Novel stochastic framework for automatic segmentation of human thigh MRI volumes and its applications in spinal cord injured individuals

Abstract

Severe spinal cord injury (SCI) leads to skeletal muscle atrophy and adipose tissue infiltration in the skeletal muscle, which can result in compromised muscle mechanical output and lead to health-related complications. In this study, we developed a novel automatic 3-D approach for volumetric segmentation and quantitative assessment of thigh Magnetic Resonance Imaging (MRI) volumes in individuals with chronic SCI as well as non-disabled individuals. In this framework, subcutaneous adipose tissue, inter-muscular adipose tissue and total muscle tissue are segmented using linear combination of discrete Gaussians algorithm. Also, three thigh muscle groups were segmented utilizing the proposed 3-D Joint Markov Gibbs Random Field model that integrates first order appearance model, spatial information, and shape model to localize the muscle groups. The accuracy of the automatic segmentation method was tested both on SCI (N = 16) and on non-disabled (N = 14) individuals, showing an overall 0.93±0.06 accuracy for adipose tissue and muscle compartments segmentation based on Dice Similarity Coefficient. The proposed framework for muscle compartment segmentation showed an overall higher accuracy compared to ANTs and STAPLE, two previously validated atlas-based segmentation methods. Also, the framework proposed in this study showed similar Dice accuracy and better Hausdorff distance measure to that obtained using DeepMedic Convolutional Neural Network structure, a well-known deep learning network for 3-D medical image segmentation. The automatic segmentation method proposed in this study can provide fast and accurate quantification of adipose and muscle tissues, which have important health and functional implications in the SCI population.

Deep learning-based thigh muscle segmentation for reproducible fat fraction quantification using fat–water decomposition MRI

“…Our method shows advantages compared to other studies that tackled this challenging task in recent years [21][22][23][24][25]. Kemnitz et al [21] developed a semiautomated thigh muscle segmentation method using an active shape model.…”

“…They segmented the entire muscle region without distinguishing any muscle groups. Mesbah et al [ 24 ] segmented three thigh muscle groups on the fat and water images utilizing a 3-D Joint Markov Gibbs Random Field model. The approach was performed on the preselected 50 central slices in a total of seven steps, which might make it difficult to apply in clinical settings.…”

“…Such a process can lower the accuracy and reproducibility, which is also not feasible for clinical adoption. Although recent studies developed semiautomated or automated algorithms [21][22][23][24][25], they are either based on nonquantitative MRI or difficult to apply in clinical settings [26]. A faster, simpler and fully automated thigh muscle segmentation method for reproducible fat fraction quantification is highly desired.…”

Overview of MR Image Segmentation Strategies in Neuromuscular Disorders

“…Very recently, Mesbah et al ( 53 ) introduced a Markov random field model combining appearance and spatial models with the prior shape information from atlases and so in order to segment the three main muscle groups of the thigh. They reported good DSC scores (0.89 ± 0.05 to 0.95 ± 0.03) but the HD scores were of poor quality with an average ranging from 10.51 ± 6.37 to 31.53 ± 14.24 mm for the medial compartment.…”

Carpal Tunnel Syndrome Secondary to Ganglion Cyst, with Denervation of Abductor Pollicis Brevis

“…Short axis length and short axis: long axis ratio on MRI correlate with distal motor latency (DML) results, and may be used as a less invasive confirmatory findings [9]. Automatic segmentation using machine learning algorithms has shown high levels of accuracy in thigh muscles secondary to chronic spinal cord injuries [19]. It is possible that other muscle groups with denervation atrophy may be similarly amenable to evaluation using machine learning algorithms.…”