Abstract
Purpose This study aimed to estimate the diagnostic accuracy of machine learning- (ML-) based radiomics in differentiating high-grade gliomas (HGG) from low-grade gliomas (LGG) and to identify potential covariates that could affect the diagnostic accuracy of ML-based radiomic analysis in classifying gliomas. Method A primary literature search of the PubMed database was conducted to find all related literatures in English between January 1, 2009, and May 1, 2020, with combining synonyms for “machine learning,” “glioma,” and “radiomics.” Five retrospective designed original articles including LGG and HGG subjects were chosen. Pooled sensitivity, specificity, their 95% confidence interval, area under curve (AUC), and hierarchical summary receiver-operating characteristic (HSROC) models were obtained. Result The pooled sensitivity when diagnosing HGG was higher (96% (95% CI: 0.93, 0.98)) than the specificity when diagnosing LGG (90% (95% CI 0.85, 0.93)). Heterogeneity was observed in both sensitivity and specificity. Metaregression confirmed the heterogeneity in sample sizes (p=0.05), imaging sequence types (p=0.02), and data sources (p=0.01), but not for the inclusion of the testing set (p=0.19), feature extraction number (p=0.36), and selection of feature number (p=0.18). The results of subgroup analysis indicate that sample sizes of more than 100 and feature selection numbers less than the total sample size positively affected the diagnostic performance in differentiating HGG from LGG. Conclusion This study demonstrates the excellent diagnostic performance of ML-based radiomics in differentiating HGG from LGG.
Highlights
Glioma is the most common primary malignant brain tumor that accounts for 80% of malignancies [1], and 2% of all cancers in US adults [2]
According to the World Health Organization (WHO) classification [3], gliomas are subdivided into two groups based on their malignant status lowgrade glioma (LGG) for grades I to II with focal symptoms and high-grade glioma (HGG) for III to IV with generalized symptoms
Treatment of gliomas is essential since there is an eventual progression from LGG to HGG due to gliomas’ distinctive molecular and clinical features [6]
Summary
Glioma is the most common primary malignant brain tumor that accounts for 80% of malignancies [1], and 2% of all cancers in US adults [2]. Grade IV tumors called glioblastoma (GBM) account for 54% of all gliomas [4], with a median survival rate of 15 months [5]. Magnetic resonance imaging (MRI) has been utilized to classify gliomas noninvasively for histopathological purposes. Recent studies have demonstrated the feasibility of conventional MRI sequences, especially gadolinium-based contrast-enhanced T1-weighted imaging (T1-CE) [7] when grading gliomas. With technological developments, advanced MRI sequences contribute to physiological and metabolic assessments when classifying gliomas, such as perfusion-weighted imaging (PWI) [8] and diffusionweighted imaging (DWI) [9]. Previous studies on Contrast Media & Molecular Imaging grading gliomas were limited due to utilizing only a small number of parameters extracted from a single MRI sequence
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
