Importance of neural network complexity for the automatic segmentation of individual thigh muscles in MRI images from patients with neuromuscular diseases.
Journal:
Magma (New York, N.Y.)
PMID:
39798067
Abstract
OBJECTIVE: Segmentation of individual thigh muscles in MRI images is essential for monitoring neuromuscular diseases and quantifying relevant biomarkers such as fat fraction (FF). Deep learning approaches such as U-Net have demonstrated effectiveness in this field. However, the impact of reducing neural network complexity remains unexplored in the FF quantification in individual muscles.
Authors
Keywords
Adipose Tissue
Adult
Aged
Algorithms
Databases, Factual
Deep Learning
Female
Humans
Image Interpretation, Computer-Assisted
Image Processing, Computer-Assisted
Magnetic Resonance Imaging
Male
Middle Aged
Muscle, Skeletal
Neural Networks, Computer
Neuromuscular Diseases
Reproducibility of Results
Thigh