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

Ugga, Lorenzo; Spadarella, Gaia; Pinto, Lorenzo; Cuocolo, Renato; Brunetti, Arturo

doi:10.3390/cancers14112605

Cited by 17 publications

(7 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…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.…”

Section: Discussionmentioning

confidence: 99%

Segmentation accuracy and the reliability of radiomics features

Cama¹,

Candiani²,

Roccatagliata³

et al. 2022

Preprint

View full text Add to dashboard Cite

<p>In this paper we introduce a novel computational procedure to quantitatively investigate how image segmentation affects radiomics feature computation. Specifically, this study introduces four correlation coefficients that quantitatively assess the features' reliability in terms of quality, consistency, robustness, and instability of the features themselves. We validate our analysis in the case of an MRI-based study involving meningioma patients. The proposed approach has been intrinsically conceived for automated radiomics analysis and it is of potential interest for other imaging-driven applications in oncology.</p>

show abstract

Section: Discussionmentioning

confidence: 99%

Segmentation accuracy and the reliability of radiomics features

Cama¹,

Candiani²,

Roccatagliata³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Noteworthy, brain invasion as well as meningioma grade may be better predicted prior to surgery by modern high-dimensional quantitative imaging analysis, the so-called radiomics ( Zhang et al, 2020 ; Ugga et al, 2022 ). Radiomics is increasingly attracting attention in medical oncology, since radiomics-derived nomograms may predict the diagnosis and biological behaviour of different tumours ( Lambin et al, 2017 ).…”

Section: Imaging Of Cns Invasionmentioning

confidence: 99%

Meningiomas with CNS invasion

2023

View full text Add to dashboard Cite

CNS invasion has been included as an independent criterion for the diagnosis of a high-grade (WHO and CNS grade 2 and 3) meningioma in the 2016 and more recently in the 2021 WHO classification. However, the prognostic role of brain invasion has recently been questioned. Also, surgical treatment for brain invasive meningiomas may pose specific challenges. We conducted a systematic review of the 2016–2022 literature on brain invasive meningiomas in Pubmed, Scopus, Web of Science and the Cochrane Library. The prognostic relevance of brain invasion as a stand-alone criterion is still unclear. Additional and larger studies using robust definitions of histological brain invasion and addressing the issue of sampling errors are clearly warranted. Although the necessity of molecular profiling in meningioma grading, prognostication and decision making in the future is obvious, specific markers for brain invasion are lacking for the time being. Advanced neuroimaging may predict CNS invasion preoperatively. The extent of resection (e.g., the Simpson grading) is an important predictor of tumor recurrence especially in higher grade meningiomas, but also – although likely to a lesser degree – in benign tumors, and therefore also in brain invasive meningiomas with and without other histological features of atypia or malignancy. Hence, surgery for brain invasive meningiomas should follow the principles of maximal but safe resections. There are some data to suggest that safety and functional outcomes in such cases may benefit from the armamentarium of surgical adjuncts commonly used for surgery of eloquent gliomas such as intraoperative monitoring, awake craniotomy, DTI tractography and further advanced intraoperative brain tumor visualization.

show abstract

“…Radiomics performed on magnetic resonance imaging (MRI) were shown to predict molecular alterations such as IDH1/2 mutations [7,8], 1p19q co-deletion [9], ATRX status [10], MGMT promoter methylation [11] and also TERT promoter mutations [12] in gliomas with remarkable accuracy. In meningiomas, numerous studies analyzed correlations of radiomics features with intraoperative and histological characteristics or prognosis [13,14], while the predictive value for molecular alterations has not been investigated yet. Of note, conventional MRI analyses revealed distinct anatomical distributions of key genetic and epigenetic alterations such as DNA methylation [15] or hotspot mutations including TERT [16][17][18][19] as well as their correlations with further imaging characteristics [16,18,20], indicating the immense potential of imaging data to predict molecular alterations in meningiomas.…”

Section: Introductionmentioning

confidence: 99%

Radiomics-Based Prediction of TERT Promotor Mutations in Intracranial High-Grade Meningiomas

Akkurt,

Spille,

Peetz-Dienhart

et al. 2023

Cancers

View full text Add to dashboard Cite

Purpose: In meningiomas, TERT promotor mutations are rare but qualify the diagnosis of anaplasia, directly impacting adjuvant therapy. Effective screening for patients at risk for promotor mutations could enable more targeted molecular analyses and improve diagnosis and treatment. Methods: Semiautomatic segmentation of intracranial grade 2/3 meningiomas was performed on preoperative magnetic resonance imaging. Discriminatory power to predict TERT promoter mutations was analyzed using a random forest algorithm with an increasing number of radiomic features. Two final models with five and eight features with both fixed and differing radiomics features were developed and adjusted to eliminate random effects and to avoid overfitting. Results: A total of 117 image sets including training (N = 94) and test data (N = 23) were analyzed. To eliminate random effects and demonstrate the robustness of our approach, data partitioning and subsequent model development and testing were repeated a total of 100 times (each time with repartitioned training and independent test data). The established five- and eight-feature models with both fixed and different radiomics features enabled the prediction of TERT with similar but excellent performance. The five-feature (different/fixed) model predicted TERT promotor mutation status with a mean AUC of 91.8%/94.3%, mean accuracy of 85.5%/88.9%, mean sensitivity of 88.6%/91.4%, mean specificity of 83.2%/87.0%, and a mean Cohen’s Kappa of 71.0%/77.7%. The eight-feature (different/fixed) model predicted TERT promotor mutation status with a mean AUC of 92.7%/94.6%, mean accuracy of 87.3%/88.9%, mean sensitivity of 89.6%/90.6%, mean specificity of 85.5%/87.5%, and a mean Cohen’s Kappa of 74.4%/77.6%. Of note, the addition of further features of up to N = 8 only slightly increased the performance. Conclusions: Radiomics-based machine learning enables prediction of TERT promotor mutation status in meningiomas with excellent discriminatory performance. Future analyses in larger cohorts should include grade 1 lesions as well as additional molecular alterations.

show abstract

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

Cited by 17 publications

References 51 publications

Segmentation accuracy and the reliability of radiomics features

Segmentation accuracy and the reliability of radiomics features

Meningiomas with CNS invasion

Radiomics-Based Prediction of TERT Promotor Mutations in Intracranial High-Grade Meningiomas

Contact Info

Product

Resources

About