Abstract
Skeletal muscle biopsy commonly used for light microscopic, electron microscopic and biochemical and transcriptional evaluation remains the gold standard for establishing the etiology of a myopathy. While most myopathies exhibit one or more phenotypes, early stages or several metabolic myopathies often exhibit normal muscle morphology, making diagnosis difficult. In such cases where standard staining techniques fail to offer definitive diagnostic information, a combination of expensive and time-consuming electron microscopy and biochemical testing is required to provide definitive diagnosis. As a step toward overcoming these limitations in diagnostic pathology of skeletal muscle tissue, here we report the application of parameter estimation machine learning approaches on immunofluorescent images of human skeletal muscle tissue acquired using fluorescent microscopy. The machine learning morphometric approach enables the recognition of fine cellular changes in skeletal muscle tissue, allowing determination of skeletal muscle remodeling as a consequence of immobilization.
Competing Interest Statement
The authors have declared no competing interest.
