Radiosurgery For Brain Metastases Research Articles

Quality of life after stereotactic radiosurgery for brain metastasis: an assessment from a prospective national registry.

Stereotactic radiosurgery (SRS) is frequently used in the management of brain metastasis patients. However, there is an urgent need to evaluate post-treatment outcomes and quality of life metrics for patients undergoing SRS for brain metastases. The NeuroPoint Alliance (NPA) SRS Quality Registry conducted prospective enrollment of patients undergoing SRS from 2017 to 2024. Patients with brain metastases from lung cancer, breast cancer, and melanoma were included in the analysis. Outcomes of interest included quality of life metrics, as captured by the five-dimension Euro-QOL (EQ-5D) at 6-12 months and last record follow-up, overall survival, local progression, out-of-field progression, and overall intracranial progression. 522 patients comprised our analytic cohort, and 315 patients had available EQ-5D data at the time of SRS and final follow-up. 264 (47.8%), 197 (35.7%), and 91 (16.5%) patients had 1, 2-4, and 5-14 lesions pre-SRS, respectively. The median overall survival time from diagnosis was 27.3 months. The median time-to-local progression was not reached. At final follow-up, 107 (34.0%) patients had improvement, 51 (16.2%) patients had stable, and 113 patients (35.9%) had worsening EQ-5D scores when compared to baseline. For 44 (13.9%) patients mixed responses across the EQ-5D indices were reported. Linear regression analysis showed that male sex, smoking status, primary tumor type, time-to-overall progression, cumulative intracranial tumor volume (CITV), and baseline EQ-5D were statistically significantly associated with EQ-5D single index at the final follow-up. Real-world data from the SRS NPA Registry demonstrated that most patients with brain metastasis had no change or improvement in quality of life after SRS. Baseline EQ-5D was predictive of EQ-5D single index at final follow-up, and, as such, EQ-5D at baseline would be a valuable assessment measure for brain metastasis patients undergoing SRS.

16 Fractionated Stereotactic Radiosurgery in Brain Metastases: A Single Institute Retrospective Analysis

16 Fractionated Stereotactic Radiosurgery in Brain Metastases: A Single Institute Retrospective Analysis

Comparative effectiveness of frame-based and mask-based Gamma Knife stereotactic radiosurgery in brain metastases: A 509 patient meta-analysis.

Stereotactic Radiosurgery (SRS) is the primary treatment for patients with limited numbers of small brain metastases. Head fixation is usually performed with framed-based (FB) fixation; however, mask-based (MB) fixation has emerged as a less invasive alternative. A comparative meta-analysis between both approaches has not been performed. Databases were searched until August 28th, 2023, to identify studies comparing MB and FB SRS in the treatment of brain metastases. Our outcomes of interest included local tumor control (LTC), radiation necrosis (RN), mortality, and treatment time (TT). Mean difference (MD), risk ratio (RR), and hazard ratio (HR) were used for statistical comparisons. From 295 articles initially identified, six studies (1 clinical trial) involving 509 patients were included. LTC revealed comparable RR at 6-months (RR = 0.95[95%CI = 0.89-1.01], p = 0.12) and a marginal benefit in FB SRS at 1-year (RR = 0.87[95%CI = 0.78-0.96], p = 0.005). However, in oligometastases exclusively treated with single-fraction SRS, LTC was similar among groups (RR = 0.92 [95%CI = 0.89-1.0], p = 0.30). Similarly, in patients with oligometastases treated with single-fraction SRS, RN (HR = 1.69; 95%CI = 0.72-3.97, p = 0.22), TT (MD = -29.64; 95%CI = -80.38-21.10, p = 0.25), and mortality were similar among groups (RR = 0.62; 95%CI = 0.22-1.76, p = 0.37). Our findings suggest that FB and MB SRS, particularly oligometastases treated with single-fraction, are comparable in terms of LTC, RN, TT, and mortality. Further research is essential to draw definitive conclusions.

Modern Systemic therapies with Radiosurgery for Brain Metastases from Breast Cancer

Modern Systemic therapies with Radiosurgery for Brain Metastases from Breast Cancer

Consideration of Optimal Evaluation Metrics for Internal Gross Tumor Dose Relevant to Tumor Response in Multi-fraction Stereotactic Radiosurgery of Brain Metastasis.

