Meeting Banner
Abstract #5070

Semi-automatic segmentation of individual muscles in MR images: A new tool dedicated to the follow-up of patients with neuromuscular disorders

Augustin C Ogier1,2, Linda Heskamp3, Alexandre Fouré2, Marc-Emmanuel Bellemare1, Arnaud Le Troter2, Arend Heerschap3, and David Bendahan2

1Aix Marseille Univ, Université de Toulon, CNRS, ENSAM, LSIS, UMR 7296, Marseille, France, 2Aix Marseille Univ, CNRS, Centre de Résonance Magnétique Biologique et Médicale (CRMBM), UMR 7339, Marseille, France, 3Department of Radiology and Nuclear Medicine, Radboud university medical center, Nijmegen, Netherlands

Quantitative magnetic resonance imaging can monitor intramuscular fat accumulation and has proven value for follow-up and therapy evaluation of neuromuscular disease. So far, segmentation processes of individual muscles from quantitative MRI data have been recognized as challenging in healthy subjects and even more challenging in patients for whom borders between muscles can be compromised by the disease process. We designed a semi-automatic segmentation pipeline of individual leg muscles in MR images based on automatic propagation of a minimal number of manually segmented MR slices. This segmentation pipeline allows an accurate follow-up of any MRI biomarkers in neuromuscular disorders.

This abstract and the presentation materials are available to members only; a login is required.

Join Here