Study of the accuracy of a machine learning muscle MRI-based tool for diagnosis the of muscular dystrophies

Objective: Genetic diagnosis of muscular dystrophies (MDs) has classically been guided by clinical presentation, muscle biopsy and muscle MRI data. Muscle MRI suggests diagnosis based on the pattern of muscle fatty replacement. However, patterns overlap between different disorders and knowledge about disease-specific patterns is limited. Our aim was to develop a software-based tool that can recognize muscle MRI patterns and thus aid diagnosis of MDs. Methods: We collected 976 pelvic and lower limbs T1 weighted muscle MRIs from 10 different MDs. Fatty replacement was quantified using Mercuri score and files containing the numeric data were generated. Random forest unsupervised machine learning was applied to develop a model useful to identify the correct diagnosis. 2000 different models were generated and the one with higher accuracy was selected. A new set of 20 MRIs was used to test the accuracy of the model, and the results were compared with diagnoses proposed by 4 specialists in the...