Introduction In stereotactic radiosurgery (SRS) for brain metastasis (BM), the target dose inhomogeneity remains highly variable among modalities, irradiation techniques, and facilities, which can affect tumor response during and after multi-fraction SRS. Volumetric-modulated arcs (VMAs) can provide a concentrically-layered steep dose increase inside a gross tumor volume (GTV) boundarycompared to dynamic conformal arcs. This study was conducted to review the optimal evaluation method for the internal GTV doses relevant to maximal response and local control, specifically to examine the significance of the doses 2 mm and 4 mm inside the GTV boundary in VMA-based SRS. Materials and methods This was a planning study for the clinical scenario of a single BM and targeted 25 GTVs of >0.50 cc, including eight spherical models with diameters of 10-45 mm and 17 clinical BMs (GTV: 0.72-44.33 cc). SRS plans were generated for each GTV using VMA with a 5-mm leaf-width multileaf collimator and the optimization that prioritized the steepness of the dose gradient outside the GTV boundary without any internal dose constraints. The dose prescription and evaluation were based on the GTV D V-0.01 cc, a minimum dose of GTV minus 0.01 cc. Two planning systems were compared for the GTV - 2 mm and GTV - 4 mm structures that were generated by equally reducing 2 mm and 4 mm from the GTV surface. The D eIIVs, a minimum dose of the irradiated isodose volume equivalent to the GTV - 2 mm and GTV - 4 mm, were compared to other common metrics. Results The GTV - 2 mm and GTV - 4 mm volumes differed significantly between the systems. In the spherical GTVs, the irradiated isodose surfaces of GTV D 80% and D 50% corresponded to 0.4-1.6 mm (<2 mm) and 1.0-4.6 mm inside the GTV boundary, respectively. In the 25 GTVs, the GTV - 2 mm coverage with the D eIIV varied from 83.7% to 98.2% (95-98% in 68% of the cases), while the GTV coverage with the GTV - 2 mm D eIIV was 20.2-75.9%. In the 23 GTVs of ≥1.26 cc, the GTV coverage with the GTV - 4 mm D eIIVvaried from 1.9% to 55.6% (<50% in 87% of the cases). No significant difference was observed between the GTV D 50% and the GTV - 2 mm D eIIV, while the GTV - 4 mm D eIIV was significantly higher than the GTV D 50%. No significant correlations were observed between the GTV D 50% and the D eIIVs of the GTV - 2 mm and GTV - 4 mm. Conclusions The doses 2 mm and 4 mm inside a GTV have low correlations with the GTV D 50% and may be more relevant tomaximal response and local control for SRS of BM. The D eIIVinstead of the minimum dose of a fixed % coverage (e.g. D 98%) is suitable for reporting the doses 2 mm and 4 mm inside the GTV boundary in terms of avoiding the over- or under-coverage, with consideration tosubstantial variability inminus margin addition functions among planning systems. In VMA-based SRS with a steep dose gradient, the doses 2-4 mm inside a GTV decrease significantly as the GTV increases, which can attenuate the excessive dose exposure to the surrounding brain in a large BM due to the GTV shrinkage during multi-fraction SRS.

Appropriateness of Dose Attenuation Margin Outside the Gross Tumor Volume (GTV) in Volumetric-Modulated Arc-Based Radiosurgery for Brain Metastasis With the Steepest Dose Gradient Outside the GTV and Biologically Effective Dose 80 Gy to GTV Boundary.

