1
|
Li X, Lu Y, Liu L, Wang D, Zhao Y, Mei N, Geng D, Ma X, Zheng W, Duan S, Wu PY, Wen H, Tan Y, Sun X, Sun S, Li Z, Yu T, Yin B. Predicting peritumoral edema development after gamma knife radiosurgery of meningiomas using machine learning methods: a multicenter study. Eur Radiol 2023; 33:8912-8924. [PMID: 37498381 DOI: 10.1007/s00330-023-09955-9] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/06/2022] [Revised: 05/09/2023] [Accepted: 05/16/2023] [Indexed: 07/28/2023]
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.
Collapse
Affiliation(s)
- Xuanxuan Li
- Department of Radiology, Huashan Hospital, Fudan University, 12, Middle Wulumuqi Rd., Jing'an District, Shanghai, 200040, China
| | - Yiping Lu
- Department of Radiology, Huashan Hospital, Fudan University, 12, Middle Wulumuqi Rd., Jing'an District, Shanghai, 200040, China
| | - Li Liu
- Department of Radiology, Shanghai Cancer Center, Fudan University, Shanghai, China
| | - Dongdong Wang
- Department of Radiology, Huashan Hospital, Fudan University, 12, Middle Wulumuqi Rd., Jing'an District, Shanghai, 200040, China
| | - Yajing Zhao
- Department of Radiology, Huashan Hospital, Fudan University, 12, Middle Wulumuqi Rd., Jing'an District, Shanghai, 200040, China
| | - Nan Mei
- Department of Radiology, Huashan Hospital, Fudan University, 12, Middle Wulumuqi Rd., Jing'an District, Shanghai, 200040, China
| | - Daoying Geng
- Department of Radiology, Huashan Hospital, Fudan University, 12, Middle Wulumuqi Rd., Jing'an District, Shanghai, 200040, China
| | - Xin Ma
- Suzhou Institute of Biomedical Engineering and Technology, Chinese Academy of Sciences, Suzhou, Jiangsu Province, China
| | - Weiwei Zheng
- Department of Environmental Health, School of Public Health, Fudan University, Shanghai, China
| | | | | | - Hongkai Wen
- Department of Computer Science, University of Warwick, Coventry, UK
| | - Yongli Tan
- Neurosurgery Gamma Knife Centre, Zibo Wanjie Cancer Hospital, Zibo City, Shandong, China
| | - Xiaogang Sun
- Neurosurgery Gamma Knife Centre, Zibo Wanjie Cancer Hospital, Zibo City, Shandong, China
| | - Shibin Sun
- Beijing Neurosurgical Institute, Beijing Tiantan Hospital, Capital Medical University, Beijing, China
| | - Zhiwei Li
- Neurosurgery Department, Wenzhou Central Hospital, Wenzhou, Zhejiang Province, China
| | - Tonggang Yu
- Department of Radiology, Shanghai Gamma Hospital, Huashan Hospital, Fudan University, 518, Middle Wuzhong Rd., Xuhui District, Shanghai, 200235, China.
| | - Bo Yin
- Department of Radiology, Huashan Hospital, Fudan University, 12, Middle Wulumuqi Rd., Jing'an District, Shanghai, 200040, China.
| |
Collapse
|
2
|
Speckter H, Radulovic M, Trivodaliev K, Vranes V, Joaquin J, Hernandez W, Mota A, Bido J, Hernandez G, Rivera D, Suazo L, Valenzuela S, Stoeter P. MRI radiomics in the prediction of the volumetric response in meningiomas after gamma knife radiosurgery. J Neurooncol 2022; 159:281-291. [PMID: 35715668 DOI: 10.1007/s11060-022-04063-y] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/08/2022] [Accepted: 06/07/2022] [Indexed: 10/18/2022]
Abstract
PURPOSE This report presents the first investigation of the radiomics value in predicting the meningioma volumetric response to gamma knife radiosurgery (GKRS). METHODS The retrospective study included 93 meningioma patients imaged by three Tesla MRI. Tumor morphology was quantified by calculating 337 shape, first- and second-order radiomic features from MRI obtained before GKRS. Analysis was performed on original 3D MR images and after their laplacian of gaussian (LoG), logarithm and exponential filtering. The prediction performance was evaluated by Pearson correlation, linear regression and ROC analysis, with meningioma volume change per month as the outcome. RESULTS Sixty calculated features significantly correlated with the outcome. The feature selection based on LASSO and multivariate regression started from all available 337 radiomic and 12 non-radiomic features. It selected LoG-sigma-1-0-mm-3D_firstorder_InterquartileRange and logarithm_ngtdm_Busyness as the predictively most robust and non-redundant features. The radiomic score based on these two features produced an AUC = 0.81. Adding the non-radiomic karnofsky performance status (KPS) to the score has increased the AUC to 0.88. Low values of the radiomic score defined a homogeneous subgroup of 50 patients with consistent absence (0%) of tumor progression. CONCLUSION This is the first report of a strong association between MRI radiomic features and volumetric meningioma response to radiosurgery. The clinical importance of the early and reliable prediction of meningioma responsiveness to radiosurgery is based on its potential to aid individualized therapy decision making.
