Garaba, Alexandru

Purpose: To better define the overall performance of the current radiomics-based models for the discrimination of pediatric posterior fossa tumors. Methods: A comprehensive literature search of the databases PubMed, Ovid MEDLINE, Ovid EMBASE, Web of Science, and Scopus was designed and conducted by an experienced librarian. We estimated overall sensitivity (SEN) and specificity (SPE). Event rates were pooled across studies using a random-effects meta-analysis, and the χ2 test was performed to assess the heterogeneity. Results: Overall SEN and SPE for differentiation between MB, PA, and EP were found to be promising, with SEN values of 93% (95% CI = 0.88–0.96), 83% (95% CI = 0.66–0.93), and 85% (95% CI = 0.71–0.93), and corresponding SPE values of 87% (95% CI = 0.82–0.90), 95% (95% CI = 0.90–0.98) and 90% (95% CI = 0.84–0.94), respectively. For MB, there is a better trend for LR classifiers, while textural features are the most used and the best performing (ACC 96%). As for PA and EP, a synergistic employment of LR and NN classifiers, accompanied by geometrical or morphological features, demonstrated superior performance (ACC 94% and 96%, respectively). Conclusions: The diagnostic performance is high, making radiomics a helpful method to discriminate these tumor types. In the forthcoming years, we expect even more precise models.

Abstract Purpose: Numerous radiomics-based models have been proposed to discriminate between central nervous system (CNS) gliomas and primary central nervous system lymphomas (PCNSLs). Given the heterogeneity of the existing models, we aimed to define their overall performance and identify the most critical variables to pilot future algorithms. Methods: A systematic review of the literature and a meta-analysis were conducted, focusing on studies reporting on radiomics to differentiate gliomas from PCNSLs. A comprehensive literature search was performed through PubMed, Ovid MEDLINE, Ovid EMBASE, Web of Science, and Scopus databases. Overall sensitivity (SEN) and specificity (SPE) were estimated. Event rates were pooled using a random-effects meta-analysis, and the heterogeneity was assessed using the χ2 test. Results: The overall SEN and SPE for differentiation between CNS gliomas and PCNSLs were 88% (95% CI = 0.83 – 0.91) and 87% (95% CI = 0.83 – 0.91), respectively. The best-performing features were the Gray Level Run Length Matrix (GLRLM; ACC 97%), followed by the Neighboring Gray Tone Difference Matrix (NGTDM; ACC 93%), and shape-based features (ACC 91%). The 18F-FDG-PET/CT was the best-performing imaging modality (ACC 97%), followed by the MRI CE-T1W (AUC 87% - 95%). Most studies applied a cross-validation analysis (92%). Conclusion: The current SEN and SPE of radiomics to discriminate CNS gliomas from PCNSLs are high, making radiomics a helpful method to differentiate these tumor types. The best-performing features are the GLRLM, NGTDM, and shape-based features. The 18F-FDG-PET/CTimaging modality is the best-performing, while the MRI CE-T1W is the most used.