From the Neuromuscular Disorders Unit, Neurology Department (J.V.-D., J.A.-P., I.I., J.D.-M.), and Radiology Department (C.N.-P., J.L.), Hospital de la Santa Creu I Sant Pau, Barcelona, Spain; UOC di Neurologia (G.T.), Fondazione Policlinico Universitario A. Gemelli IRCCS, Rome, Italy; Copenhagen Neuromuscular Center, Department of Neurology (J.V.), Rigshospitalet, University of Copenhagen, Denmark; John Walton Muscular Dystrophy Research Centre (V.S., J.D.-M.), University of Newcastle, Newcastle Upon Tyne, UK; Hospital Universitario Donostia (R.F.-T.); and Centro de Investigación Biomédica en Red en Enfermedades Raras (CIBERER) (I.I., J.D.-M.), Madrid, Spain.
Neurology. 2020 Mar 10;94(10):e1094-e1102. doi: 10.1212/WNL.0000000000009068. Epub 2020 Feb 6.
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.
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 supervised machine learning was applied to develop a model useful to identify the correct diagnosis. Two thousand different models were generated and the one with highest 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 field.
A total of 976 lower limbs MRIs from 10 different MDs were used. The best model obtained had 95.7% accuracy, with 92.1% sensitivity and 99.4% specificity. When compared with experts on the field, the diagnostic accuracy of the model generated was significantly higher in a new set of 20 MRIs.
Machine learning can help doctors in the diagnosis of muscle dystrophies by analyzing patterns of muscle fatty replacement in muscle MRI. This tool can be helpful in daily clinics and in the interpretation of the results of next-generation sequencing tests.
This study provides Class II evidence that a muscle MRI-based artificial intelligence tool accurately diagnoses muscular dystrophies.
肌肉萎缩症 (MDs) 的基因诊断传统上由临床表型、肌肉活检和肌肉 MRI 数据指导。肌肉 MRI 根据肌肉脂肪替代模式来提示诊断。然而，不同疾病之间的模式存在重叠，并且对特定疾病模式的了解有限。我们的目标是开发一种基于软件的工具，可以识别肌肉 MRI 模式，从而辅助 MDs 的诊断。
我们收集了来自 10 种不同 MDs 的 976 例骨盆和下肢 T1 加权肌肉 MRI。使用 Mercuri 评分量化脂肪替代情况，并生成包含数值数据的文件。应用随机森林监督机器学习来开发一种可用于识别正确诊断的模型。生成了 2000 个不同的模型，并选择了具有最高准确性的模型。使用一组新的 20 个 MRI 来测试模型的准确性，并将结果与该领域的 4 位专家提出的诊断进行比较。
共使用了来自 10 种不同 MDs 的 976 例下肢 MRI。获得的最佳模型具有 95.7%的准确性，灵敏度为 92.1%，特异性为 99.4%。与该领域的专家相比，在一组新的 20 个 MRI 中，生成的模型的诊断准确性显著更高。
机器学习可以通过分析肌肉 MRI 中肌肉脂肪替代模式来帮助医生诊断肌肉萎缩症。该工具可在日常临床中以及下一代测序测试结果的解释中提供帮助。
这项研究提供了 II 级证据，证明基于肌肉 MRI 的人工智能工具可以准确诊断肌肉萎缩症。
