Department of Radiology, Saitama Medical University Hospital, 38 Morohongo Moroyama-machi, Iruma-gun, Saitama, Japan.
Department of Rheumatology and Applied Immunology, Saitama Medical University Hospital, 38 Morohongo Moroyama-machi, Iruma-gun, Saitama, Japan.
Sci Rep. 2021 May 10;11(1):9821. doi: 10.1038/s41598-021-89311-3.
To develop a machine learning (ML) model that predicts disease groups or autoantibodies in patients with idiopathic inflammatory myopathies (IIMs) using muscle MRI radiomics features. Twenty-two patients with dermatomyositis (DM), 14 with amyopathic dermatomyositis (ADM), 19 with polymyositis (PM) and 19 with non-IIM were enrolled. Using 2D manual segmentation, 93 original features as well as 93 local binary pattern (LBP) features were extracted from MRI (short-tau inversion recovery [STIR] imaging) of proximal limb muscles. To construct and compare ML models that predict disease groups using each set of features, dimensional reductions were performed using a reproducibility analysis by inter-reader and intra-reader correlation coefficients, collinearity analysis, and the sequential feature selection (SFS) algorithm. Models were created using the linear discriminant analysis (LDA), quadratic discriminant analysis (QDA), support vector machine (SVM), k-nearest neighbors (k-NN), random forest (RF) and multi-layer perceptron (MLP) classifiers, and validated using tenfold cross-validation repeated 100 times. We also investigated whether it was possible to construct models predicting autoantibody status. Our ML-based MRI radiomics models showed the potential to distinguish between PM, DM, and ADM. Models using LBP features provided better results, with macro-average AUC values of 0.767 and 0.714, accuracy of 61.2 and 61.4%, and macro-average recall of 61.9 and 59.8%, in the LDA and k-NN classifiers, respectively. In contrast, the accuracies of radiomics models distinguishing between non-IIM and IIM disease groups were low. A subgroup analysis showed that classification models for anti-Jo-1 and anti-ARS antibodies provided AUC values of 0.646-0.853 and 0.692-0.792, with accuracy of 71.5-81.0 and 65.8-78.3%, respectively. ML-based TA of muscle MRI may be used to predict disease groups or the autoantibody status in patients with IIM and is useful in non-invasive assessments of disease mechanisms.
利用肌肉 MRI 放射组学特征，开发一种机器学习（ML）模型，以预测特发性炎性肌病（IIM）患者的疾病组或自身抗体。共纳入 22 例皮肌炎（DM）患者、14 例无肌病性皮肌炎（ADM）患者、19 例多发性肌炎（PM）患者和 19 例非 IIM 患者。使用 2D 手动分割，从近端肢体肌肉的 MRI（短 tau 反转恢复 [STIR] 成像）中提取了 93 个原始特征和 93 个局部二值模式（LBP）特征。为了构建和比较使用每组特征预测疾病组的 ML 模型，通过读者间和读者内相关性系数、共线性分析和顺序特征选择（SFS）算法进行了降维。使用线性判别分析（LDA）、二次判别分析（QDA）、支持向量机（SVM）、k-最近邻（k-NN）、随机森林（RF）和多层感知器（MLP）分类器创建模型，并使用 10 倍交叉验证重复 100 次进行验证。我们还研究了是否可以构建预测自身抗体状态的模型。我们基于 ML 的 MRI 放射组学模型显示出区分 PM、DM 和 ADM 的潜力。使用 LBP 特征的模型提供了更好的结果，LDA 和 k-NN 分类器的宏观平均 AUC 值分别为 0.767 和 0.714，准确性分别为 61.2%和 61.4%，宏观平均召回率分别为 61.9%和 59.8%。相比之下，区分非 IIM 和 IIM 疾病组的放射组学模型的准确性较低。亚组分析表明，针对抗 Jo-1 和抗 ARS 抗体的分类模型的 AUC 值为 0.646-0.853 和 0.692-0.792，准确性分别为 71.5%-81.0%和 65.8%-78.3%。基于 ML 的肌肉 MRI TA 可用于预测 IIM 患者的疾病组或自身抗体状态，并且在疾病机制的非侵入性评估中很有用。
