Automated Volumetry of Meningiomas in Contrast-enhanced T1-Weighted MRI Using Deep Learning

Overview

Journal World Neurosurg X

Date 2024 Mar 8

PMID 38455247

Authors

Takamitsu Iwata

Ryuichi Hirayama

Shuhei Yamada

Noriyuki Kijima

Yoshiko Okita

Naoki Kagawa

Haruhiko Kishima

Affiliations

Soon will be listed here.

Abstract

Background: Meningiomas are among the most common intracranial tumors. In these tumors, volumetric assessment is not only important for planning therapeutic intervention but also for follow-up examination.However, a highly accurate automated volumetric method for meningiomas using single-modality magnetic resonance imaging (MRI) has not yet been reported. Here, we aimed to develop a deep learning-based automated volumetry method for meningiomas in MRI and investigate its accuracy and potential clinical applications.

Methods: For deep learning, we used MRI images of patients with meningioma who were referred to Osaka University Hospital between January 2007 and October 2020. Imaging data of eligible patients were divided into three non-overlapping groups: training, validation, and testing. The model was trained and tested using the leave-oneout cross-validation method. Dice index (DI) and root mean squared percentage error (RMSPE) were measured to evaluate the model accuracy. Result: A total of 178 patients (64.6 ± 12.3 years [standard deviation]; 147 women) were evaluated. Comparison of the deep learning model and manual segmentation revealed a mean DI of 0.923 ± 0.051 for tumor lesions. For total tumor volume, RMSPE was 9.5 ± 1.2%, and Mann-Whitney U test did not show a significant difference between manual and algorithm-based measurement of the tumor volume (p = 0.96).

Conclusion: The automatic tumor volumetry algorithm developed in this study provides a potential volume-based imaging biomarker for tumor evaluation in the field of neuroradiological imaging, which will contribute to the optimization and personalization of treatment for central nervous system tumors in the near future.

References

Goldbrunner R, Minniti G, Preusser M, Jenkinson M, Sallabanda K, Houdart E . EANO guidelines for the diagnosis and treatment of meningiomas. Lancet Oncol. 2016; 17(9):e383-91. DOI: 10.1016/S1470-2045(16)30321-7. View

Laukamp K, Pennig L, Thiele F, Reimer R, Gortz L, Shakirin G . Automated Meningioma Segmentation in Multiparametric MRI : Comparable Effectiveness of a Deep Learning Model and Manual Segmentation. Clin Neuroradiol. 2020; 31(2):357-366. DOI: 10.1007/s00062-020-00884-4. View

Jaaskelainen J, Haltia M, Laasonen E, Wahlstrom T, Valtonen S . The growth rate of intracranial meningiomas and its relation to histology. An analysis of 43 patients. Surg Neurol. 1985; 24(2):165-72. DOI: 10.1016/0090-3019(85)90180-6. View

Chang V, Narang J, Schultz L, Issawi A, Jain R, Rock J . Computer-aided volumetric analysis as a sensitive tool for the management of incidental meningiomas. Acta Neurochir (Wien). 2012; 154(4):589-97. DOI: 10.1007/s00701-012-1273-9. View

Nakasu S, Nakasu Y . Natural History of Meningiomas: Review with Meta-analyses. Neurol Med Chir (Tokyo). 2020; 60(3):109-120. PMC: 7073704. DOI: 10.2176/nmc.ra.2019-0213. View

Violaris K, Katsarides V, Karakyriou M, Sakellariou P . Surgical Outcome of Treating Grades II and III Meningiomas: A Report of 32 Cases. Neurosci J. 2015; 2013:706481. PMC: 4475582. DOI: 10.1155/2013/706481. View

Boto J, Guatta R, Fitsiori A, Hofmeister J, Meling T, Vargas M . Is Contrast Medium Really Needed for Follow-up MRI of Untreated Intracranial Meningiomas?. AJNR Am J Neuroradiol. 2021; 42(8):1421-1428. PMC: 8367609. DOI: 10.3174/ajnr.A7170. View

