AUTOMATIC 3-D MUSCLE AND FAT SEGMENTATION OF THIGH MAGNETIC RESONANCE IMAGES IN INDIVIDUALS WITH SPINAL CORD INJURY

Spinal cord injured (SCI) individuals are often subject to skeletal muscles deterioration and adipose tissue gain in paralyzed muscles. These negative impacts can limit motor functions and lead to secondary complications such as diabetes, cardiovascular diseases and metabolic syndrome. In this study, we proposed an accurate and fast automatic framework for thigh muscle and fat volume segmentation using magnetic resonance 3-D images, which is aimed at quantifying the impact of SCI and different rehabilitative interventions for these individuals. In this framework, the subcutaneous, intermuscular fat volumes were segmented using a Linear Combination of Discrete Gaussians (LCDG) algorithm. In order to segment muscle group volumes, each MRI volume was initially registered to a training database using a 3-D Cubic B-splines based method. As a second step, a 3-D level-set method was developed utilizing the Joint Markov Gibbs Random Field (MGRF) model that integrates first order appearance model of the muscles, spatial information, and shape model to localize the muscle groups. The results of testing the new method on 15 MRI datasets from 10 SCI and 5 non-disabled subjects showed accuracy of 87.10% for fat segmentation and 96.71% for muscle group segmentation based on Dice similarity coefficient measurements.