Key result
A novel automatic 3-D segmentation approach for thigh MRI volumes achieved an overall Dice Similarity Coefficient accuracy of 0.93±0.06 for adipose tissue and muscle compartments.
Why the study?
Severe spinal cord injury causes skeletal muscle atrophy and adipose infiltration leading to compromised muscle function and health complications, necessitating methods for volumetric segmentation and quantitative assessment of thigh MRI volumes.
Does a novel 3-D automatic segmentation framework improve the accuracy of thigh MRI volume segmentation in individuals with and without spinal cord injury compared to existing methods?
Does a novel 3-D automatic segmentation framework improve the accuracy of thigh MRI volume segmentation in individuals with and without spinal cord injury compared to existing methods?
The proposed automatic 3-D segmentation framework provides fast and accurate quantification of thigh adipose and muscle tissues in SCI and non-disabled individuals, outperforming several existing atlas-based methods.
May accelerate thigh composition research in SCI; leaves open prospective validation before clinical use.
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.
No takes yet. Share an insight, caveat, or question.
Mesbah et al. (2019) studied Chronic spinal cord injury (n=30). Automatic 3-D volumetric segmentation approach vs. ANTs, STAPLE, and DeepMedic Convolutional Neural Network was evaluated on Accuracy for adipose tissue and muscle compartments segmentation based on Dice Similarity Coefficient. A novel automatic 3-D segmentation approach for thigh MRI volumes achieved an overall Dice Similarity Coefficient accuracy of 0.93±0.06 for adipose tissue and muscle compartments.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: