Factors Associated with Treatment Failure and Radiosurgery-Related Edema in WHO Grade 1 and 2 Meningioma Patients Receiving Gamma Knife Radiosurgery

Predicting peritumoral edema development after gamma knife radiosurgery of meningiomas using machine learning methods: a multicenter study

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.

MRI radiomics in the prediction of the volumetric response in meningiomas after gamma knife radiosurgery

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.

Meningiomas

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.

The positive effects of surgery on symptomatic stereotactic radiation-induced peritumoral brain edema: A report of three cases

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.

Proton Therapy for Intracranial Meningioma for the Treatment of Primary/Recurrent Disease Including Re-Irradiation

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.