Search

Purpose: The clinical management of brain metastases after stereotactic radiosurgery (SRS) is difficult, because a physician must review follow-up magnetic resonance imaging (MRI) scans to determine treatment outcome, which is often labor intensive. The purpose of this study was to develop an automated framework to contour brain metastases in MRI to help treatment planning for SRS and understand its limitations. Methods and Materials: Two self-adaptive nnU-Net models trained on postcontrast 3-dimensional T1-weighted MRI scans from patients who underwent SRS were analyzed. Performance was evaluated by computing positive predictive value (PPV), sensitivity, and Dice similarity coefficient (DSC). The training and testing sets included 3482 metastases on 845 patient MRI scans and 930 metastases on 206 patient MRI scans, respectively. Results: In the per-patient analysis, PPV was 90.1% ± 17.7%, sensitivity 88.4% ± 18.0%, DSC 82.2% ± 9.5%, and false positive (FP) 0.4 ± 1.0. For large metastases (≥6 mm), the per-patient PPV was 95.6% ± 17.5%, sensitivity 94.5% ± 18.1%, DSC 86.8% ± 7.5%, and FP 0.1 ± 0.4. The quality of autosegmented true-positive (TP) contours was also assessed by 2 physicians using a 5-point scale for clinical acceptability. Seventy-five percent of contours were assigned scores of 4 or 5, which shows that contours could be used as-is in clinical application, and the remaining 25% were assigned a score of 3, which means they needed minor editing only. Notably, a deep dive into FPs indicated that 9% were TP metastases not identified on the original radiology review, but identified on subsequent follow-up imaging (early detection). Fifty-four percent were real metastases (TP) that were identified but purposefully not contoured for target treatment, mainly because the patient underwent whole-brain radiation therapy before/after SRS treatment. Conclusions: These findings show that our tool can help radiologists and radiation oncologists detect and contour tumors from MRI, make precise decisions about suspicious lesions, and potentially find lesions at early stages.

Background: Brainstem toxicity after radiation therapy (RT) is a devastating complication and a particular concern with proton radiation (PBT). We investigated the incidence and clinical correlates of brainstem injury in pediatric brain tumors treated with PBT., Methods: All patients <21 years with brain tumors treated with PBT at our institution from 2007-2019, with a brainstem Dmean >30 Gy and/or Dmax >50.4 Gy were included. Symptomatic brainstem injury (SBI) was defined as any new or progressive cranial neuropathy, ataxia, and/or motor weakness with corresponding radiographic abnormality within brainstem., Results: A total of 595 patients were reviewed and 468 (medulloblastoma = 200, gliomas = 114, ependymoma = 87, ATRT = 43) met our inclusion criteria. Median age at RT was 6.3 years and median prescribed RT dose was 54Gy [RBE]. Fifteen patients (3.2%) developed SBI, at a median of 4 months after RT. Grades 2, 3, 4, and 5 brainstem injuries were seen in 7, 5, 1, and 2 patients respectively. Asymptomatic radiographic changes were seen in 51 patients (10.9%). SBI was significantly higher in patients with age ≤3 years, female gender, ATRT histology, patients receiving high-dose chemotherapy with stem cell rescue, and those not receiving craniospinal irradiation. Patients with SBI had a significantly higher V50-52. In 2014, our institution started using strict brainstem dose constraints (Dmax ≤57 Gy, Dmean ≤52.4 Gy, and V54≤10%). There was a trend towards decrease in SBI from 4.4% (2007-2013) to 1.5% (2014-2019) (P = .089) without affecting survival., Conclusion: Our results suggest a low risk of SBI after PBT for pediatric brain tumors, comparable to photon therapy. A lower risk was seen after adopting strict brainstem dose constraints., (© The Author(s) 2022. Published by Oxford University Press on behalf of the Society for Neuro-Oncology. All rights reserved. For permissions, please e-mail: journals.permissions@oup.com.)