Multiparametric MRI Features Predict the SYP Gene Expression in Low-Grade Glioma Patients: A Machine Learning-Based Radiomics Analysis

Abstract

Purpose: Synaptophysin (SYP) gene expression levels correlate with the survival rate of glioma patients. This study aimed to explore the feasibility of applying a multiparametric magnetic resonance imaging (MRI) radiomics model composed of a convolutional neural network to predict the SYP gene expression in patients with glioma.

Method: Using the TCGA database, we examined 614 patients diagnosed with glioma. First, the relationship between the SYP gene expression level and outcome of survival rate was investigated using partial correlation analysis. Then, 7266 patches were extracted from each of the 108 low-grade glioma patients who had available multiparametric MRI scans, which included preoperative T1-weighted images (T1WI), T2-weighted images (T2WI), and contrast-enhanced T1WI images in the TCIA database. Finally, a radiomics features-based model was built using a convolutional neural network (ConvNet), which can perform autonomous learning classification using a ROC curve, accuracy, recall rate, sensitivity, and specificity as evaluation indicators.

Results: The expression level of SYP decreased with the increase in the tumor grade. With regard to grade II, grade III, and general patients, those with higher SYP expression levels had better survival rates. However, the SYP expression level did not show any significant association with the outcome in Level IV patients.

Conclusion: Our multiparametric MRI radiomics model constructed using ConvNet showed good performance in predicting the SYP gene expression level and prognosis in low-grade glioma patients.

Keywords: MRI radiomics model; convolutional neural network; glioma; machine learning; synaptophysin (SYP).

Figure 1

The learning framework of the ResNet50.

Figure 2

The structure of the residual block of the ResNet.

Figure 3

Expression of SYP genes in different grades of gliomas and their relationship with the survival rate of patients. (A) Expression level of SYP genes is significantly correlated with the grade of gliomas. (B–E) In terms of patients with grade II, III and the overall, the higher the level of SYP expression, the higher the survival rate of patients, while in terms of patients with grade IV, the level of SYP expression is not related to prognosis.

Figure 4

Forest map of clinical characters in univariate (A) and multivariate analysis (B). The coordinate of the blue diamond represents the odds ratio. Univariate and multivariate Cox regression analysis were performed. Subgroup with a value of p < 0.05 was considered statistically significant.

Figure 5

Convolutional neural network for the extraction of image features. Through the automatic extraction of image features by class activation mapping (CAM), the areas marked red in the image are the ones with high activation response to the visualized image.

Figure 6

The prediction potential of convolutional neural network for the expression level of SYP genes. (A) Evaluation of radiomics model constructed by convolutional neural network through ROC. (B) Confusion matrix of the radiomics model. The upper left is true negative, the lower left is false negative, the upper right is false positive, and the lower right is true positive.