Introduction In stereotactic radiosurgery (SRS) for brain metastasis (BM), volumetric-modulated arcs (VMA) can provide a suitable dose distribution and efficient delivery, even with a widely available 5-mm leaf-width multileaf collimator (MLC). The planning optimization with affirmatively accepting internal high doses of a gross tumor volume (GTV) enhances the steepness of the dose gradient outside the GTV. However, an excessively steep dose falloff outside a GTV is susceptible to insufficient coverage of inherent irradiation uncertainties with the dose attenuation margin. This study was conducted to examine the appropriateness of dose attenuation margin outside a GTV in 5-mm MLC VMA-based SRS with a steep dose gradient and dose prescription with a biologically effective dose (BED) 80 Gy in various fractions to the GTV margin. Materials and methods This was a planning study for the clinical scenario of a single BM and targeted 28 GTVs, including nine sphere-shaped models with diameters of 5-45 mm and 19 clinical BMs (GTV 0.08-44.33 cc). SRS plans were generated for each GTV using 5-mm MLC VMA with an optimization that prioritized the steepness of dose falloff outside the GTV boundary without any internal dose constraints. A prescribed dose with the BED 80 Gy in 1-10 fraction(s) was assigned to the GTV D V-0.01 cc, a minimum dose of GTV minus 0.01 cc (D >95% for GTV >0.20 cc, D 95% for GTV ≤0.20 cc). The BED was based on the linear-quadratic formula with an alpha/beta ratio of 10 (BED10). Two planning systems were compared for the GTV + 2 mm structures that were generated by adding an isotropic 2-mm margin to the GTV. Results The GTV + 2 mm volumes differed significantly between the systems and further varied on the dose-volume histograms. The D V-0.05 cc, D 98%, and D 95% of the GTV + 2 mm were associated with substantial over- or under-coverages of the GTV + 2 mm, although the irradiated isodose volumes (IIVs) of the D 98% were closest to the GTV + 2 mm in general. The coverage values of the GTV + 2 mm with the minimum dose of the IIV equivalent to the GTV + 2 mm, D eIIV, were 93.3%-98.7% (≥95% in 26 cases). The GTV + 2 mm D eIIV relative to the GTV D V-0.01 cc was ≥81.9% (BED10 ≥60 Gy in ≤5 fractions) in 13 cases, while those were <69.8% (BED10 <48 Gy in ≤5 fractions) in four cases with the GTV of 0.33-1.77 cc. Conclusions A dose attenuation margin outside a GTV can be excessively steep for some small GTVs in 5-mm MLC VMA-based SRS with a steepest dose gradient and a BED10 80 Gy in ≤5 fractions to the GTV D V-0.01 cc, for which an adjustment of the too precipitous dose gradient is preferred to sufficiently cover relevant uncertainties. A GTV + 2 mm D eIIV with ≥95% coverage is more suitable for evaluating the appropriateness of dose attenuation outside the GTV than other common metrics with a fixed % coverage or D V-≤0.05 cc. Given the substantial variability in margin addition functions among planning systems, dose prescription to a margin-added GTV is unsuitable for ensuring uniform dose prescription.

Severe pneumocranium after gamma knife stereotactic radiosurgery for brain metastasis: A case report and literature review.

Gamma knife stereotactic radiosurgery (GKRS) is a recognized safe and effective treatment for brain metastasis; however, some complications can present significant clinical challenges. This case report highlights a rare occurrence of cerebrospinal fluid (CSF) leakage and pneumocranium following GKRS, emphasizing the need for awareness and prompt management of these complications. A 35-year-old male with a history of malignant neoplasm of the lip in 2015 and perineural spread of malignancy into the left cavernous sinus was treated with GKRS in 2017. The patient was admitted emergently 39 days after discharge due to persistent headache and dizziness. Brain computed tomography (CT) revealed diffuse bilateral pneumocranium alongside an observation of CSF leakage. A surgical procedure involving a left frontal-temporal craniotomy was performed to excise a residual skull base tumor and repair the dura, guided by a navigator system. The conclusive pathological assessment revealed the presence of squamous cell carcinoma markers. The patient exhibited excellent tolerance to the entire procedure and experienced a prompt and uneventful recovery process. After surgery, the symptoms alleviated and CSF leak stopped. The follow-up image showed the pneumocranium resolved. Pneumocranium due to early-stage post-GKRS is uncommon. The rapid tumor shrinkage and timing of brain metastasis spreading through the dura can lead to CSF leak and pneumocranium. We reviewed current treatment options and presented a successful craniotomy-based dura repair case.

Prediction of treatment response after stereotactic radiosurgery of brain metastasis using deep learning and radiomics on longitudinal MRI data

We developed artificial intelligence models to predict the brain metastasis (BM) treatment response after stereotactic radiosurgery (SRS) using longitudinal magnetic resonance imaging (MRI) data and evaluated prediction accuracy changes according to the number of sequential MRI scans. We included four sequential MRI scans for 194 patients with BM and 369 target lesions for the Developmental dataset. The data were randomly split (8:2 ratio) for training and testing. For external validation, 172 MRI scans from 43 patients with BM and 62 target lesions were additionally enrolled. The maximum axial diameter (Dmax), radiomics, and deep learning (DL) models were generated for comparison. We evaluated the simple convolutional neural network (CNN) model and a gated recurrent unit (Conv-GRU)-based CNN model in the DL arm. The Conv-GRU model performed superior to the simple CNN models. For both datasets, the area under the curve (AUC) was significantly higher for the two-dimensional (2D) Conv-GRU model than for the 3D Conv-GRU, Dmax, and radiomics models. The accuracy of the 2D Conv-GRU model increased with the number of follow-up studies. In conclusion, using longitudinal MRI data, the 2D Conv-GRU model outperformed all other models in predicting the treatment response after SRS of BM.

