Diagnostic accuracy of MRI-derived imaging biomarkers and machine learning-based classification in distal and myofibrillar myopathies.
Authors
Affiliations (27)
Affiliations (27)
- UOC di Neurologia, Fondazione Policlinico Universitario "A. Gemelli" IRCCS, Rome, Italy.
- Università Cattolica del Sacro Cuore, Rome, Italy.
- John Walton Muscular Dystrophy Research Centre, NIHR Biomedical Research Centre: Newcastle, Newcastle University and Newcastle Hospitals NHS Foundation Trust, Newcastle upon Tyne, UK.
- Neuroimmunology and Neuromuscular Disorders Unit, Fondazione IRCCS Istituto Neurologico Carlo Besta, Milan, Italy.
- Neuroradiology, Fondazione IRCCS Istituto Neurologico Carlo Besta, Milan, Italy.
- Department of Neurosciences, Neuromuscular Center, University of Padova, Padova, Italy.
- Institute of Radiology, Department of Medicine-DIMED, University of Padua, Padua, Italy.
- Department of Neurosciences Rita Levi Montalcini, University of Torino, Torino, Italy.
- Department of Neurosciences, Biomedicine and Movement Sciences, University of Verona, Verona, Italy.
- IRCCS Mondino Foundation, Pavia, Italy.
- IRCCS Institute of Neurological Sciences of Bologna, UOC Clinica Neurologica, Bologna, Italy.
- Department of Biomedical and NeuroMotor Sciences, University of Bologna, Bologna, Italy.
- Institute of Experimental Neurology (INSPE), Division of Neuroscience, IRCCS San Raffaele Scientific Institute, Milan, Italy.
- Neurophysiopathology Unit, Fondazione Policlinico Universitario "A. Gemelli" IRCCS, Rome, Italy.
- Fondazione UILDM Lazio Onlus, Rome, Italy.
- Department of Medicine, Surgery and Neurosciences, University of Siena, Siena, Italy.
- Center for Neuromuscular and Neurological Rare Diseases, S. Camillo Forlanini Hospital, Rome, Italy.
- Department of Translational Research and of New Surgical and Medical Technologies, University of Pisa, Pisa, Italy.
- Neuromuscular and Rare Disease Center, Department of Neuroscience, Mental Health and Sensory Organs (NESMOS), Sapienza University, Sant'Andrea Hospital, Rome, Italy.
- Department of Clinical and Experimental Medicine, Neurological Clinic, University of Pisa, Pisa, Italy.
- Department of Clinical and Experimental Medicine, ERN-NMD center for Neuromuscular Disorders of Messina, University of Messina, Messina, Italy.
- Neuroradiology Unit, ASST Papa Giovanni XXIII, Bergamo, Italy.
- Vita-Salute San Raffaele University, Milan, Italy.
- Laboratori de Malalties Neuromusculars, Institut de Recerca de l'Hospital de la Santa Creu i Sant Pau, Barcelona, Spain.
- Centro de Investigación Biomédica en Red en Enfermedades Raras (CIBERER), Barcelona, Spain.
- Folkhalsan Research Center, Helsinki, Finland.
- John Walton Muscular Dystrophy Research Centre, NIHR Biomedical Research Centre: Newcastle, Newcastle University and Newcastle Hospitals NHS Foundation Trust, Newcastle upon Tyne, UK. [email protected].
Abstract
To characterise and validate disease-specific muscle imaging patterns in distal and myofibrillar myopathies, quantify their diagnostic performance, and develop an imaging-based classification framework incorporating machine learning. Muscle MRI and CT scans from a multicentre national cohort of patients with genetically defined distal and myofibrillar myopathies were retrospectively analysed. The pattern of muscle involvement for each disease entity was described, and its sensitivity and specificity calculated. Supervised machine learning algorithms were trained using muscle scores and imaging-derived features, and their diagnostic performance was compared using balanced accuracy. A total of 165 patients (mean age 48 ± 16 years; 87 men), including 138 molecularly confirmed cases spanning 19 disease genes, were analysed. Overall, 6350 muscles were systematically evaluated. Key findings included early biceps femoris short head involvement in GNE myopathy, "fat pockets" in myotilinopathy, and early flexor hallucis longus involvement in desminopathy. All imaging patterns showed high sensitivity and specificity (from 75 to 100%). Among the tested machine learning models, XGBoost achieved the highest performance, correctly distinguishing among 11 genetic disease entities with a balanced accuracy of 69%. Distal and myofibrillar myopathies demonstrate reproducible disease-specific imaging signatures with high diagnostic accuracy. Integration of these imaging biomarkers into a machine learning framework enables systematic prioritisation of likely genetic diagnoses and may facilitate diagnostic work-up in these heterogeneous inherited muscle disorders. Question How accurately do muscle MRI patterns distinguish distal and myofibrillar myopathies, and how do imaging features perform in an updated MRI-based diagnostic algorithm? Findings Disease-specific muscle MRI patterns showed high diagnostic accuracy, while XGBoost achieved the highest balanced accuracy among machine learning models for imaging-based disease classification. Clinical relevance Refined muscle MRI patterns provide diagnostically useful imaging biomarkers in distal and myofibrillar myopathies. Their integration into machine learning-based classification models may facilitate precision diagnostics and guide targeted genetic testing.