant ones and nally performing the rFM approach. It showed increased, robust and faster results compared to clinical manual segmentation. Our method was evaluated on 3D synthetic images and patients’ whole-body MRI. It allowed a robust and exible handling of organs longitudinal deformations while considerably reducing manual interventions.

Voir la notice complète sur HAL

Actualités