748: External validation of a prediction model for radionecrosis after radiosurgery in brain metastases

748: External validation of a prediction model for radionecrosis after radiosurgery in brain metastases

Impact of Planning Target Volume Margins in Stereotactic Radiosurgery for Brain Metastasis: A Review

Impact of Planning Target Volume Margins in Stereotactic Radiosurgery for Brain Metastasis: A Review

Radiosurgery for Brain Metastases: Challenges in Imaging Interpretation after Treatment.

Stereotactic radiosurgery (SRS) has transformed the management of brain metastases by achieving local tumor control, reducing toxicity, and minimizing the need for whole-brain radiation therapy (WBRT). This review specifically investigates radiation-induced changes in patients treated for metastasis, highlighting the crucial role of magnetic resonance imaging (MRI) in the evaluation of treatment response, both at very early and late stages. The primary objective of the review is to evaluate the most effective imaging techniques for assessing radiation-induced changes and distinguishing them from tumor growth. The limitations of conventional imaging methods, which rely on size measurements, dimensional criteria, and contrast enhancement patterns, are critically evaluated. In addition, it has been investigated the potential of advanced imaging modalities to offer a more precise and comprehensive evaluation of treatment response. Finally, an overview of the relevant literature concerning the interpretation of brain changes in patients undergoing immunotherapies is provided.

Immune checkpoint inhibition and single fraction stereotactic radiosurgery in brain metastases from non-small cell lung cancer: an international multicenter study of 395 patients.

Approximately 80% of brain metastases originate from non-small cell lung cancer (NSCLC). Immune checkpoint inhibitors (ICI) and stereotactic radiosurgery (SRS) are frequently utilized in this setting. However, concerns remain regarding the risk of radiation necrosis (RN) when SRS and ICI are administered concurrently. A retrospective study was conducted through the International Radiosurgery Research Foundation. Logistic regression models and competing risks analyses were utilized to identify predictors of any grade RN and symptomatic RN (SRN). The study included 395 patients with 2,540 brain metastases treated with single fraction SRS and ICI across 11 institutions in four countries with a median follow-up of 14.2months. The median age was 67years. The median margin SRS dose was 19Gy; 36.5% of patients had a V12 Gy ≥ 10 cm3. On multivariable analysis, V12 Gy ≥ 10 cm3 was a significant predictor of developing any grade RN (OR: 2.18) and SRN (OR: 3.95). At 1-year, the cumulative incidence of any grade and SRN for all patients was 4.8% and 3.8%, respectively. For concurrent and non-concurrent groups, the cumulative incidence of any grade RN was 3.8% versus 5.3%, respectively (p = 0.35); and for SRN was 3.8% vs. 3.6%, respectively (p = 0.95). The risk of any grade RN and symptomatic RN following single fraction SRS and ICI for NSCLC brain metastases increases as V12 Gy exceeds 10 cm3. Concurrent ICI and SRS do not appear to increase this risk. Radiosurgical planning techniques should aim to minimize V12 Gy.

Interpretable AI-assisted clinical decision making (CDM) for dose prescription in radiosurgery of brain metastases

