Journal of neuroimaging : official journal of the American Society of Neuroimaging
-
An essential step during endovascular thrombectomy is identifying the occluded arterial vessel on a cerebral digital subtraction angiogram (DSA). We developed an algorithm that can detect and localize the position of occlusions in cerebral DSA. ⋯ This work demonstrates that a deep learning strategy using a limited dataset can generate effective representations used to identify LVOs. Generating an expanded and more complete dataset of LVOs with obstructed LVOs is likely the best way to improve the model's ability to localize LVOs.
-
To present the first study analyzing the clinical and radiological course of carotid-cavernous fistulas (CCFs) following incomplete embolization. The study compares magnetic resonance angiography (MRA) to plain angiography (digital subtraction angiography [DSA]) and investigates the long-term ophthalmological impact of residual fistula. ⋯ The goal of CCF treatment is safe and complete embolization. However, if adequate flow reduction is achieved, both direct and indirect CCFs tend to spontaneously thrombose. Residual flow does not result in ophthalmological deterioration until the fistula is completely closed. MRA may not be sufficiently sensitive to detect residues of fistulas including cortical venous drainage. Therefore, complete CCF closure should be confirmed through DSA.
-
To define cystic patterns resulting from term hypoxic ischemic injury (HII) on delayed Magnetic Resonance Imaging (MRI) and determine associated HII patterns and lesions that reflect the severity of injury, from a database of African children with cerebral palsy. ⋯ Cystic encephalomalacia was seen in almost one-third of patients with term HII imaged with delayed MRI, with a similar prevalence of focal-cystic and multicystic injury. Multicystic injury was associated with caudate and globus pallidi involvement, typical of the BGT pattern of HII, whereas the focal-cystic pattern was associated with ulegyria, typical of watershed injury.
-
Hemorrhagic transformation (HT) is a common complication of endovascular thrombectomy (EVT) in patients with acute ischemic stroke (AIS). Our study aims to investigate the clinical and imaging predictors of HT and symptomatic intracranial hemorrhage (sICH) in patients who underwent EVT. ⋯ Collateral status, ASPECTS, relative CBF ratio, and blood glucose on admission were predictors for HT in AIS patients, while collateral status, ASPECTS, and blood glucose on admission were also predictors for sICH. In addition, the established predictive model showed good diagnostic value for prediction of HT after EVT.
-
We aimed to predict the functional outcome of acute ischemic stroke patients with anterior circulation large vessel occlusions (LVOs), irrespective of how they were treated or the severity of the stroke at admission, by only using imaging parameters in machine learning models. ⋯ Using only imaging parameters, our model had an AUROC of 0.91 which was superior to most previous studies, indicating that imaging parameters may be as accurate as conventional predictors. The multiphase CTA collateral score was the most predictive variable, highlighting the importance of collaterals.