Table of Contents
Perspectives
Review Articles
Research Perspectives
General Contents
- Application of Deep Learning to Predict Standardized Uptake Value Ratio and Amyloid Status on 18F-Florbetapir PET Using ADNI Data
Using the Alzheimer's Disease Neuroimaging Initiative dataset, the authors identified 2582 18F-florbetapir PET scans, which were separated into positive and negative cases by using a standardized uptake value ratio threshold of 1.1. They trained convolutional neural networks to predict standardized uptake value ratio and classify amyloid status. The best performance was seen for ResNet-50 by using regression before classification, 3 input PET slices, and pretraining, with a standardized uptake value ratio root-mean-squared error of 0.054, corresponding to 95.1% correct amyloid status prediction. The best trained network was more accurate than humans (96% versus a mean of 88%, respectively). They conclude that deep learning algorithms can estimate standardized uptake value ratio and use this to classify 18F-florbetapir PET scans and have promise to automate this laborious calculation.
- Resting-State Brain Activity for Early Prediction Outcome in Postanoxic Patients in a Coma with Indeterminate Clinical Prognosis
The authors used resting-state fMRI in a prospective study to compare whole-brain functional connectivity between patients with good and poor outcomes, implementing support vector machine learning. They automatically predicted coma outcome using resting-state fMRI and also compared the prediction based on resting-state fMRI with the outcome prediction based on DWI. Of 17 eligible patients who completed the study procedure (among 351 patients screened), 9 regained consciousness and 8 remained comatose. They found higher functional connectivity in patients recovering consciousness, with greater changes occurring within and between the occipitoparietal and temporofrontal regions. Coma outcome prognostication based on resting-state fMRI machine learning was very accurate, notably for identifying patients with good outcome. They conclude that resting-state fMRI might bridge the gap left in early prognostication of postanoxic patients in a coma by identifying those with both good and poor outcomes.
- Long-Term Outcomes of the WEB Device for Treatment of Wide-Neck Bifurcation Aneurysms
With a mean follow-up of approximately 15 months, the authors evaluated 41 cases of wide-neck aneurysms. Overall, 78.8% of the aneurysms had complete occlusion in the last follow-up, and 19.5% required retreatment with additional endovascular devices. A good clinical outcome (mRS: 0–2) was obtained in 95.1% of the patients, and the overall treatment-related morbidity and mortality rates were 2.4% and 0.0%, respectively. They conclude that treatment of wide-neck bifurcation aneurysms with a WEB device is feasible with an acceptable safety and efficacy rate.
- Fetal and Neonatal MRI Predictors of Aggressive Early Clinical Course in Vein of Galen Malformation
The authors aimed to identify brain MR imaging characteristics obtained from fetal and early neonatal scans that can predict the clinical presentation. A total of 32 neonatal patients (21 patients in the neonatal at-risk cohort, 11 in the infantile treatment cohort) were identified. Maximal mediolateral diameter and cross-sectional area at the narrowest point of the straight/falcine sinus were most predictive of clinical evolution into the neonatal at-risk cohort. This measurement clearly and unambiguously differentiated between high- and low-risk cohorts. The ability to accurately predict clinical evolution after birth based on fetal MR imaging can be of help for both caregivers and families, enabling better preparedness for urgent treatment and better planning for allocation of resources.
- Counterpoint: Conventional Fluoroscopy-Guided Selective Cervical Nerve Root Block—A Safe, Effective, and Efficient Modality in the Hands of an Experienced Proceduralist
Two-hundred fifty-four conventional fluoroscopy-guided selective cervical nerve root blocks were performed via an anterolateral approach with an average fluoroscopy time of 24.3 seconds for all cases. There were no aborted procedures and no major or permanent complications. There were 14 minor complications; 12 of these were periprocedural and resolved by the 2-week follow-up visit. One-hundred eighty-five patients (75.2%) reported pain improvement of >50% from baseline at 15 minutes postinjection. The authors conclude that this study confirms that conventional fluoroscopy is as safe and effective as CT for the guidance of selective cervical nerve root block when using a meticulous technique and a nonparticulate steroid and performed by an experienced proceduralist.
- High Prevalence of Spinal Cord Cavernous Malformations in the Familial Cerebral Cavernous Malformations Type 1 Cohort
With prospective imaging to screen the spinal cord, the authors found SCCMs in 21 of 29 familial CCM1 patients, a prevalence of 72.4%. They conclude that the study demonstrates that SCCMs are indeed a common finding in patients with familial CCM and supports the idea of familial CCM syndrome as a progressive systemic disease that affects the entire central nervous system. They found an expected positive correlation of number of SCCMs with both patient age and number of intracranial CCMs. They also found a high prevalence of vertebral intraosseous vascular malformations (69%), including atypical (T1 hypointense) intraosseous vascular malformation in approximately 38% of the patients who underwent MR imaging screening.
Online Features
Letters