Myo-Guide: A Machine Learning-Based Web Application for Neuromuscular Disease Diagnosis With MRI.
Authors
Affiliations (45)
Affiliations (45)
- John Walton Muscular Dystrophy Research Centre, Newcastle University, Newcastle upon Tyne, UK.
- Department of Medicine (Neurology), The Ottawa Hospital, Ottawa, Canada.
- Department of Genetics, Children's Hospital of Eastern Ontario, Ottawa, Canada.
- Ottawa Hospital Research Institute, Ottawa, Canada.
- Copenhagen Neuromuscular Centre, Rigshospitalet, Copenhagen University Hospital, Copenhagen, Denmark.
- Department of Neurology, Huashan Hospital, Fudan University, Shanghai, China.
- Neuromuscular Disorders Unit, Neurology Department, Hospital 12 de Octubre, Madrid, Spain.
- Hospital Universitari Vall d'Hebron, Barcelona, Spain.
- Neuromuscular Disorders Unit, Neurology Department, Hospital Universitari Vall d'Hebron, Barcelona, Spain.
- Department of Brain and Behavioural Sciences, University of Pavia, Pavia, Italy.
- Advanced Imaging and AI Center, Mondino IRCCS Foundation, Pavia, Italy.
- University of Pavia; Mondino IRCCS Foundation, Pavia, Italy.
- UOC di Neurologia, Fondazione Policlinico Universitario Agostino Gemelli IRCCS, Rome, Italy.
- Fondazione Policlinico Universitario Agostino Gemelli, Rome, Italy.
- Pediatric Neurology, Department of Woman and Child Health and Public Health, Child Health Area, Università Cattolica del Sacro Cuore, Rome, Italy.
- Hospital Clínico Universidad de Chile, Santiago de Chile, Chile.
- Programa de Doctorado en Ciencias Médicas y Especialidad, Escuela de Postgrado Facultad de Medicina Universidad de Chile, Santiago, Chile.
- University Hospital Brno, Brno, Czech Republic.
- Neuromuscular Disease Unit, Neurology Department, Hospital Universitario Nuestra Señora de Candelaria, Tenerife, Spain.
- Neuromuscular Disorders Unit, Department of Neurology, Hospital de la Santa Creu i Sant Pau, Barcelona, Spain.
- Biomedical Research Institute Sant Pau (IIB Sant Pau), Barcelona, Spain.
- Centro de Investigaciones Biomédicas en Red en Enfermedades Raras (CIBERER), Madrid, Spain.
- Department of Neurology, Leiden University Medical Center, Leiden, The Netherlands.
- C.J. Gorter MRI Center, Department of Radiology, Leiden University Medical Center, Leiden, The Netherlands.
- Northern Care Alliance NHS Foundation Trust, Manchester, UK.
- Department of Translational Research and of New Surgical and Medical Technologies, University of Pisa, Pisa, Italy.
- Department of Neurology, Pusan National University School of Medicine, Busan, Republic of Korea.
- Centre de Référence des Maladies du Motoneurone, Department of Neurology, Montpellier University Hospital, Montpellier, France.
- Department of Neuroradiology, I2FH Platform, Montpellier University Hospital, Montpellier, France.
- Leeds Teaching Hospitals NHS Trust, Leeds, UK.
- Paris Est University, APHP Henri-Mondor University Hospital, Créteil, France.
- Dubowitz Neuromuscular Centre, UCL Great Ormond Street Institute of Child Health & Great Ormond Street Hospital, London, UK.
- Department of Neuroradiology, Great Ormond Street Hospital for Children NHS Foundation Trust, London, UK.
- Department of Neurology, Faculdade de Medicina da Universidade de São Paulo (FMUSP), São Paulo, Brazil.
- St George's University and St George's University Hospitals NHS Foundation Trust, London, UK.
- Reference Center for Neuromuscular Disorders CHU La Timone, Aix-Marseille University, Marseille, France.
- Aix-Marseille University, CRMBM, CNRS UMR 7339, Marseille, France.
- Department of Neuroscience, Mental Health and Sensory Organs (NESMOS), SAPIENZA University of Rome, Rome, Italy.
- Neuromuscular and Rare Disease Centre, Neurology Unit, Sant'Andrea Hospital, Rome, Italy.
- Neuromuscular Reference Center, Department of Neurology, Universitair Ziekenhuis van Antwerpen, Universiteit Antwerpen, Antwerp, Belgium.
- University Hospital Raymond-Poincaré, Garches, France.
- Neurology Department, Shariati Hospital, Neuromuscular Research Center, Tehran University of Medical Sciences, Tehran, Iran.
- National Institute of Mental Health and Neurosciences (NIMHANS), Bengaluru, India.
- Translational and Clinical Research Institute, Newcastle University, Newcastle upon Tyne, UK.
- Interdisciplinary Computing and Complex BioSystems (ICOS) Research Group, School of Computing, Newcastle University, Newcastle upon Tyne, UK.
Abstract
Neuromuscular diseases (NMDs) are rare disorders characterized by progressive muscle fibre loss, leading to replacement by fibrotic and fatty tissue, muscle weakness and disability. Early diagnosis is critical for therapeutic decisions, care planning and genetic counselling. Muscle magnetic resonance imaging (MRI) has emerged as a valuable diagnostic tool by identifying characteristic patterns of muscle involvement. However, the increasing complexity of these patterns complicates their interpretation, limiting their clinical utility. Additionally, multi-study data aggregation introduces heterogeneity challenges. This study presents a novel multi-study harmonization pipeline for muscle MRI and an AI-driven diagnostic tool to assist clinicians in identifying disease-specific muscle involvement patterns. We developed a preprocessing pipeline to standardize MRI fat content across datasets, minimizing source bias. An ensemble of XGBoost models was trained to classify patients based on intramuscular fat replacement, age at MRI and sex. The SHapley Additive exPlanations (SHAP) framework was adapted to analyse model predictions and identify disease-specific muscle involvement patterns. To address class imbalance, training and evaluation were conducted using class-balanced metrics. The model's performance was compared against four expert clinicians using 14 previously unseen MRI scans. Using our harmonization approach, we curated a dataset of 2961 MRI samples from genetically confirmed cases of 20 paediatric and adult NMDs. The model achieved a balanced accuracy of 64.8% ± 3.4%, with a weighted top-3 accuracy of 84.7% ± 1.8% and top-5 accuracy of 90.2% ± 2.4%. It also identified key features relevant for differential diagnosis, aiding clinical decision-making. Compared to four expert clinicians, the model obtained the highest top-3 accuracy (75.0% ± 4.8%). The diagnostic tool has been implemented as a free web platform, providing global access to the medical community. The application of AI in muscle MRI for NMD diagnosis remains underexplored due to data scarcity. This study introduces a framework for dataset harmonization, enabling advanced computational techniques. Our findings demonstrate the potential of AI-based approaches to enhance differential diagnosis by identifying disease-specific muscle involvement patterns. The developed tool surpasses expert performance in diagnostic ranking and is accessible to clinicians worldwide via the Myo-Guide online platform.