Abstract 7387: Fully automated segmentation and volumetric measurement of intracranial meningioma using deep learning

Abstract

Abstract Most intracranial meningiomas are small, asymptomatic, and incidentally found tumors. Since the growth of meningioma is the principal indication of treatment, accurate and rapid measurement of the volume of intracranial meningiomas is essential in clinical practice to determine the growth rate of the tumor. It could be useful for the management of meningiomas given their increasing incidence and the wait-and-see policy currently in use for asymptomatic meningiomas. The aim of this study was to develop and validate a computational model for fully automated meningioma segmentation and volume measurement on contrast-enhanced MR scans using deep learning. The retrospectively collected axial contrast-enhanced T1-weighted section images from patients diagnosed with meningioma were manually segmented and used to construct automatic segmentation models with six U-Net- and nnU-Net-based architectures. The performance of each model was evaluated with the Sørensen-Dice similarity coefficient (DSC) with internal (IVS) and external validation sets (EVS), each consisting of 100 independent MRI examinations. A total of 12,909 section images from 459 patients were applied for the training (median age 58 [52-66] [IQR]; 385 women [83.9%]). The median tumor volume of the training set was 2.36 cm3. A 2D nnU-Net showed the highest median DSCs of 0.922 and 0.893 for the IVS and EVS, respectively. The nnU-Nets achieved superior performance in meningioma segmentation than the U-Nets. The DSCs of the 2D nnU-Net for small meningiomas less than 1 cm3 were 0.769 and 0.780 with the IVS and EVS, respectively. We successfully developed a fully automated and accurate volumetric measurement tool for meningioma using nnU-Net. The volumetry performance for small meningioma was significantly better than that achieved in previous studies. The results of this study are clinically applicable and are expected to be of great use in the management of monitored meningioma patients. Citation Format: Ho Kang, Joseph N. Witanto, Kevin Pratama, Doohee Lee, Kyu Sung Choi, Seung Hong Choi, Min-Sung Kim, Jin Wook Kim, Yong Hwy Kim, Sang Joon Park, Chul-Kee Park. Fully automated segmentation and volumetric measurement of intracranial meningioma using deep learning [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 1 (Regular Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(6_Suppl):Abstract nr 7387.