Collapse
Affiliation(s)
- Herwin Speckter
- Centro Gamma Knife Dominicano and Department of Radiology, CEDIMAT, Plaza de la Salud, Santo Domingo, Dominican Republic.
| | - Marko Radulovic
- Department of Experimental Oncology, Institute for Oncology & Radiology of Serbia, Pasterova 14, 11000, Belgrade, Serbia
| | | | - Velicko Vranes
- Instituto Tecnológico de Santo Domingo (INTEC), Santo Domingo, Dominican Republic
| | - Johanna Joaquin
- Centro Gamma Knife Dominicano and Department of Radiology, CEDIMAT, Plaza de la Salud, Santo Domingo, Dominican Republic
| | - Wenceslao Hernandez
- Centro Gamma Knife Dominicano and Department of Radiology, CEDIMAT, Plaza de la Salud, Santo Domingo, Dominican Republic
| | - Angel Mota
- Centro Gamma Knife Dominicano and Department of Radiology, CEDIMAT, Plaza de la Salud, Santo Domingo, Dominican Republic
| | - Jose Bido
- Centro Gamma Knife Dominicano and Department of Radiology, CEDIMAT, Plaza de la Salud, Santo Domingo, Dominican Republic
| | - Giancarlo Hernandez
- Centro Gamma Knife Dominicano and Department of Radiology, CEDIMAT, Plaza de la Salud, Santo Domingo, Dominican Republic
| | - Diones Rivera
- Centro Gamma Knife Dominicano and Department of Radiology, CEDIMAT, Plaza de la Salud, Santo Domingo, Dominican Republic
| | - Luis Suazo
- Centro Gamma Knife Dominicano and Department of Radiology, CEDIMAT, Plaza de la Salud, Santo Domingo, Dominican Republic
| | - Santiago Valenzuela
- Centro Gamma Knife Dominicano and Department of Radiology, CEDIMAT, Plaza de la Salud, Santo Domingo, Dominican Republic
| | - Peter Stoeter
- Centro Gamma Knife Dominicano and Department of Radiology, CEDIMAT, Plaza de la Salud, Santo Domingo, Dominican Republic
| |
Collapse
|
3
|
Ganz JC. Meningiomas. PROGRESS IN BRAIN RESEARCH 2022; 268:163-190. [PMID: 35074079 DOI: 10.1016/bs.pbr.2021.10.031] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Subscribe] [Scholar Register] [Indexed: 10/19/2022]
Abstract
Meningiomas arise in various locations. Convexity tumors are relatively simple to remove. Skull base tumors and tumors adjacent to the major cerebral veins and venous sinuses can be very difficult to extirpate. Attempts at radical resection can lead to serious morbidity. The combination of bulk reduction using microsurgery followed by GKNS gives greatly improved survival and very low morbidity. With smaller tumors, GKNS may be used as the primary treatment. Increasing numbers of asymptomatic meningiomas are demonstrated either as an unexpected finding or as a residual or recurrent tumor after surgery. In all of these situations, GKNS gives a better result than observation or reoperation.
Collapse
Affiliation(s)
- Jeremy C Ganz
- Department of Neurosurgery, Haukeland University Hospital, Bergen, Norway.
| |
Collapse
|
4
|
Mantziaris G, Pikis S, Samanci Y, Peker S, Nabeel AM, Reda WA, Tawadros SR, El-Shehaby AMN, Abdelkarim K, Emad RM, Delabar V, Mathieu D, Lee CC, Yang HC, Liscak R, Hanuska J, Alvarez RM, Moreno NM, Tripathi M, Speckter H, Albert C, Benveniste RJ, Bowden GN, Patel DN, Kondziolka D, Bernstein K, Lunsford LD, Jenkinson MD, Islim AI, Sheehan J. Stereotactic radiosurgery versus active surveillance for asymptomatic, skull-based meningiomas: an international, multicenter matched cohort study. J Neurooncol 2022; 156:509-518. [DOI: 10.1007/s11060-021-03923-3] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/22/2021] [Accepted: 12/06/2021] [Indexed: 11/25/2022]
|
5
|
Stefini R, Peron S, Lacamera A, Cividini A, Fiaschi P, Sicuri GM. The positive effects of surgery on symptomatic stereotactic radiation-induced peritumoral brain edema: A report of three cases. Surg Neurol Int 2021; 12:358. [PMID: 34345498 PMCID: PMC8326067 DOI: 10.25259/sni_111_2021] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/05/2021] [Accepted: 06/08/2021] [Indexed: 11/04/2022] Open
Abstract
Background Peritumoral brain edema is an uncommon but life-threatening side effect of brain tumors radiosurgery. Medical therapy usually alleviates symptoms until edema spontaneously disappears. However, when peritumoral brain edema endangers the patient's life or medical therapy fails to guarantee an acceptable quality of life, surgery might be considered. Case Description Our report focuses on three patients who developed extensive peritumoral brain edema after radiosurgery. Two were affected by vestibular schwannomas and one by a skull-base meningioma. Peritumoral brain edema worsened despite maximal medical therapy in all cases; therefore, surgical removal of the radiated lesion was carried out. In the first patient, surgery was overdue and resulted in a fatal outcome. On the other hand, in the latter two cases surgery was quickly effective. In all three cases, an unmanageable brain swelling was not found at surgery. Conclusion Surgical removal of brain tumors previously treated with radiosurgery was safe and effective in resolving shortly peritumoral brain edema. This solution should be considered in patients who do not respond to medical therapy and before worsening of clinical conditions. Interestingly, the expected brain swelling was not confirmed intraoperatively. In our experience, this magnetic resonance finding should not be considered a criterion to delay surgery.
