Machine Learning Models for Sarcopenia Identification Based on Radiomic Features of Muscles in Computed Tomography

Abstract

The diagnosis of sarcopenia requires accurate muscle quantification. As an alternative to manual muscle mass measurement through computed tomography (CT), artificial intelligence can be leveraged for the automation of these measurements. Although generally difficult to identify with the naked eye, the radiomic features in CT images are informative. In this study, the radiomic features were extracted from L3 CT images of the entire muscle area and partial areas of the erector spinae collected from non-small cell lung carcinoma (NSCLC) patients. The first-order statistics and gray-level co-occurrence, gray-level size zone, gray-level run length, neighboring gray-tone difference, and gray-level dependence matrices were the radiomic features analyzed. The identification performances of the following machine learning models were evaluated: logistic regression, support vector machine (SVM), random forest, and extreme gradient boosting (XGB). Sex, coarseness, skewness, and cluster prominence were selected as the relevant features effectively identifying sarcopenia. The XGB model demonstrated the best performance for the entire muscle, whereas the SVM was the worst-performing model. Overall, the models demonstrated improved performance for the entire muscle compared to the erector spinae. Although further validation is required, the radiomic features presented here could become reliable indicators for quantifying the phenomena observed in the muscles of NSCLC patients, thus facilitating the diagnosis of sarcopenia.

Keywords: computed tomography; identification; machine learning; radiomic feature; sarcopenia.

Figure 1

Flowchart of sarcopenia data collection and analysis. NSCLC, non-small cell lung carcinoma; GLCM, gray-level co-occurrence matrix; GLSZM, gray-level size zone matrix; GLRLM, gray-level run length matrix; NGTDM, neighboring gray-tone difference matrix; GLDM, gray-level dependence matrix; SMOTE, synthetic minority oversampling technique; LR, logistic regression; SVM, support vector machine; RF, random forest; XGB, extreme gradient boosting.

Figure 2

Areas of body components identified by Gachon_DeepBody: muscle (green), subcutaneous fat (red), visceral fat (yellow).

Figure 3

Examples of ROIs for two types of muscles. ROI for the entire muscle area (left), ROI for the left and right erector spinae muscles (right).

Figure 4

Feature importance plot showing the relative importance of four features with respect to the identification of sarcopenia and non-sarcopenia groups.

Figure 5

Comparison of ROC curves among different machine learning models for the identification of sarcopenia. The left graph presents the ROC curves of the entire muscle, where XGB has the highest AUC. The right graph shows those of the erect spinae muscle, where LR has the highest AUC. LR, logistic regression; SVM, support vector machine; RF, random forest; XGB, extreme gradient boosting; ROC, receiver operating characteristic; AUC, area under the curve.

Figure 6

Heatmap of the effects of the functions selected in each machine learning model for the identification of sarcopenia. The higher the heatmap value (that is, the closer the color is to white), the more intense the impact of a feature on the identification of sarcopenia. LR, logistic regression; SVM, support vector machine; RF, random forest; XGB, extreme gradient boosting.