Accuracy of Radiomics in Predicting IDH Mutation Status in Diffuse Gliomas: A Bivariate Meta-Analysis

Abstract

Purpose To perform a systematic review and meta-analysis assessing the predictive accuracy of radiomics in the noninvasive determination of isocitrate dehydrogenase (IDH) status in grade 4 and lower-grade diffuse gliomas. Materials and Methods A systematic search was performed in the PubMed, Scopus, Embase, Web of Science, and Cochrane Library databases for relevant articles published between January 1, 2010, and July 7, 2021. Pooled sensitivity and specificity across studies were estimated. Risk of bias was evaluated using Quality Assessment of Diagnostic Accuracy Studies-2, and methods were evaluated using the radiomics quality score (RQS). Additional subgroup analyses were performed according to tumor grade, RQS, and number of sequences used (PROSPERO ID: CRD42021268958). Results Twenty-six studies that included 3280 patients were included for analysis. The pooled sensitivity and specificity of radiomics for the detection of IDH mutation were 79% (95% CI: 76, 83) and 80% (95% CI: 76, 83), respectively. Low RQS scores were found overall for the included works. Subgroup analyses showed lower false-positive rates in very low RQS studies (RQS < 6) (meta-regression, z = -1.9; P = .02) compared with adequate RQS studies. No substantial differences were found in pooled sensitivity and specificity for the pure grade 4 gliomas group compared with the all-grade gliomas group (81% and 86% vs 79% and 79%, respectively) and for studies using single versus multiple sequences (80% and 77% vs 79% and 82%, respectively). Conclusion The pooled data showed that radiomics achieved good accuracy performance in distinguishing IDH mutation status in patients with grade 4 and lower-grade diffuse gliomas. The overall methodologic quality (RQS) was low and introduced potential bias. Keywords: Neuro-Oncology, Radiomics, Integration, Application Domain, Glioblastoma, IDH Mutation, Radiomics Quality Scoring Supplemental material is available for this article. Published under a CC BY 4.0 license.

Keywords: Application Domain; Glioblastoma; IDH Mutation; Integration; Neuro-Oncology; Radiomics; Radiomics Quality Scoring.

Figure 1:

Flow diagram for selection pipeline according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses 2020 statement. GBM = glioblastoma, IDH = isocitrate dehydrogenase, WoS = Web of Science. (Adapted, under a CC BY 4.0 license, from reference .)

Figure 2:

Forest plots of sensitivity and specificity with 95% CIs per study. Vertical red dashed lines denote summary estimates of sensitivity and specificity.

Figure 3:

Graph of summary receiver operating characteristic (SROC) curve of pooled sensitivity and specificity of all studies included in the meta-analysis (26 studies), with area under the ROC curve of 0.85, indicating good performance of radiomics analysis for predicting isocitrate dehydrogenase mutation. Conf = confidence.

Figure 4:

(A) Comparison of low and good radiomics quality score (RQS) studies with summary receiver operating characteristic (ROC) curves showing that the summary estimates for both groups are separated, but the confidence regions are overlapped. The area under the ROC curve (AUC) for predicting isocitrate dehydrogenase mutation was 0.85 for low RQS and 0.84 for good RQS. (B) Comparison of very low and adequate RQS studies with summary ROC curves showing that the summary estimates for both groups are well separated, but the confidence regions are slightly overlapped. The AUC was 0.92 for low RQS and 0.83 for high RQS. (C) Comparison of grade 4 and mixed-grade (2–4) glioma studies with summary ROC curves. Note the overlapping summary estimates and confidence regions for both groups. The AUC was 0.87 for grade 4 gliomas and 0.82 for mixed-grade gliomas. (D) Comparison of summary ROC curves for single versus multiple sequences and/or modalities. Note the distinct overlap of the summary estimates and confidence regions. Nonetheless, slightly higher false-positive rates were detected in studies using modalities with multiple sequences. The AUC was 0.88 for single sequence modalities and 0.79 for multiple sequence modalities.