Background Cerebral aneurysms should be treated before rupture because ruptured aneurysms result in serious disability. Therefore, accurate prediction of rupture risk is important and has been estimated using various hemodynamic factors. Objective To suggest a new way to predict rupture risk in cerebral aneurysms using a novel deep learning model based on hemodynamic parameters for better decision-making about treatment. Methods A novel convolutional neural network (CNN) model was used for rupture risk prediction retrospectively of 123 aneurysm cases. To include the effect of hemodynamic parameters into the CNN, the hemodynamic parameters were first calculated using computational fluid dynamics and fluid–structure interaction. Then, they were converted into images for training the CNN using a novel approach. In addition, new data augmentation methods were devised to obtain sufficient training data. A total of 53,136 images generated by data augmentation were used to train and test the CNN. Results The CNNs trained with wall shear stress (WSS), strain, and combination images had area under the receiver operating characteristics curve values of 0.716, 0.741, and 0.883, respectively. Based on the cut-off values, the CNN trained with WSS (sensitivity: 0.5, specificity: 0.79) or strain (sensitivity: 0.74, specificity: 0.71) images alone was not highly predictive. However, the CNN trained with combination images of WSS and strain showed a sensitivity and specificity of 0.81 and 0.82, respectively. Conclusion CNN-based deep learning algorithm using hemodynamic factors, including WSS and strain, could be an effective tool for predicting rupture risk in cerebral aneurysms with good predictive accuracy.

Purpose: The purpose of this study was to evaluate the prevalence and risk factors of unruptured intracranial aneurysms (UIAs), which can help establish guidelines of treatment for asymptomatic Korean adults using 3T magnetic resonance angiography (MRA).Materials and Methods: Our Institutional Review Board approved this retrospective study, and informed consent was waived. All patients consisted of healthy individuals who underwent brain MRA using 3T magnetic resonance imaging between January 2011 and December 2012 as part of a routine health examination. Patient data and follow-up results were obtained from medical records.Results: A total of 2,118 individuals (mean age=53.9±9.6 years, male:female=1,188:930) who had undergone brain MRA were enrolled in the study. UIAs were found in 80 patients with 105 UIAs (3.77%). Female predominance (55% in UIA versus 43.47% in non-UIA, P=0.0416) and hypertension were more common in the UIA group (43.75% vs. 28.8%, P=0.004, respectively). The mean size of the aneurysms was 3.10±1.62 mm, and they were all saccular in shape and asymptomatic. The UIAs were most common in the internal carotid artery (59.1%), internal carotid-posterior communicating artery (15.2%), middle cerebral artery (9.5%), anterior communicating artery (8.6%), anterior cerebral artery (4.8%), and vertebral artery (2.9%). Twenty-eight of 80 patients (35%) had multiple aneurysms. The incidence of UIAs increased significantly with age (P=0.014).Conclusion: In single center experience, we demonstrated the characteristics and prevalence of UIAs in asymptomatic adults, which may help establish guidelines or therapeutic standards for UIAs.

Purpose: While symptomatic basilar artery (BA) stenosis is associated with a higher risk of recurrent stroke or death, there is no consensus on the management of these patients who are refractory to antiplatelet therapy. This study retrospectively assesses the outcomes of endovascular treatment (EVT) for symptomatic BA stenosis.Materials and Methods: We conducted a retrospective review of patients with symptomatic BA stenosis who underwent EVT, including angioplasty or stenting, from 2006 to 2018. A total of 15 patients, who experienced transient ischemic attacks or strokes despite dual antiplatelet therapy, were included. EVT was performed under local anesthesia after pretreatment with antiplatelet medications. Angiographic follow-up was performed at 12 and 24 months post-EVT. Clinical outcomes were evaluated using the modified Rankin Scale (mRS).Results: EVT was successfully completed in all patients. Peri/post-procedural complications occurred in 33% of cases, including in-stent thrombosis, intracranial hemorrhage, and pontine infarction. At long-term follow-up (mean 98.5±80.5 months), 73.3% of patients achieved a favorable functional outcome (mRS≤2) without disability or mortality. Patients with unfavorable outcomes had previous infarcts, with 2 experiencing new pontine infarctions after stenting.Conclusion: This study suggests that EVT, including angioplasty and stenting, may offer promise as a treatment option for symptomatic BA stenosis refractory to medical therapy. However, the procedure carries a notable risk of complications, especially in patients with severe stenosis and previous infarcts. Careful patient selection, based on clinical and radiological criteria, is crucial.

Purpose: Patients with minor stroke (National Institutes of Health Stroke Scale score ≤5) and large vessel occlusion (LVO) often experience neurological deterioration >24 hours after onset. However, the efficacy of endovascular reperfusion therapy in these patients remains unclear. The aim of this study was to determine the efficacy and safety of reperfusion therapy in patients with minor stroke and neurological deterioration >24 hours after onset.Materials and Methods: Data were retrospectively reviewed from patients between January 2019 and April 2022 who met the following criteria: (1) minor stroke and small definitive ischemic lesions at initial visit, (2) onset to neurological deterioration >24 hours, (3) cortical signs, Alberta Stroke Program Early computed tomography (CT) Score >6 points, and large artery occlusion confirmed by CT angiography at neurological deterioration. Efficacy and safety outcomes were based on final thrombolysis in cerebral infarction (TICI), incidence of symptomatic intracranial hemorrhage (ICH), and mortality. Outcomes were assessed using the modified Rankin Scale (mRS) at 3 months. Good outcome was defined as a mRS of 0, 1, or 2.Results: Data from 26 patients (38.4% female, mean age 75.8 years) were analyzed; 18 (69.2%) had a good outcome. A final TICI of 2b or 3 was observed in 24 (92.3%) patients. No other adverse events, including dissection, vasospasm or distal embolization, were observed during the procedures. Hemorrhagic events occurred in 8 patients after the procedure; however, there were no symptomatic ICHs. Good prognostic factors were younger age (P=0.062) and carotid stenting (P=0.025).Conclusion: Endovascular reperfusion therapy performed in selected patients with minor stroke, LVO, and neurological deterioration >24 hours after stroke onset demonstrated favorable outcomes and safety.