PurposeAI modeling physicians’ clinical decision-making (CDM) can improve the efficiency and accuracy of clinical practice or serve as a surrogate to provide initial consultations to patients seeking secondary opinions. In this study, we developed an interpretable AI model that predicts dose fractionation for patients receiving radiation therapy for brain metastases with an interpretation of its decision-making process. Materials/Methods152 patients with brain metastases treated by radiosurgery from 2017 to 2021 were obtained. CT images and target and organ-at-risk (OAR) contours were extracted. Eight non-image clinical parameters were also extracted and digitized, including age, the number of brain metastasis, ECOG performance status, presence of symptoms, sequencing with surgery (pre- or post-operative radiation therapy), de novo vs. re-treatment, primary cancer type, and metastasis to other sites. 3D convolutional neural networks (CNN) architectures with encoding paths were built based on the CT data and clinical parameters to capture three inputs: (1) Tumor size, shape, and location; (2) The spatial relationship between tumors and OARs; (3) The clinical parameters. The models fuse the features extracted from these three inputs at the decision-making level to learn the input independently to predict dose prescription. Models with different independent paths were developed, including models combining two independent paths (IM-2), three independent paths (IM-3), and ten independent paths (IM-10) at the decision-making level. A class activation score and relative weighting were calculated for each input path during the model prediction to represent the role of each input in the decision-making process, providing an interpretation of the model prediction. The actual prescription in the record was used as ground truth for model training. The model performance was assessed by 19-fold cross-validation, with each fold consisting of randomly selected 128 training, 16 validation, and 8 testing subjects. ResultThe dose prescriptions of 152 patient cases included 48 cases with 1 × 24 Gy, 48 cases with 1 × 20–22 Gy, 32 cases with 3 × 9 Gy, and 24 cases with 5 × 6 Gy prescribed by 8 physicians. IM-2 achieved slightly superior performance than IM-3 and IM-10, with 131 (86%) patients classified correctly and 21 (14%) patients misclassified. IM-10 provided the most interpretability with a relative weighting for each input: target (34%), the relationship between target and OAR (35%), ECOG (6%), re-treatment (6%), metastasis to other sites (6%), number of brain metastases (3%), symptomatic (3%), pre/post-surgery (3%), primary cancer type (2%), age (2%), reflecting the importance of the inputs in decision making. The importance ranking of inputs interpreted from the model also matched closely with a physician’s own ranking in the decision process. ConclusionInterpretable CNN models were successfully developed to use CT images and non-image clinical parameters to predict dose prescriptions for brain metastases patients treated by radiosurgery. Models showed high prediction accuracy while providing an interpretation of the decision process, which was validated by the physician. Such interpretability makes the model more transparent, which is crucial for the future clinical adoption of the models in routine practice for CDM assistance.

Leptomeningeal metastasis in patients with non-small cell lung cancer after stereotactic radiosurgery for brain metastasis.

Stereotactic radiosurgery (SRS) is an effective treatment for brain metastases (BMs) in patients with non-small cell lung cancer (NSCLC). However, factors associated with the development of post-SRS leptomeningeal metastasis (LM) remain unclear. The authors analyzed the incidence and risk factors of LM development in patients with NSCLC and BMs after SRS and examined the survival outcomes and prognostic factors after LM development. This retrospective study included patients with NSCLC treated with SRS for MRI-diagnosed BM from 2002 to 2021. The authors recorded various clinical and demographic data, including age, sex, tumor histology, molecular profile of tumors, extracranial disease status, previous craniotomy, Karnofsky Performance Status, systemic treatments, tumor volume, and number of BMs. The management and survival outcomes after LM diagnosis were also recorded. LM developed in 13.7% of patients with NSCLC and BMs after SRS treatment. Large initial tumor volume and more than 5 BM lesions, but not EGFR mutation status and post-SRS treatment, were associated with LM development after SRS. Multivariate analysis revealed that chemotherapy and targeted therapy after LM were associated with better survival in patients with LM after SRS. This study is the first to evaluate the risk factors for LM in a relatively large cohort of patients with NSCLC after SRS. In patients with BMs harboring risk factors for subsequent LM, such as initial tumor volume and number of metastatic lesions, aggressive therapies with high CNS penetrating ability should be considered.

Role of Boswellia Serrata in Management of CNS Radiation Necrosis After Radiosurgery for Brain Metastases

Role of Boswellia Serrata in Management of CNS Radiation Necrosis After Radiosurgery for Brain Metastases

Brain Metastasis Growth Kinetics: A Novel Prognosticator for Stereotactic Radiotherapy

