MY CONTENT

Does Embolization with Larger Coils Lead to Better Treatment of Aneurysms (DELTA) was an investigator-initiated multicenter prospective, parallel, randomized, controlled clinical trial. Patients had 4- to 12-mm unruptured aneurysms. Treatment allocation to either 15- (experimental group) or 10-caliber coils (control group) was randomized 1:1 using a Web-based platform. The primary efficacy outcome was a major recurrence or a residual aneurysm at follow-up angiography at 12 ± 2 months adjudicated by an independent core lab blinded to the treatment allocation. The trial was stopped after 210 patients were recruited between November 2013 and June 2017 when funding was interrupted. On an intent-to-treat analysis, the primary outcome was reached in 37 patients allocated to 15-caliber coils and 36 patients allocated to 10-caliber coils. Safety and other clinical outcomes were similar. Coiling of aneurysms randomized to 15-caliber coils achieved higher packing densities compared with 10-caliber coils, but this had no impact on the angiographic outcomes at 1 year, which were primarily driven by aneurysm size and initial angiographic results.

Fifty patients with high-grade gliomas from the authors’ hospital and 128 patients with high-grade gliomas from The Cancer Genome Atlas were included in this study. For each patient, the authors calculated 348 hand-crafted radiomics features and 8192 deep features generated by a pretrained convolutional neural network. They then applied feature selection and Elastic Net-Cox modeling to differentiate patients into long- and short-term survivors. In the 50 patients with high-grade gliomas from their institution, the combined feature analysis framework classified the patients into long- and short-term survivor groups with a log-rank test P value <.001. In the 128 patients from The Cancer Genome Atlas, the framework classified patients into long- and short-term survivors with a log-rank test P value of .014. In conclusion, the authors report successful production and initial validation of a deep transfer learning model combining radiomics and deep features to predict overall survival of patients with glioblastoma from postcontrast T1-weighed brain MR imaging.