Abstract
Objectives
Edema is a complication of gamma knife radiosurgery (GKS) in meningioma patients that leads to a variety of consequences. The aim of this study is to construct radiomics-based machine learning models to predict post-GKS edema development.
Methods
In total, 445 meningioma patients who underwent GKS in our institution were enrolled and partitioned into training and internal validation datasets (8:2). A total of 150 cases from multicenter data were included as the external validation dataset. In each case, 1132 radiomics features were extracted from each pre-treatment MRI sequence (contrast-enhanced T1WI, T2WI, and ADC maps). Nine clinical features and eight semantic features were also generated. Nineteen random survival forest (RSF) and nineteen neural network (DeepSurv) models with different combinations of radiomics, clinical, and semantic features were developed with the training dataset, and evaluated with internal and external validation. A nomogram was derived from the model achieving the highest C-index in external validation.
Results
All the models were successfully validated on both validation datasets. The RSF model incorporating clinical, semantic, and ADC radiomics features achieved the best performance with a C-index of 0.861 (95% CI: 0.748–0.975) in internal validation, and 0.780 (95% CI: 0.673–0.887) in external validation. It stratifies high-risk and low-risk cases effectively. The nomogram based on the predicted risks provided personalized prediction with a C-index of 0.962 (95%CI: 0.951–0.973) and satisfactory calibration.
Conclusion
This RSF model with a nomogram could represent a non-invasive and cost-effective tool to predict post-GKS edema risk, thus facilitating personalized decision-making in meningioma treatment.
Clinical relevance statement
The RSF model with a nomogram built in this study represents a handy, non-invasive, and cost-effective tool for meningioma patients to assist in better counselling on the risks, appropriate individual treatment decisions, and customized follow-up plans.
Key Points
• Machine learning models were built to predict post-GKS edema in meningioma. The random survival forest model with clinical, semantic, and ADC radiomics features achieved excellent performance.
• The nomogram based on the predicted risks provides personalized prediction with a C-index of 0.962 (95%CI: 0.951–0.973) and satisfactory calibration and shows the potential to assist in better counselling, appropriate treatment decisions, and customized follow-up plans.
• Given the excellent performance and convenient acquisition of the conventional sequence, we envision that this non-invasive and cost-effective tool will facilitate personalized medicine in meningioma treatment.
Similar content being viewed by others
Abbreviations
- ADC:
-
Apparent diffusion coefficient
- CE-T1WI:
-
Contrast-enhanced T1-weighted image
- CI:
-
Confidence interval
- CPH:
-
Cox proportional hazards
- DWI:
-
Diffusion-weighted Imaging
- EANO:
-
European Association of Neuro-Oncology
- GKS:
-
Gamma knife radiosurgery
- GND:
-
Greenwood-Nam-D’Agostino
- ICC:
-
Intraclass/interclass correlation coefficient
- IRB:
-
Institutional review board
- ML:
-
Machine learning
- OOB:
-
Out-of-bag
- RANO:
-
Response Assessment in Neuro-Oncology
- RSF:
-
Random survival forest
- SRS:
-
Stereotactic radiosurgery
- T2WI:
-
T2-weighted image
- VEGF:
-
Vascular endothelial growth factor
- VOI:
-
Volume of interest
- VPF:
-
Vascular permeability factor
References
Kim J-H, Gwak H-S, Hong EK, Bang CW, Lee SH, Yoo H (2015) A case of benign meningioma presented with subdural hemorrhage. Brain Tumor Res Treat. https://doi.org/10.14791/btrt.2015.3.1.30
Chang JH, Chang JW, Choi JY, Park YG, Chung SS (2003) Complications after gamma knife radiosurgery for benign meningiomas. J Neurol Neurosurg Psychiatry. https://doi.org/10.1136/jnnp.74.2.226
