- Deep Transfer Learning and Radiomics Feature Prediction of Survival of Patients with High-Grade Gliomas
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.
- Flow-Diversion Treatment for Unruptured Nonsaccular Intracranial Aneurysms of the Posterior and Distal Anterior Circulation: A Meta-Analysis
The authors’ aim was to analyze the outcomes after flow diversion among nonsaccular unruptured lesions. Fifteen studies (213 aneurysms) were included in the analysis. The long-term adequate occlusion rate was 85.3%. Treatment-related complications were 17.4%. Overall, 15% were ischemic events. They conclude that unruptured nonsaccular aneurysms located in the posterior and distal anterior circulations can be effectively treated with a flow-diversion strategy. Nevertheless, treatment-related complications are not negligible, with about 15% ischemic events and 8% morbidity. Larger size (>10 mm) significantly increased the risk of procedure-related adverse events among nonsaccular lesions.
- Anatomy of the Great Posterior Radiculomedullary Artery
The authors describe the microsurgical anatomy of the great posterior radiculomedullary artery with emphasis on its morphometric parameters as well as its implications for spinal cord blood supply. The artery of Adamkiewicz in spinal cord specimens (n = 50) was injected with colored latex until the small-caliber arterial vessels were filled and the great posterior radiculomedullary artery was identified. The course, diameter, and location of great posterior radiculomedullary artery were documented. A great posterior radiculomedullary artery was identified in 36 (72%) spinal cord specimens. In 11 (22%) specimens, bilateral great posterior radiculomedullary arteries were present. In 13 cases (26%), a unilateral left-sided great posterior radiculomedullary artery was identified. In 11 cases (22%), a unilateral right-sided great posterior radiculomedullary artery was identified.
- Intracranial Atherosclerotic Burden on 7T MRI Is Associated with Markers of Extracranial Atherosclerosis: The SMART-MR Study
Intracranial atherosclerosis, a major risk factor for ischemic stroke, is thought to have different atherogenic mechanisms than extracranial atherosclerosis. Studies investigating their relationship in vivo are sparse and report inconsistent results. Within the Second Manifestations of ARTerial disease–Magnetic Resonance (SMART) Study, cross-sectional analyses were performed in 130 patients with a history of vascular disease and with assessable 7T intracranial vessel wall MR imaging data. Intracranial atherosclerosis burden was defined as the number of intracranial vessel wall lesions in the circle of Willis and its major branches. Significant associations were observed between higher intracranial atherosclerosis burden and carotid intima-media thickness, 50%–100% carotid stenosis versus no stenosis, ankle-brachial index, and estimated glomerular filtration rate. No significant differences in intracranial atherosclerosis burden were found among different categories of vascular disease.