Zuo Huayan, Wang Qiyang, Bi Guoli, Wang Yijin, Yang Guang, Zhang Chengxiu, Song Yang, Wu Yunzhu, Gong Xiarong, Bi Qiu
The Affiliated Hospital of Kunming University of Science and Technology, Department of MRI, the First People's Hospital of Yunnan Province, Kunming, Yunnan 650500, China.
Department of Orthopedic Surgery, the Key Laboratory of Digital Orthopaedics of Yunnan Provincial, Yunnan Province Spinal Cord Disease Clinical Medical Center, the First People's Hospital of Yunnan Province, the Affiliated Hospital of Kunming University of Science and Technology, Kunming, Yunnan 650032, China.
Eur J Radiol. 2024 Dec;181:111748. doi: 10.1016/j.ejrad.2024.111748. Epub 2024 Sep 19.
To compare the performance of MRI-based Gaussian mixture model (GMM), K-means clustering, and Otsu unsupervised algorithms in predicting sarcopenia and to develop a combined model by integrating clinical indicators.
Retrospective analysis was conducted on clinical and lumbar MRI data from 118 patients diagnosed with sarcopenia and 222 patients without the sarcopenia. All patients were randomly divided into training and validation groups in a 7:3 ratio. Regions of interest (ROI), specifically the paravertebral muscles at the L3/4 intervertebral disc level, were delineated on axial T2-weighted images (T2WI). The Gaussian mixture model (GMM), K-means clustering, and Otsu's thresholding algorithms were employed to automatically segment muscle and adipose tissues at both the cohort and case levels. Subsequently, the mean signal intensity, volumes, and percentages of these tissues were calculated and compared. Logistic regression analyses were conducted to construct models and identify independent predictors of sarcopenia. An combined model was developed by combining the optimal magnetic resonance imaging (MRI) model and clinical predictors. The performance of the constructed model was assessed using receiver operating characteristic (ROC) curve analysis.
Age, BMI, and serum albumin were identified as independent clinical predictors of sarcopenia. The cohort-level GMM demonstrated the best predictive performance both in the training group (AUC=0.840) and validation group (AUC=0.800), while the predictive performance of the other models was lower than that of the clinical model both in the training and validation groups. After combining the cohort-level GMM with the independent clinical predictors, the AUC of the training and validation groups increased to 0.871 and 0.867, respectively.
The cohort-level GMM shows potential in predicting sarcopenia, and the incorporation of independent clinical predictors further increased the performance.
比较基于磁共振成像（MRI）的高斯混合模型（GMM）、K均值聚类和大津无监督算法在预测肌肉减少症方面的性能，并通过整合临床指标开发一种联合模型。
对118例诊断为肌肉减少症的患者和222例未患肌肉减少症的患者的临床及腰椎MRI数据进行回顾性分析。所有患者按7:3的比例随机分为训练组和验证组。在轴向T2加权图像（T2WI）上勾勒出感兴趣区域（ROI），具体为L3/4椎间盘水平的椎旁肌。采用高斯混合模型（GMM）、K均值聚类和大津阈值算法在队列和病例水平上自动分割肌肉和脂肪组织。随后，计算并比较这些组织的平均信号强度、体积和百分比。进行逻辑回归分析以构建模型并确定肌肉减少症的独立预测因素。通过结合最佳磁共振成像（MRI）模型和临床预测因素开发联合模型。使用受试者工作特征（ROC）曲线分析评估构建模型的性能。
年龄、体重指数（BMI）和血清白蛋白被确定为肌肉减少症的独立临床预测因素。队列水平的GMM在训练组（AUC = 0.840）和验证组（AUC = 0.800）中均表现出最佳预测性能，而其他模型在训练组和验证组中的预测性能均低于临床模型。将队列水平的GMM与独立临床预测因素相结合后，训练组和验证组的AUC分别增至0.871和0.867。
队列水平的GMM在预测肌肉减少症方面显示出潜力，纳入独立临床预测因素可进一步提高性能。
