Save
Identification of high-risk atypical meningiomas by using semantic and radiomic characteristics
EANS Academy. Kalasauskas D. 09/26/19; 276026; EP04019
Dr. Darius Kalasauskas
Dr. Darius Kalasauskas

Access to this content is reserved for EANS members and attendees of this event. Click here to become an EANS member and gain your access to the full content of the EANS Academy


Abstract
Discussion Forum (0)
Rate & Comment (0)
Introduction: Atypical meningiomas (WHO grade II) comprise a relatively heterogeneous tumor entity. New molecular markers have been introduced to differentiate high-risk tumors from those with benign growth pattern. However, no clear radiological criteria exist to identify tumors with high risk for relapse. The aim of this study was to assess the association of certain MRI radiomic and semantic features of atypical meningiomas with tumor relapse.
Patients and methods: We retrospectively analyzed clinical and MRI data of patients with primary intracranial atypical meningiomas operated in our clinic. Preoperative contrast-enhanced T1-MRI sequences were used for the radiomic analysis. In total, 15 quantitatively-defined radiomic (35 patients) and 11 qualitatively-defined semantic (47 patients) features (such as shape, heterogeneity etc.) were used for tumor analysis. The data was then evaluated using clinical characteristics. Statistical analysis was performed by Chi-square test, univariate and multivariate logistic regression and receiver operator characteristics (ROC) curve.
Results: Mean patient age was 59.7 (SD 12.4) years, there were 70.0% women. Mean follow-up was 42 months (range 5-110 months). There were 23.3% relapses in total. The semantic analysis revealed the characteristic of cystic component as the single feature associated with tumor relapse (OR 15.5, 95% CI 2.6-91.2). Quantitative analysis showed cluster prominence to be a single radiomic feature to correlate with tumor recurrence (AUC 0.80, p=0.035). When combining both features, the classification power for tumor recurrence increased (AUC 0.91, p=0.004).
Conclusions: The combination of radiomic and semantic features might be a promising tool to identify high-risk atypical meningiomas. Further validation of this analysis method can provide valuable additional information for patient treatment and follow-up towards a more individualized aftercare.
Introduction: Atypical meningiomas (WHO grade II) comprise a relatively heterogeneous tumor entity. New molecular markers have been introduced to differentiate high-risk tumors from those with benign growth pattern. However, no clear radiological criteria exist to identify tumors with high risk for relapse. The aim of this study was to assess the association of certain MRI radiomic and semantic features of atypical meningiomas with tumor relapse.
Patients and methods: We retrospectively analyzed clinical and MRI data of patients with primary intracranial atypical meningiomas operated in our clinic. Preoperative contrast-enhanced T1-MRI sequences were used for the radiomic analysis. In total, 15 quantitatively-defined radiomic (35 patients) and 11 qualitatively-defined semantic (47 patients) features (such as shape, heterogeneity etc.) were used for tumor analysis. The data was then evaluated using clinical characteristics. Statistical analysis was performed by Chi-square test, univariate and multivariate logistic regression and receiver operator characteristics (ROC) curve.
Results: Mean patient age was 59.7 (SD 12.4) years, there were 70.0% women. Mean follow-up was 42 months (range 5-110 months). There were 23.3% relapses in total. The semantic analysis revealed the characteristic of cystic component as the single feature associated with tumor relapse (OR 15.5, 95% CI 2.6-91.2). Quantitative analysis showed cluster prominence to be a single radiomic feature to correlate with tumor recurrence (AUC 0.80, p=0.035). When combining both features, the classification power for tumor recurrence increased (AUC 0.91, p=0.004).
Conclusions: The combination of radiomic and semantic features might be a promising tool to identify high-risk atypical meningiomas. Further validation of this analysis method can provide valuable additional information for patient treatment and follow-up towards a more individualized aftercare.
Code of conduct/disclaimer available in General Terms & Conditions
Anonymous User Privacy Preferences

Strictly Necessary Cookies (Always Active)

MULTILEARNING platforms and tools hereinafter referred as “MLG SOFTWARE” are provided to you as pure educational platforms/services requiring cookies to operate. In the case of the MLG SOFTWARE, cookies are essential for the Platform to function properly for the provision of education. If these cookies are disabled, a large subset of the functionality provided by the Platform will either be unavailable or cease to work as expected. The MLG SOFTWARE do not capture non-essential activities such as menu items and listings you click on or pages viewed.


Performance Cookies

Performance cookies are used to analyse how visitors use a website in order to provide a better user experience.



Google Analytics is used for user behavior tracking/reporting. Google Analytics works in parallel and independently from MLG’s features. Google Analytics relies on cookies and these cookies can be used by Google to track users across different platforms/services.


Save Settings