Oermann EK, Bhandari R, Chen VJ et al (2013) Five fraction image-guided radiosurgery for primary and recurrent meningiomas. Front Oncol. https://doi.org/10.3389/fonc.2013.00213
Liščák R, Kollová A, Vladyka V, Šimonová G, Novotný J (2004) Gamma knife radiosurgery of skull base meningiomas. Acta Neurochir Suppl. https://doi.org/10.1007/978-3-7091-0583-2_7
Hoe Y, Choi YJ, Kim JH, Kwon DH, Kim CJ, Cho YH (2015) Peritumoral brain edema after stereotactic radiosurgery for asymptomatic intracranial meningiomas : risks and pattern of evolution. J Korean Neurosurg Soc. https://doi.org/10.3340/jkns.2015.58.4.379
Kondziolka D, Patel AD, Kano H, Flickinger JC, Lunsford LD (2016) Long-term outcomes after gamma knife radiosurgery for meningiomas. Am J Clin Oncol. https://doi.org/10.1097/COC.0000000000000080
Sheehan J, Pikis S, Islim A et al (2021) An international multicenter matched cohort analysis of incidental meningioma progression during active surveillance or after stereotactic radiosurgery: the IMPASSE Study. Neuro Oncol. https://doi.org/10.1093/neuonc/noab132
Milano MT, Sharma M, Soltys SG et al (2018) Radiation-induced edema after single-fraction or multifraction stereotactic radiosurgery for meningioma: a critical review. Int J Radiat Oncol Biol Phys. https://doi.org/10.1016/j.ijrobp.2018.03.026
Sheehan JP, Cohen-Inbar O, Ruangkanchanasetr R et al (2015) Post-radiosurgical edema associated with parasagittal and parafalcine meningiomas: a multicenter study. J Neurooncol. https://doi.org/10.1007/s11060-015-1911-1
Novotný J, Kollová A, Liscák R (2006) Prediction of intracranial edema after radiosurgery of meningiomas. J Neurosurg. https://doi.org/10.3171/sup.2006.105.7.120
Han M-S, Jang W-Y, Moon K-S et al (2017) Is fractionated gamma knife radiosurgery a safe and effective treatment approach for large-volume (>10 cm(3)) intracranial meningiomas? World Neurosurg. https://doi.org/10.1016/j.wneu.2016.12.056
Cai R, Barnett GH, Novak E, Chao ST, Suh JH (2016) Principal risk of peritumoral edema after stereotactic radiosurgery for intracranial meningioma is tumor-brain contact interface area. Neurosurgery. https://doi.org/10.1227/01.NEU.0000365366.53337.88
Unger KR, Lominska CE, Chanyasulkit J et al (2012) Risk factors for posttreatment edema in patients treated with stereotactic radiosurgery for meningiomas. Neurosurgery. https://doi.org/10.1227/neu.0b013e3182351ae7
Cai R, Barnett GH, Novak E, Chao ST, Suh JH (2010) Principal risk of peritumoral edema after stereotactic radiosurgery for intracranial meningioma is tumor-brain contact interface area. Neurosurgery. https://doi.org/10.1227/01.NEU.0000365366.53337.88
Girvigian MR, Chen JCT, Rahimian J, Miller MJ, Tome M (2008) Comparison of early complications for patients with convexity and parasagittal meningiomas treated with either stereotactic radiosurgery or fractionated stereotactic radiotherapy. Neurosurgery. https://doi.org/10.1227/01.neu.0000325933.34154.cb
Hadelsberg U, Nissim U, Cohen ZR, Spiegelmann R (2015) LINAC radiosurgery in the management of parasagittal meningiomas. Stereotact Funct Neurosurg. https://doi.org/10.1159/000368440
Zada G, Pagnini PG, Yu C et al (2010) Long-term outcomes and patterns of tumor progression after gamma knife radiosurgery for benign meningiomas. Neurosurgery. https://doi.org/10.1227/01.NEU.0000371974.88873.15
Conti A, Pontoriero A, Siddi F et al (2016) Post-treatment edema after meningioma radiosurgery is a predictable complication. Cureus. https://doi.org/10.7759/cureus.605
O’Connor KP, Algan O, Vesely SK et al (2019) Factors associated with treatment failure and radiosurgery-related edema in WHO grade 1 and 2 meningioma patients receiving gamma knife radiosurgery. World Neurosurg. https://doi.org/10.1016/j.wneu.2019.06.152
Akai H, Yasaka K, Kunimatsu A et al (2018) Predicting prognosis of resected hepatocellular carcinoma by radiomics analysis with random survival forest. Diagn Interv Imaging. https://doi.org/10.1016/j.diii.2018.05.008