Collapse
Affiliation(s)
- Roberto Stefini
- Department of Neurosurgery, ASST Ovest Milanese, Legnano, Milano, Italy
| | - Stefano Peron
- Department of Neurosurgery, ASST Ovest Milanese, Legnano, Milano, Italy
| | - Alessandro Lacamera
- Department of Neurosurgery, ASST Grande Ospedale Metropolitano Niguarda, Milano, Italy
| | - Andrea Cividini
- Department of Neurosurgery, ASST Ovest Milanese, Legnano, Milano, Italy
| | - Pietro Fiaschi
- Department of Neurosurgery, San Martino IST University Hospital, Genova, Italy
| | | |
Collapse
|
6
|
Weber DC, Bizzocchi N, Bolsi A, Jenkinson MD. Proton Therapy for Intracranial Meningioma for the Treatment of Primary/Recurrent Disease Including Re-Irradiation. Front Oncol 2020; 10:558845. [PMID: 33381447 PMCID: PMC7769250 DOI: 10.3389/fonc.2020.558845] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/04/2020] [Accepted: 10/28/2020] [Indexed: 01/14/2023] Open
Abstract
Meningeal tumors represent approximately 10-25% of primary brain tumors and occur usually in elderly female patients. Most meningiomas are benign (80-85%) and for symptomatic and/or large tumors, surgery, with or without radiation therapy (RT), has been long established as an effective means of local tumor control. RT can be delivered to inoperable lesions or to those with non-benign histology and for Simpson I-III and IV-V resection. RT can be delivered with photons or particles (protons or carbon ions) in stereotactic or non-stereotactic conditions. Particle therapy delivered for these tumors uses the physical properties of charged carbon ions or protons to spare normal brain tissue (i.e. Bragg peak), with or without or a dose-escalation paradigm for non-benign lesions. PT can substantially decrease the dose delivered to the non-target brain tissues, including but not limited to the hippocampi, optic apparatus or cochlea. Only a limited number of meningioma patients have been treated with PT in the adjuvant or recurrent setting, as well as for inoperable lesions with pencil beam scanning and with protons only. Approximately 500 patients with image-defined or WHO grade I meningioma have been treated with protons. The reported outcome, usually 5-year local tumor control, ranges from 85 to 99% (median, 96%). For WHO grade II or III patients, the outcome of only 97 patients has been published, reporting a median tumor local control rate of 52% (range, 38-71.1). Only 24 recurring patients treated previously with photon radiotherapy and re-treated with PT were reported. The clinical outcome of these challenging patients seems interesting, provided that they presented initially with benign tumors, are not in the elderly category and have been treated previously with conventional radiation dose of photons. Overall, the number of meningioma patients treated or-re-irradiated with this treatment modality is small and the clinical evidence level is somewhat low (i.e. 3b-5). In this review, we detail the results of upfront PT delivered to patients with meningioma in the adjuvant setting and for inoperable tumors. The outcome of meningioma patients treated with this radiation modality for recurrent tumors, with or without previous RT, will also be reviewed.
Collapse
Affiliation(s)
- Damien C Weber
- Center for Proton Therapy, Paul Scherrer Institute, ETH Domain, Villigen, Switzerland.,Radiation Oncology Department, University Hospital Zürich, Zürich, Switzerland.,Radiation Oncology Department, University Hospital of Bern, Inselspital, Bern, Switzerland
| | - Nicola Bizzocchi
- Center for Proton Therapy, Paul Scherrer Institute, ETH Domain, Villigen, Switzerland
| | - Alessandra Bolsi
- Center for Proton Therapy, Paul Scherrer Institute, ETH Domain, Villigen, Switzerland
| | - Michael D Jenkinson
- Department of Neurosurgery, The Walton Centre NHS Foundation Trust, Liverpool, United Kingdom.,Institute of Translational Medicine, University of Liverpool, Liverpool, United Kingdom
| |
Collapse
|