AimsThe rate of size change in brain metastasis may have clinical implications on tumour biology and prognosis for patients who receive stereotactic radiotherapy (SRT). We analysed the prognostic value of brain metastasis size kinetics and propose a model for patients with brain metastases treated with linac-based SRT in predicting overall survival. Materials and methodsWe analysed the patients receiving linac-based SRT between 2010 and 2020. Patient and oncological factors, including the changes in sizes of brain metastasis between the diagnostic and stereotactic magnetic resonance imaging, were collected. The associations between prognostic factors and overall survival were assessed using Cox regression with least absolute selection and shrinkage operator (LASSO) checked by 500 bootstrap replications. Our prognostic score was calculated by evaluating the most statistically significant factors. Patients were grouped and compared according to our proposed score, Score Index for Radiosurgery in Brain Metastases (SIR) and Basic Score for Brain Metastases (BS-BM). ResultsIn total, 85 patients were included. We developed the prognostic model based on the most important predictors of overall survival: growth kinetics, i.e. percentage change in brain metastasis size per day between the diagnostic and stereotactic magnetic resonance imaging (hazard ratio per 1% increase, 1.32; 95% confidence interval 1.06–1.65), extracranial oligometastatic diseases (≤5 involvements) (hazard ratio 0.28; 95% confidence interval 0.16–0.52) and the presence of neurological symptoms (hazard ratio 2.99; 95% confidence interval 1.54–5.81). Patients with scores 0, 1, 2 and 3 had a median overall survival of 44.4 (95% confidence interval 9.6–not reached), 20.4 (95% confidence interval 15.6–40.8), 12.0 (95% confidence interval 7.2–22.8) and 2.4 (95% confidence interval 1.2–not reached) years, respectively. The optimism-corrected c-indices for our proposed model, SIR and BS-BM were 0.65, 0.58 and 0.54, respectively. ConclusionsBrain metastasis growth kinetics is a valuable metric for survival outcomes of SRT. Our model is useful in identifying patients with brain metastasis treated with SRT with different overall survival.

AI-assisted clinical decision making (CDM) for dose prescription in radiosurgery of brain metastases using three-path three-dimensional CNN

PurposeAI modeling physicians’ clinical decision-making (CDM) can improve the efficiency and accuracy of clinical practice or serve as a surrogate to provide initial consultations to patients seeking secondary opinions. In this study, we developed an AI network to model radiotherapy CDM and used dose prescription as an example to demonstrate its feasibility. Materials/Methods152 patients with brain metastases treated by radiosurgery from 2017 to 2021 were included. CT images and tumor and organ-at-risk (OAR) contours were exported. Eight relevant clinical parameters were extracted and digitized, including age, numbers of lesions, performance status (ECOG), presence of symptoms, arrangement with surgery (pre- or post-surgery radiation therapy), re-treatment, primary cancer type, and metastasis to other sites. A 3D convolutional neural network (CNN) architecture was built using three encoding paths with the same kernel and filters to capture the different image and contour features. Specifically, one path was built to capture the tumor feature, including the size and location of the tumor, another path was built to capture the relative spatial relationship between the tumor and OARs, and the third path was built to capture the clinical parameters. The model combines information from three paths to predict dose prescription. The actual prescription in the patient record was used as ground truth for model training. The model performance was assessed by 19-fold-cross-validation, with each fold consisting of randomly selected 128 training, 16 validation, and 8 testing subjects. ResultThe dose prescriptions of 152 patient cases included 48 cases with 1 × 24 Gy, 48 cases with 1 × 20–22 Gy, 32 cases with 3 × 9 Gy, and 24 cases with 5 × 6 Gy prescribed by 8 physicians. The AI model prescribed correctly for 124 (82 %) cases, including 44 (92 %) cases with 1 × 24 Gy, 36 (75 %) cases with 1 × 20–22 Gy, 25 (78 %) cases with 3 × 9 Gy, and 19 (79 %) cases with 5 × 6 Gy. Analysis of the failed cases showed the potential cause of practice variations across individual physicians, which were not accounted for in the model trained by the group data. Including clinical parameters improved the overall prediction accuracy by 20 %. ConclusionTo our best knowledge, this is the first study to demonstrate the feasibility of AI in predicting dose prescription in CDM in radiation therapy. Such CDM models can serve as vital tools to address healthcare disparities by providing preliminary consultations to patients in underdeveloped areas or as a valuable quality assurance (QA) tool for physicians to cross-check intra- and inter-institution practices.

