A Spotlight on the Role of Radiomics and Machine-Learning Applications in the Management of Intracranial Meningiomas: A New Perspective in Neuro-Oncology: A Review

Abstract

Background: In recent decades, the application of machine learning technologies to medical imaging has opened up new perspectives in neuro-oncology, in the so-called radiomics field. Radiomics offer new insight into glioma, aiding in clinical decision-making and patients’ prognosis evaluation. Although meningiomas represent the most common primary CNS tumor and the majority of them are benign and slow-growing tumors, a minor part of them show a more aggressive behavior with an increased proliferation rate and a tendency to recur. Therefore, their treatment may represent a challenge. Methods: According to PRISMA guidelines, a systematic literature review was performed. We included selected articles (meta-analysis, review, retrospective study, and case–control study) concerning the application of radiomics method in the preoperative diagnostic and prognostic algorithm, and planning for intracranial meningiomas. We also analyzed the contribution of radiomics in differentiating meningiomas from other CNS tumors with similar radiological features. Results: In the first research stage, 273 papers were identified. After a careful screening according to inclusion/exclusion criteria, 39 articles were included in this systematic review. Conclusions: Several preoperative features have been identified to increase preoperative intracranial meningioma assessment for guiding decision-making processes. The development of valid and reliable non-invasive diagnostic and prognostic modalities could have a significant clinical impact on meningioma treatment.

The Long and Winding Road: An Overview of the Immunological Landscape of Intracranial Meningiomas

“…(3) “the venous compression theory”, where increased intra-tumor venous pressure could lead to tumor congestion, increase in vasogenic substances and cerebral–pial capillary permeability, and PTBE formation and expansion through vasogenic edema production [ 48 ]. (4) “the hydrodynamic theory”, according to the idea that tumor stasis occurs not only because of the compression of an adjacent cortical vein, but mostly from poor development of the tumor’s drainage system; when tumor blood supply becomes insufficient, meningiomas secrete angiogenic factors (such as VEGF-A, Endothelin-1, Caveolin-1) resulting in immature permeable neovessels, leakage of plasma proteins, and PTBE development in the surrounding brain parenchyma [ 45 , 49 , 63 ].…”

Updated Systematic Review on the Role of Brain Invasion in Intracranial Meningiomas: What, When, Why?

“…This context provided the opportunity for the development and integration of more advanced artificial intelligence (AI) methodologies and their subvisual feature analysis as radiomics. Radiomics is a machine-learning (ML) methodology that allows extraction of quantitative and reproducible tissue and lesion features from diagnostic images, called radiomics features [ 36 ]. It represents a new, low-cost, reliable, and promising tool in the individualized oncological management of meningioma patients [ 37 , 38 ] and provides some advantages compared to the previous qualitative radiological interpretations; in fact, by using defined algorithms, radiomics analysis could capture and reveal more specific information of the disease undetectable for the human eye and provide analysis about intensity distributions, spatial relationships, and texture heterogeneity within a region, as well as across the entire volume of the tumor [ 37 , 38 , 39 , 40 ], identifying invisible different subregions, which is not possible through biopsies, and analyzing their potential changes over time on serial imaging [ 41 , 42 , 43 ].…”

Segmentation accuracy and the reliability of radiomics features

“…In the case of meningiomas, a quite extensive review [37] quotes 'Entropy' as one of the most stable first-order features in terms of ICC, which is again in accordance with our results. Finally, in the case of MRI radiomics of meningioma patients, most of the existing papers perform feature ranking according to the feature prediction power [38,39], instead of computing the fully feature reproducibility.…”