Purpose: Treatment effect or radiation necrosis after stereotactic radiosurgery (SRS) for brain metastases is a common phenomenon often indistinguishable from true progression. Radiomics is an emerging field that promises to improve on conventional imaging. In this study, we sought to apply a radiomics-based prediction model to the problem of diagnosing treatment effect after SRS. Methods and Materials: We included patients in the Johns Hopkins Health System who were treated with SRS for brain metastases who subsequently underwent resection for symptomatic growth. We also included cases of likely treatment effect in which lesions grew but subsequently regressed spontaneously. Lesions were segmented semiautomatically on preoperative T1 postcontrast and T2 fluid-attenuated inversion recovery magnetic resonance imaging, and radiomic features were extracted with software developed in-house. Top-performing features on univariate logistic regression were entered into a hybrid feature selection/classification model, IsoSVM, with parameter optimization and further feature selection performed using leave-one-out cross-validation. Final model performance was assessed by 10-fold cross-validation with 100 repeats. All cases were independently reviewed by a board-certified neuroradiologist for comparison. Results: We identified 82 treated lesions across 66 patients, with 77 lesions having pathologic confirmation. There were 51 radiomic features extracted per segmented lesion on each magnetic resonance imaging sequence. An optimized IsoSVM classifier based on top-ranked radiomic features had sensitivity and specificity of 65.38% and 86.67%, respectively, with an area under the curve of 0.81 on leave-one-out cross-validation. Only 73% of cases were classifiable by the neuroradiologist, with a sensitivity of 97% and specificity of 19%. Conclusions: Radiomics holds promise for differentiating between treatment effect and true progression in brain metastases treated with SRS. A predictive model built on radiomic features from an institutional cohort performed well on cross-validation testing. These results warrant further validation in independent datasets. Such work could prove invaluable for guiding management of individual patients and assessing outcomes of novel interventions.

Stereotactic radiosurgery (SRS) and whole brain radiation therapy (WBRT) are effective treatments for management of brain metastases. Prospective trials comparing the 2 modalities in patients with fewer than 4 brain metastases demonstrate that overall survival (OS) is similar. Intracranial failure is more common after SRS, while WBRT is associated with neurocognitive decline. As technology has advanced, fewer technical obstacles remain for treating patients with 4 or more brain metastases with SRS, but level I data supporting its use are lacking. Observational prospective studies and retrospective series indicate that in patients with 4 or more brain metastases, performance status, total volume of intracranial disease, histology, and rate of development of new brain metastases predict outcomes more accurately than the number of brain metastases. It may be reasonable to initially offer SRS to some patients with 4 or more brain metastases. Initiating therapy with SRS avoids the acute and late sequelae of WBRT. Multiple phase III trials of SRS vs WBRT, both currently open or under development, are directly comparing quality of life and OS for patients with 4 or more brain metastases to help answer the question of SRS appropriateness for these patients.

Purpose/Objective(s) Regional failures occur in up to 15% of patients treated with stereotactic body radiotherapy (SBRT) for stage I/II lung cancer. This report focuses on the management of the unique scenario of isolated regional failures. Methods Patients treated initially with SBRT or accelerated hypo-fractionated radiotherapy were screened for curative intent treatment of isolated mediastinal failures (IMFs). Local control, regional control, progression-free survival, and distant control were estimated from the date of salvage treatment using the Kaplan–Meier method. Results Among 160 patients treated from 2002 to 2012, 12 suffered IMF and were amenable to salvage treatment. The median interval between treatments was 16 months (2–57 mo). Median salvage dose was 66 Gy (60–70 Gy). With a median follow-up of 10 months, the median overall survival was 15 months (95% confidence interval, 5.8–37 mo). When estimated from original treatment, the median overall survival was 38 months (95% confidence interval, 17–71 mo). No subsequent regional failures occurred. Distant failure was the predominant mode of relapse following salvage for IMF with a 2-year distant control rate of 38%. At the time of this analysis, three patients have died without recurrence while four are alive and no evidence of disease. High-grade toxicity was uncommon. Conclusions To our knowledge, this is first analysis of salvage mediastinal radiation after SBRT or accelerated hypofractionated radiotherapy in lung cancer. Outcomes appear similar to stage III disease at presentation. Distant failures were common, suggesting a role for concurrent or sequential chemotherapy. A standard full course of external beam radiotherapy is advisable in this unique clinical scenario.

BackgroundThe incidence of brain metastasis continues to increase as therapeutic strategies have improved for a number of solid tumors. The presence of brain metastasis is associated with worse prognosis but it is unclear if distinctive biomarkers can separate patients at risk for CNS related death.MethodsWe executed a single institution retrospective collection of brain metastasis from patients who were diagnosed with lung, breast, and other primary tumors. The brain metastatic samples were sent for RNA sequencing, proteomic and metabolomic analysis of brain metastasis. The primary outcome was distant brain failure after definitive therapies that included craniotomy resection and radiation to surgical bed. Novel prognostic subtypes were discovered using transcriptomic data and sparse non-negative matrix factorization.ResultsWe discovered two molecular subtypes showing statistically significant differential prognosis irrespective of tumor subtype. The median survival time of the good and the poor prognostic subtypes were 7.89 and 42.27 months, respectively. Further integrated characterization and analysis of these two distinctive prognostic subtypes using transcriptomic, proteomic, and metabolomic molecular profiles of patients identified key pathways and metabolites. The analysis suggested that immune microenvironment landscape as well as proliferation and migration signaling pathways may be responsible to the observed survival difference.ConclusionA multi-omics approach to characterization of brain metastasis provides an opportunity to identify clinically impactful biomarkers and associated prognostic subtypes and generate provocative integrative understanding of disease.