Ingrisch M, Schneider MJ, Nörenberg D et al (2017) Radiomic analysis reveals prognostic information in T1-weighted baseline magnetic resonance imaging in patients with glioblastoma. Invest Radiol. https://doi.org/10.1097/RLI.0000000000000349
Hamidi O, Poorolajal J, Farhadian M, Tapak L (2016) Identifying important risk factors for survival in kidney graft failure patients using random survival forests. Iran J Public Health 45:27–33
Wang H, Li G (2017) A selective review on random survival forests for high dimensional data. Quant Bio-Science. https://doi.org/10.22283/qbs.2017.36.2.85
Katzman JL, Shaham U, Cloninger A, Bates J, Jiang T, Kluger Y (2018) DeepSurv: personalized treatment recommender system using a Cox proportional hazards deep neural network. BMC Med Res Methodol. https://doi.org/10.1186/s12874-018-0482-1
Bice N, Kirby N, Bahr T et al (2020) Deep learning-based survival analysis for brain metastasis patients with the national cancer database. J Appl Clin Med Phys. https://doi.org/10.1002/acm2.12995
Cao J, Lan S, Shen L et al (2017) Hemoglobin level, a prognostic factor for nasal extranodal natural killer/T-cell lymphoma patients from stage I to IV: a validated prognostic nomogram. Sci Rep. https://doi.org/10.1038/s41598-017-11137-9
Tapak L, Sheikh V, Jenabi E, Khazaei S (2020) Predictors of mortality among hemodialysis patients in hamadan province using random survival forests. J Prev Med Hyg. https://doi.org/10.15167/2421-4248/jpmh2020.61.3.1421
Huang RY, Bi WL, Weller M et al (2019) Proposed response assessment and endpoints for meningioma clinical trials: report from the Response Assessment in Neuro-Oncology Working Group. Neuro Oncol. https://doi.org/10.1093/neuonc/noy137
Yushkevich PA, Piven J, Hazlett HC et al (2006) User-guided 3D active contour segmentation of anatomical structures: significantly improved efficiency and reliability. Neuroimage. https://doi.org/10.1016/j.neuroimage.2006.01.015
Bae S, Choi YS, Ahn SS et al (2018) Radiomic MRI phenotyping of glioblastoma: Improving survival prediction. Radiology. https://doi.org/10.1148/radiol.2018180200
Goldbrunner R, Minniti G, Preusser M et al (2016) EANO guidelines for the diagnosis and treatment of meningiomas. Lancet Oncol. https://doi.org/10.1016/S1470-2045(16)30321-7
Bitzer M, Klose U, Geist-Barth B et al (2002) Alterations in diffusion and perfusion in the pathogenesis of peritumoral brain edema in meningiomas. Eur Radiol 12:2062–2076. https://doi.org/10.1007/s003300101025
Kollová A, Liščák R, Novotný J, Vladyka V, Šimonová G, Janoušková L (2007) Gamma Knife surgery for benign meningioma. J Neurosurg. https://doi.org/10.3171/JNS-07/08/0325
Wassenaar TM, Yaffe K, van der Werf YD, Sexton CE (2019) Associations between modifiable risk factors and white matter of the aging brain: insights from diffusion tensor imaging studies. Neurobiol Aging. https://doi.org/10.1016/j.neurobiolaging.2019.04.006
Peters A (2002) The effects of normal aging on myelin and nerve fibers: A review. J Neurocytol. https://doi.org/10.1023/A:1025731309829
Fatima Z, Motosugi U, Hori M et al (2013) Age-related white matter changes in high b-value q-space diffusion-weighted imaging. Neuroradiology. https://doi.org/10.1007/s00234-012-1099-4
Toh CH, Castillo M (2021) Peritumoral brain edema volume in meningioma correlates with tumor fractional anisotropy but not apparent diffusion coefficient or cerebral blood volume. Neuroradiology 63:1263–1270. https://doi.org/10.1007/s00234-021-02646-6
Bologna M, Calareso G, Resteghini C et al (2020) Relevance of apparent diffusion coefficient features for a radiomics-based prediction of response to induction chemotherapy in sinonasal cancer. NMR Biomed. https://doi.org/10.1002/nbm.4265
Lu Y, Liu L, Luan S, Xiong J, Geng D, Yin B (2019) The diagnostic value of texture analysis in predicting WHO grades of meningiomas based on ADC maps: an attempt using decision tree and decision forest. Eur Radiol. https://doi.org/10.1007/s00330-018-5632-7
