Diagnostic performance of deep learning for predicting glioma isocitrate dehydrogenase and 1p/19q co-deletion in MRI: a systematic review and meta-analysis

TL;DR

This systematic review and meta-analysis evaluates the diagnostic accuracy of deep learning-based radiomics models in predicting glioma molecular markers IDH mutation and 1p/19q co-deletion from MRI, highlighting methodological factors affecting performance.

Contribution

It provides a comprehensive meta-analysis of DL radiomics for glioma molecular prediction and identifies key methodological factors influencing accuracy and generalizability.

Findings

Pooled sensitivity for IDH prediction: 0.80

Pooled specificity for IDH prediction: 0.85

Meta-regression highlights segmentation method as a key factor

Abstract

Objectives We aimed to evaluate the diagnostic performance of deep learning (DL)-based radiomics models for the noninvasive prediction of isocitrate dehydrogenase (IDH) mutation and 1p/19q co-deletion status in glioma patients using MRI sequences, and to identify methodological factors influencing accuracy and generalizability. Materials and methods Following PRISMA guidelines, we systematically searched major databases (PubMed, Scopus, Embase, Web of Science, and Google Scholar) up to March 2025, screening studies that utilized DL to predict IDH and 1p/19q co-deletion status from MRI data. We assessed study quality and risk of bias using the Radiomics Quality Score and the QUADAS-2 tool. Our meta-analysis employed a bivariate model to compute pooled sensitivity and specificity, and meta-regression to assess interstudy heterogeneity. Results Among the 1517 unique publications, 104 were included in the qualitative synthesis, and 72 underwent meta-analysis. Pooled estimates for IDH prediction in test cohorts yielded a sensitivity of 0.80 and specificity of 0.85. For 1p/19q co-deletion, sensitivity was 0.75 and specificity was 0.82. Meta-regression identified the tumor segmentation method and the extent of DL integration into the radiomics pipeline as significant contributors to interstudy variability. Conclusion Although DL models demonstrate strong potential for noninvasive molecular classification of gliomas, clinical translation requires several critical steps: harmonization of multi-center MRI data using techniques such as histogram matching and DL-based style transfer; adoption of standardized and automated segmentation protocols; extensive multi-center external validation; and prospective clinical validation.