Treatment Outcome of Gamma Knife Radiosurgery for Brain Metastasis from Thyroid Cancer: Favorable Local Control but Poor Survival

Brain metastasis from thyroid cancer (TCBM) is extremely rare; thus, despite a good treatment outcome for thyroid cancer, TCBM has shown poor clinical outcomes. Considering the short survival and poor general condition of patients with TCBM, stereotactic radiosurgery may be preferred to achieve local control. A total of 25 patients with TCBM who underwent Gamma Knife radiosurgery (GKS) were initially included in this study; however, 3 patients were excluded because of a lack of data. There were 7 men (31.8%) and 15 women (68.2%) and the mean age was 63.7 years. The most common type of thyroid cancer histology was papillary carcinoma. Fourteen patients (63.6%) harbored single brain metastatic tumor and 8 (36.3%) had multiple brain metastatic tumors. The mean duration from thyroid cancer diagnosis to detection of brain metastasis was 7.7 years (range, 0-23 years). The median dose of radiation of GKS was 22 Gy (range, 18-25 Gy). There was no radiation-induced complication after GKS. The median overall survival (OS) was 15 months and the 1-year OS of patients with TCBM was 63%, the 2-year OS was 38%, and the 5-year OS was 28%. The 6-month progression-free survival (PFS) for local recurrence of TCBM was 90.4%, the 1-year PFS was 84%, and the 3-year PFS was 84%. GKS showed favorable local control for TCBM. However, the rate of distant brain metastasis was high and median survival of patients with TCBM was only 15 months.

Brain metastases from NSCLC treated with stereotactic radiotherapy: prediction mismatch between two different radiomic platforms

Background and purposeRadiomics enables the mining of quantitative features from medical images. The influence of the radiomic feature extraction software on the final performance of models is still a poorly understood topic. This study aimed to investigate the ability of radiomic features extracted by two different radiomic platforms to predict clinical outcomes in patients treated with radiosurgery for brain metastases from non-small cell lung cancer. We developed models integrating pre-treatment magnetic resonance imaging (MRI)-derived radiomic features and clinical data. Materials and methodsPre-radiotherapy gadolinium enhanced axial T1-weighted MRI scans were used. MRI images were re-sampled, intensity-shifted, and histogram-matched before radiomic extraction by means of two different platforms (PyRadiomics and SOPHiA Radiomics). We adopted LASSO Cox regression models for multivariable analyses by creating radiomic, clinical, and combined models using three survival clinical endpoints (local control, distant progression, and overall survival). The statistical analysis was repeated 50 times with different random seeds and the median concordance index was used as performance metric of the models. ResultsWe analysed 276 metastases from 148 patients. The use of the two platforms resulted in differences in both the quality and the number of extractable features. That led to mismatches in terms of end-to-end performance, statistical significance of radiomic scores, and clinical covariates found significant in combined models. ConclusionThis study shed new light on how extracting radiomic features from the same images using two different platforms could yield several discrepancies. That may lead to acute consequences on drawing conclusions, comparing results across the literature, and translating radiomics into clinical practice.

PL01.6.A Radiomics outperforms semantic features for prediction of response to stereotactic radiosurgery in brain metastases

Abstract Background Brain metastases show different patterns of contrast enhancement, potentially reflecting hypoxic and necrotic tumor regions with reduced radiosensitivity. An objective evaluation of these patterns might allow a prediction of response to radiotherapy. We therefore investigated the potential of MRI radiomics in comparison with the visual assessment of semantic features to predict early response to stereotactic radiosurgery in patients with brain metastases. Material and Methods In this retrospective study, 150 patients with 308 brain metastases from solid tumors (NSCLC in 53% of patients) treated by stereotactic radiosurgery (single dose of 17-20 Gy) were evaluated. The response of each metastasis (partial or complete remission vs. stabilization or progression) was assessed within 180 days after radiosurgery. Patterns of contrast enhancement in the pre-treatment T1-weighted MR images were either visually classified (homogenous, heterogeneous, necrotic ring-like) or subjected to a radiomics analysis. Random forest models were optimized by cross-validation and evaluated in a hold-out test data set (30% of metastases). Results In total, 221/308 metastases (72%) responded to radiosurgery. The optimal radiomics model comprised 10 features and outperformed the model solely based on semantic features in the test data set (AUC, 0.71 vs. 0.56; accuracy, 69% vs. 54%). The diagnostic performance could be further improved by combining semantic and radiomics features resulting in an AUC of 0.74 and an accuracy of 75% in the test data set. Conclusion The developed radiomics model allowed prediction of early response to radiosurgery in patients with brain metastases and outperformed the visual assessment of patterns of contrast enhancement.