Meningioma Radiomics: At the Nexus of Imaging, Pathology and Biomolecular Characterization

Abstract

Meningiomas are the most common extra-axial tumors of the central nervous system (CNS). Even though recurrence is uncommon after surgery and most meningiomas are benign, an aggressive behavior may still be exhibited in some cases. Although the diagnosis can be made by radiologists, typically with magnetic resonance imaging, qualitative analysis has some limitations in regard to outcome prediction and risk stratification. The acquisition of this information could help the referring clinician in the decision-making process and selection of the appropriate treatment. Following the increased attention and potential of radiomics and artificial intelligence in the healthcare domain, including oncological imaging, researchers have investigated their use over the years to overcome the current limitations of imaging. The aim of these new tools is the replacement of subjective and, therefore, potentially variable medical image analysis by more objective quantitative data, using computational algorithms. Although radiomics has not yet fully entered clinical practice, its potential for the detection, diagnostic, and prognostic characterization of tumors is evident. In this review, we present a wide-ranging overview of radiomics and artificial intelligence applications in meningioma imaging.

Keywords: artificial intelligence; diagnostic imaging; meningioma; radiomics.

Figure 1

Manual and automated segmentation comparison in a meningioma of the left frontal convexity. The sharply demarcated lesion demonstrates intense contrast enhancement. Vasogenic edema of the surrounding white matter is also evident. Manual and automated segmentation are correctly matched. Three-dimensional rendering of the segmented tumor and edema volumes is also presented. T1-CE: contrast-enhanced T1-weighted imaging; FLAIR: fluid attenuated inversion recovery. Adapted from Ref. [13], under the terms of the Creative Commons Attribution-NonCommercial 4.0 License.

Figure 2

MR and pathological images of a hemangiopericytoma (upper row) and a meningioma (lower row). Nomogram (A), calibration curves (B,C), and decision analysis curves (D,E) in the training and validation cohorts for differential diagnosis between the two conditions. IHPC: intracranial hemangiopericytoma; HMDT: IHPC and Meningioma Diagnostic Tool. Adapted from Ref. [20], under the terms of the Creative Commons Attribution-NonCommercial 4.0 License.

Figure 3

Representative flowchart and radiomics nomogram for meningioma consistency prediction. (A) After region of interest delineation, the value of radiomics signature calculated by the algorithm was 0.3444, corresponding to >90% probability of a firm consistency; (B) in this case, the radiomics signature was −0.2181, corresponding to a 30% probability of a firm consistency. Consequently, the meningioma consistency was predicted to be soft. In both cases, the predicted consistency was confirmed at surgery. Reproduced from Ref. [23], under the terms of the Creative Commons Attribution-NonCommercial 4.0 License.

Figure 4

MR images depicting differences in meningioma textural heterogeneity and morphology. The graph presents patient distributions for six radiomics features. High-grade meningiomas are represented in red, while green dots symbolize low-grade lesions. These selected features were significantly different between the two groups. Adapted from Ref. [21], under the terms of the Creative Commons Attribution-NonCommercial 4.0 License.