Glioma is the most common primary malignant tumor of the central nervous system,and there are great differences in treatment and prognosis among different types of glioma. An accurate understanding of the pathological classification,molecular classification and differential diagnosis of glioma or other information before surgery is conducive to the clinical treatment and postoperative assessment of patients' prognosis,so as to improve the quality of life of patients. Radiomics has provided great help for the preoperative detection of glioma patients by non-invasive prediction of molecular types of different gliomas through high-throughput extraction of quantitative features of lesions. MRI is safe and radiation-free. The application of structure and multiple functional sequences provides us with clinical information at different levels. This article reviews the application of MRI-based radiomics in molecular classification of glioma.

Glioma is the most common primary malignant tumor of the central nervous system,and there are great differences in treatment and prognosis among different types of glioma. An accurate understanding of the pathological classification,molecular classification and differential diagnosis of glioma or other information before surgery is conducive to the clinical treatment and postoperative assessment of patients' prognosis,so as to improve the quality of life of patients. Radiomics has provided great help for the preoperative detection of glioma patients by non-invasive prediction of molecular types of different gliomas through high-throughput extraction of quantitative features of lesions. MRI is safe and radiation-free. The application of structure and multiple functional sequences provides us with clinical information at different levels. This article reviews the application of MRI-based radiomics in molecular classification of glioma.