Laukamp K, Thiele F, Shakirin G, Zopfs D, Faymonville A, Timmer M . Fully automated detection and segmentation of meningiomas using deep learning on routine multiparametric MRI. Eur Radiol. 2018; 29(1):124-132. PMC: 6291436. DOI: 10.1007/s00330-018-5595-8. View

Akkus Z, Galimzianova A, Hoogi A, Rubin D, Erickson B . Deep Learning for Brain MRI Segmentation: State of the Art and Future Directions. J Digit Imaging. 2017; 30(4):449-459. PMC: 5537095. DOI: 10.1007/s10278-017-9983-4. View

10.

Shimol E, Joskowicz L, Eliahou R, Shoshan Y . Computer-based radiological longitudinal evaluation of meningiomas following stereotactic radiosurgery. Int J Comput Assist Radiol Surg. 2017; 13(2):215-228. DOI: 10.1007/s11548-017-1673-7. View

11.

Dolecek T, Propp J, Stroup N, Kruchko C . CBTRUS statistical report: primary brain and central nervous system tumors diagnosed in the United States in 2005-2009. Neuro Oncol. 2012; 14 Suppl 5:v1-49. PMC: 3480240. DOI: 10.1093/neuonc/nos218. View

12.

Wan Y, Rahmat R, Price S . Deep learning for glioblastoma segmentation using preoperative magnetic resonance imaging identifies volumetric features associated with survival. Acta Neurochir (Wien). 2020; 162(12):3067-3080. PMC: 7593295. DOI: 10.1007/s00701-020-04483-7. View

13.

Nakasu S, Hirano A, Shimura T, Llena J . Incidental meningiomas in autopsy study. Surg Neurol. 1987; 27(4):319-22. DOI: 10.1016/0090-3019(87)90005-x. View

14.

Louis D, Perry A, Reifenberger G, von Deimling A, Figarella-Branger D, Cavenee W . The 2016 World Health Organization Classification of Tumors of the Central Nervous System: a summary. Acta Neuropathol. 2016; 131(6):803-20. DOI: 10.1007/s00401-016-1545-1. View

15.

Naser M, Deen M . Brain tumor segmentation and grading of lower-grade glioma using deep learning in MRI images. Comput Biol Med. 2020; 121:103758. DOI: 10.1016/j.compbiomed.2020.103758. View

16.

Ostrom Q, Patil N, Cioffi G, Waite K, Kruchko C, Barnholtz-Sloan J . CBTRUS Statistical Report: Primary Brain and Other Central Nervous System Tumors Diagnosed in the United States in 2013-2017. Neuro Oncol. 2020; 22(12 Suppl 2):iv1-iv96. PMC: 7596247. DOI: 10.1093/neuonc/noaa200. View

17.

Hale A, Wang L, Strother M, Chambless L . Differentiating meningioma grade by imaging features on magnetic resonance imaging. J Clin Neurosci. 2017; 48:71-75. DOI: 10.1016/j.jocn.2017.11.013. View

18.

Yamada S, Kijima N, Nakagawa T, Hirayama R, Kinoshita M, Kagawa N . How Much Tumor Volume Is Responsible for Development of Clinical Symptoms in Patients With Convexity, Parasagittal, and Falx Meningiomas?. Front Neurol. 2021; 12:769656. PMC: 8635518. DOI: 10.3389/fneur.2021.769656. View

19.

Kauke M, Safi A, Stavrinou P, Krischek B, Goldbrunner R, Timmer M . Does Meningioma Volume Correlate With Clinical Disease Manifestation Irrespective of Histopathologic Tumor Grade?. J Craniofac Surg. 2019; 30(8):e799-e802. DOI: 10.1097/SCS.0000000000005845. View

20.

Yao A, Pain M, Balchandani P, Shrivastava R . Can MRI predict meningioma consistency?: a correlation with tumor pathology and systematic review. Neurosurg Rev. 2016; 41(3):745-753. PMC: 5438899. DOI: 10.1007/s10143-016-0801-0. View