Noninvasive Determination of <i>IDH</i> and 1p19q Status of Lower-grade Gliomas Using MRI Radiomics: A Systematic Review
Abhishta Bhandari, Rebecca Liong, Jarrad Koppen, Shashidhar Venkatesh Murthy, Arian Lasocki
Abstract
<h3>BACKGROUND:</h3> Determination of <i>isocitrate dehydrogenase</i> (<i>IDH</i>) status and, if <i>IDH</i>-mutant, assessing 1p19q codeletion are an important component of diagnosis of World Health Organization grades II/III or lower-grade gliomas. This has led to research into noninvasively correlating imaging features (“radiomics”) with genetic status. <h3>PURPOSE:</h3> Our aim was to perform a diagnostic test accuracy systematic review for classifying <i>IDH</i> and 1p19q status using MR imaging radiomics, to provide future directions for integration into clinical radiology. <h3>DATA SOURCES:</h3> Ovid (MEDLINE), Scopus, and the Web of Science were searched in accordance with the Preferred Reporting Items for Systematic Reviews and Meta-Analyses for Diagnostic Test Accuracy guidelines. <h3>STUDY SELECTION:</h3> Fourteen journal articles were selected that included 1655 lower-grade gliomas classified by their <i>IDH</i> and/or 1p19q status from MR imaging radiomic features. <h3>DATA ANALYSIS:</h3> For each article, the classification of <i>IDH</i> and/or 1p19q status using MR imaging radiomics was evaluated using the area under curve or descriptive statistics. Quality assessment was performed with the Quality Assessment of Diagnostic Accuracy Studies 2 tool and the radiomics quality score. <h3>DATA SYNTHESIS:</h3> The best classifier of <i>IDH</i> status was with conventional radiomics in combination with convolutional neural network–derived features (area under the curve = 0.95, 94.4% sensitivity, 86.7% specificity). Optimal classification of 1p19q status occurred with texture-based radiomics (area under the curve = 0.96, 90% sensitivity, 89% specificity). <h3>LIMITATIONS:</h3> A meta-analysis showed high heterogeneity due to the uniqueness of radiomic pipelines. <h3>CONCLUSIONS:</h3> Radiogenomics is a potential alternative to standard invasive biopsy techniques for determination of <i>IDH</i> and 1p19q status in lower-grade gliomas but requires translational research for clinical uptake.