From the Reference Center for Neuromuscular Diseases and ALS (E.F., E.D., S.A.), La Timone University Hospital, Marseille; UMR CNRS 7339 (E.F., C.P.M., M.G., D.B.), Center for Magnetic Resonance in Biology and Medicine, Marseille; CNRS, LIS (M.A.H., M.-E.B.), UMR 7286, Medicine Faculty (E.D.), and Inserm, GMGF (S.A.), Aix-Marseille University, France.
Neurology. 2024 Nov 26;103(10):e210013. doi: 10.1212/WNL.0000000000210013. Epub 2024 Oct 24.
Intramuscular fat fraction (FF), assessed with quantitative MRI (qMRI), has emerged as one of the few responsive outcome measures in CMT1A patients. The main limitation for its use in future therapeutic trials is the time required for the manual segmentation of individual muscles. This study aimed to evaluate the accuracy and responsiveness of a fully automatic artificial intelligence (AI)-based segmentation pipeline to assess disease progression in a cohort of CMT1A patients over 1 year.
Twenty CMT1A patients were included in this observational, prospective, longitudinal study. FF was measured twice a year apart using qMRI in the lower limbs. Individual muscle segmentation was performed fully automatically using a trained convolutional neural network with or without human quality check (QC). The corresponding results were compared with those obtained by fully manual (FM) segmentation using the Dice similarity coefficient (DSC). FF progression and its standardized response mean (SRM) were also computed in individual muscles over the single central slice and a 3D volume to define the most sensitive region of interest.
AI-based segmentation showed excellent DSC values (>0.90). Significant global FF progression was observed at thigh (+0.71% ± 1.28%; = 0.016) and leg (+1.73% ± 2.88%, = 0.007) levels, similarly to that calculated using the FM technique ( = 0.363 and = 0.634). FF progression of each individual muscle was comparable when computed from either the central slice or the 3D volume. The best SRM value (0.70) was obtained for the FF progression computed using the AI-based technique with human QC in the 3D volume at the leg level. The time required for fully automatic segmentation using AI with a QC was 10 hours for the entire data set compared with 90 hours for the FM.
qMRI combined with AI-based segmentation can be considered as a process ready for assessing longitudinal FF changes in CMT1A patients. Given the slow FF progression at a thigh level and the large heterogeneity between muscles and individuals, FF should be quantified from a 3D volume at the leg level for longitudinal analyses. A QC performed after the AI-based segmentation is still advised given the increased SRM value.
使用定量磁共振成像（qMRI）评估的肌肉内脂肪分数（FF）已成为 CMT1A 患者中为数不多的反应性结局指标之一。其在未来治疗试验中的主要限制是个体肌肉手动分割所需的时间。本研究旨在评估完全自动化人工智能（AI）分割管道的准确性和反应性，以评估 1 年内 CMT1A 患者队列的疾病进展。
本研究纳入了 20 例 CMT1A 患者，采用 qMRI 每年两次测量下肢的 FF。使用经过训练的卷积神经网络进行完全自动分割，或进行 AI 分割后进行人工质量检查（QC）。将相应结果与使用完全手动（FM）分割的结果（使用 Dice 相似系数（DSC））进行比较。还在单个中央切片和 3D 体积上计算了各个肌肉的 FF 进展及其标准化反应均值（SRM），以确定最敏感的感兴趣区。
基于 AI 的分割方法具有出色的 DSC 值（>0.90）。在大腿（+0.71%±1.28%，=0.016）和小腿（+1.73%±2.88%，=0.007）水平均观察到显著的全局 FF 进展，与使用 FM 技术计算的结果相似（=0.363 和=0.634）。当从中央切片或 3D 体积计算时，各个肌肉的 FF 进展情况相似。使用 AI 技术结合 3D 体积中的人工 QC 计算得出的 FF 进展的最佳 SRM 值（0.70）。与 FM 相比，AI 结合 QC 的完全自动分割所需的时间为整个数据集的 10 小时，而 FM 则为 90 小时。
qMRI 联合基于 AI 的分割技术可用于评估 CMT1A 患者的纵向 FF 变化。鉴于大腿水平的 FF 进展缓慢，以及肌肉和个体之间的异质性较大，应在小腿水平的 3D 体积上进行 FF 定量分析。由于 SRM 值增加，建议在 AI 分割后进行 QC。
