Accuracy of Machine Learning Algorithms for the Classification of Molecular Features of Gliomas on MRI: A Systematic Literature Review and Meta-Analysis

Abstract

Treatment planning and prognosis in glioma treatment are based on the classification into low- and high-grade oligodendroglioma or astrocytoma, which is mainly based on molecular characteristics (IDH1/2- and 1p/19q codeletion status). It would be of great value if this classification could be made reliably before surgery, without biopsy. Machine learning algorithms (MLAs) could play a role in achieving this by enabling glioma characterization on magnetic resonance imaging (MRI) data without invasive tissue sampling. The aim of this study is to provide a performance evaluation and meta-analysis of various MLAs for glioma characterization. Systematic literature search and meta-analysis were performed on the aggregated data, after which subgroup analyses for several target conditions were conducted. This study is registered with PROSPERO, CRD42020191033. We identified 724 studies; 60 and 17 studies were eligible to be included in the systematic review and meta-analysis, respectively. Meta-analysis showed excellent accuracy for all subgroups, with the classification of 1p/19q codeletion status scoring significantly poorer than other subgroups (AUC: 0.748, p = 0.132). There was considerable heterogeneity among some of the included studies. Although promising results were found with regard to the ability of MLA-tools to be used for the non-invasive classification of gliomas, large-scale, prospective trials with external validation are warranted in the future.

Gaps and Opportunities of Artificial Intelligence Applications for Pediatric Oncology in European Research: A Systematic Review of Reviews and a Bibliometric Analysis

“…, and Bhandari et al. , the ability to predict the genomic profile of glioblastoma, namely IDH status, MGMT promoter methylation status, and 1p/19q codeletion status, was investigated with promising perspectives ( 22 , 25 , 29 ). A satisfactory accuracy was also found in predicting the prognosis of patients, with a sensitivity range of 78%–98% and specificity range of 76%–95% reported in the review by Sarkiss et colleagues ( 18 ).…”

Diagnostic Accuracy of Machine Learning Models on Mammography in Breast Cancer Classification: A Meta-Analysis

“…Another meta-analysis study focusing on deep learning reported good diagnostic accuracy for breast cancer detection using a mammogram, US, MRI and DBT with pooled AUCs of 0.87, 0.91, 0.87 and 0.91, respectively [ 71 ]. However, several meta-analysis studies that assessed the diagnostic accuracy of machine learning models on MRI in gliomas, prostate cancer and meningioma reported slightly lower AUCs of 0.88, 0.86 and 0.75, respectively [ 72 , 73 , 74 ]. This study included all previous studies that used any machine learning algorithms on mammography for breast cancer detection.…”

Artificial Intelligence in Brain Tumour Surgery—An Emerging Paradigm

“…Specific to intracranial tumours, ML-based imaging interpretation has made great leaps forward in the past decade. The molecular characteristics of gliomas, such as the presence of IDH mutation or 1p/19q mutations, are closely linked to the natural history of the disease, and are known to impact the efficacy of various treatments [ 68 ]. The ability to predict these features from imaging data, potentially circumventing the need for invasive biopsies, has been a focus of ML radiomic research for the past decade.…”