Radiomics analysis for glioma malignancy evaluation using diffusion kurtosis and tensor imaging

Abstract Purpose A noninvasive diagnostic method to predict the degree of malignancy accurately would be of great help in glioma management. This study aimed to create a highly accurate machine learning model to perform glioma grading. Methods Preoperative MRI acquired for cases of glioma operated on at our institution from October 2014 through January 2018 were obtained retrospectively. Six types of MRI sequences (T 2 -weighted image, diffusion-weighted image, apparent diffusion coefficient [ADC], fractional anisotropy, and mean kurtosis [MK]) were chosen for analysis; 476 features were extracted semi-automatically for each sequence (2,856 features in total). Recursive feature elimination was used to select significant features for a machine learning model that distinguishes glioblastoma from lower-grade glioma (grades II/III). Results Fifty-five datasets from 54 cases were obtained (14 grade II gliomas, 12 grade III gliomas, and 29 glioblastomas), of which 44 and 11 datasets were used for machine learning and independent testing, respectively. We detected 504 features with significant differences (false discovery rate Conclusions Our machine learning model accurately predicted glioma tumor grade. The ADC and MK sequences produced particularly useful features.