Yin B, Liu L, Zhang BY, Li YX, Li Y, Geng D (2012) Correlating apparent diffusion coefficients with histopathologic findings on meningiomas. Eur J Radiol. https://doi.org/10.1016/j.ejrad.2012.06.002
Liu L, Yin B, Geng D, Li Y, Zhang B, Peng W (2014) Comparison of ADC values of intracranial hemangiopericytomas and angiomatous and anaplastic meningiomas. J Neuroradiol 41:188–194. https://doi.org/10.1016/j.neurad.2013.07.002
Zhang T, Yu JM, Wang YQ, Yin DD, Fang LJ (2018) WHO grade I meningioma subtypes: MRI features and pathological analysis. Life Sci. https://doi.org/10.1016/j.lfs.2018.08.061
Nagar VA, Ye JR, Ng WH et al (2008) Diffusion-weighted MR imaging: Diagnosing atypical or malignant meningiomas and detecting tumor dedifferentiation. AJNR Am J Neuroradiol. https://doi.org/10.3174/ajnr.A0996
Elshafeey N, Kotrotsou A, Hassan A et al (2019) Multicenter study demonstrates radiomic features derived from magnetic resonance perfusion images identify pseudoprogression in glioblastoma. Nat Commun. https://doi.org/10.1038/s41467-019-11007-0
Osawa T, Tosaka M, Nagaishi M, Yoshimoto Y (2013) Factors affecting peritumoral brain edema in meningioma: special histological subtypes with prominently extensive edema. J Neurooncol. https://doi.org/10.1007/s11060-012-0989-y
Kan P, Liu JK, Wendland MM, Shrieve D, Jensen RL (2007) Peritumoral edema after stereotactic radiosurgery for intracranial meningiomas and molecular factors that predict its development. J Neurooncol. https://doi.org/10.1007/s11060-006-9294-y
Iwado E, Ichikawa T, Kosaka H et al (2012) Role of VEGF and matrix metalloproteinase-9 in peritumoral brain edema associated with supratentorial benign meningiomas. Neuropathology. https://doi.org/10.1111/j.1440-1789.2012.01312.x
Provias J, Claffey K, Lau N, Feldkamp M, Guha A (1997) Meningiomas: role of vascular endothelial growth factor/vascular permeability factor in angiogenesis and peritumoral edema. Neurosurgery. https://doi.org/10.1097/0006123-199705000-00027
Funding
This project was supported by the Clinical Research Plan of SHDC (Grant No. SHDC2020CR4069), the Medical Engineering Fund of Fudan University(Grant No. yg2021-029), the Shanghai Sailing Program (Grant No. 21YF1404800), the Youth Program of Special Project for Clinical Research of Shanghai Municipal Health Commission Health industry (Grant No. 20204Y0421), the Youth Medical Talents –Medical Imaging Practitioner Program (No.3030256001), the Shanghai Municipal Science and Technology Major Project (No. 2018SHZDZX01), ZJ Lab, and Shanghai Center for Brain-Inspired Technology.
Author information
Authors and Affiliations
Corresponding authors
Ethics declarations
Guarantor
The scientific guarantor of this publication is Dr. Bo Yin.
Conflict of interest
The authors of this manuscript declare no relationships with any companies, whose products or services may be related to the subject matter of the article.
Statistics and biometry
One of the authors (Weiwei Zheng, School of Public Health, Fudan University) has significant statistical expertise.
Informed consent
Approval from the institutional review board (IRB) was obtained, and written informed consent was waived.
Ethical approval
Approval from the institutional review board (IRB) was obtained, and written informed consent was waived.
Study subjects or cohorts overlap
Study subjects or cohorts have never been previously reported.
Methodology
• retrospective
• diagnostic or prognostic study
• multicenter study
Additional information
Publisher's note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Supplementary Information
Below is the link to the electronic supplementary material.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Li, X., Lu, Y., Liu, L. et al. Predicting peritumoral edema development after gamma knife radiosurgery of meningiomas using machine learning methods: a multicenter study. Eur Radiol 33, 8912–8924 (2023). https://doi.org/10.1007/s00330-023-09955-9
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00330-023-09955-9