Publications by authors named "Wi-Sun Ryu"
Introduction: Intracranial aneurysm rupture is associated with high mortality and disability rates. Early detection is crucial, but increasing diagnostic workloads place significant strain on radiologists. We evaluated the efficacy of a deep learning algorithm in detecting unruptured intracranial aneurysms (UIAs) using time-of-flight (TOF) magnetic resonance angiography (MRA).
View Article and Find Full Text PDFBackground: Elevated heart rate in patients with acute ischemic stroke is associated with increased risk of mortality. Beta-blocker therapy is well known to reduce heart rate.
Methods And Results: This study was a post hoc analysis of patients with acute ischemic stroke with maximum heart rates ≥100 bpm.
Purpose: To validate JLK-LVO, a software detecting large vessel occlusion (LVO) on computed tomography angiography (CTA), within a multicenter dataset.
Methods: From 2021 to 2023, we enrolled patients with ischemic stroke who underwent CTA within 24-hour of onset at six university hospitals for validation and calibration datasets and at another university hospital for an independent dataset for testing model calibration. The diagnostic performance was evaluated using area under the curve (AUC), sensitivity, and specificity across the entire study population and specifically in patients with isolated middle cerebral artery (MCA)-M2 occlusion.
Background: This study aims to evaluate temporal trends of advanced treatments and related clinical outcomes of ischemic stroke through a decade-long trend analysis, using data from a comprehensive, national, multicenter registry. We also seek to identify areas in need of improvement.
Methods And Results: This analysis involved patients with ischemic stroke or transient ischemic attack registered prospectively in the CRCS-K-NIH (Clinical Research Center for Stroke in Korea-National Institute of Health) registry between 2011 and 2020.
Background: Research specifically addressing the efficacy of rosuvastatin versus atorvastatin in patients with ischemic stroke is insufficient. Using a large stroke registry, we investigated whether 2 commonly used statins, rosuvastatin and atorvastatin, differ in their effectiveness in reducing the risk of vascular events in patients with acute ischemic stroke.
Methods: We analyzed data from a nationwide stroke registry in South Korea between January 2011 and April 2022.
Study Objectives: Undiagnosed or untreated moderate to severe obstructive sleep apnea (OSA) increases cardiovascular risks and mortality. Early and efficient detection is critical, given its high prevalence. We aimed to develop a practical and efficient approach for obstructive sleep apnea screening, using simple facial photography and sleep questionnaires.
View Article and Find Full Text PDFObjective: Computed tomography perfusion (CTP) imaging is crucial in quantifying cerebral blood flow (CBF) and thereby making an endovascular treatment (EVT) after large vessel occlusion. However, CTP is prone to overestimating the ischemic core. We sought to delineate the optimal regional CBF (rCBF) thresholds of pre-EVT CTP.
View Article and Find Full Text PDFBackground: This study aimed to explore the association between admission HbA1c and the risk of 1-year vascular outcomes stratified by age group in patients with acute ischemic stroke (AIS) and diabetes mellitus (DM).
Methods: This study analyzed prospective multicenter data from patients with AIS and DM. Admission HbA1C were categorized as:≤6.
Article Synopsis
- This study examined how non-traditional lipid profiles, specifically the LDL/HDL ratio, affect the risk of vascular events within a year in stroke patients already on statins and with low LDL-C levels.
- The analysis included 7028 patients with acute ischemic strokes and found a significant association between higher LDL/HDL ratios and increased risk of recurrent stroke, heart attack, or death after adjusting for other variables.
- The results suggest that even with low LDL-C levels due to statin use, monitoring the LDL/HDL ratio is important to assess residual risk after a stroke.
Article Synopsis
- Delayed-onset post-stroke cognitive decline (PSCD) can provide insights into cognitive impairment and dementia, potentially linked to amyloid pathology and cerebral small vessel disease (cSVD).
- The study assessed patients who were cognitively normal after a stroke and identified those who experienced cognitive decline using MMSE scores and various imaging techniques.
- Among the 208 patients, few showed significant differences in cSVD, with white matter hyperintensities affecting cognitive scores in those who declined, while amyloid positivity was rare, though some non-amyloid decliners exhibited correlation patterns related to cognitive outcomes.
Article Synopsis
- A multi-center MRI study investigated how white matter hyperintensity (WMH) affects recovery after stroke, focusing on different severity levels of ischemic stroke.
- Higher WMH levels were linked to worse outcomes three months later, but the impact varied based on initial stroke severity: mild strokes showed a dose-dependent effect while moderate-to-severe strokes had a threshold effect.
- The study found that WMH impacted 3-month recovery more significantly in those with mild strokes, suggesting that increased WMH burden worsens recovery, but its effect is less pronounced in more severe strokes.
Background: To evaluate the stand-alone efficacy and improvements in diagnostic accuracy of early-career physicians of the artificial intelligence (AI) software to detect large vessel occlusion (LVO) in CT angiography (CTA).
Methods: This multicenter study included 595 ischemic stroke patients from January 2021 to September 2023. Standard references and LVO locations were determined by consensus among three experts.
Introduction: We developed and externally validated a fully automated algorithm using deep learning to detect large vessel occlusion (LVO) in computed tomography angiography (CTA).
Method: A total of 2,045 patients with acute ischemic stroke who underwent CTA were included in the development of our model. We validated the algorithm using two separate external datasets: one with 64 patients (external 1) and another with 313 patients (external 2), with ischemic stroke.
Article Synopsis
- A study was conducted to develop deep learning algorithms for the automatic segmentation of white matter hyperintensity (WMH) lesions in patients with cerebral infarction, involving a large dataset of 8,421 patients from multiple hospitals in Korea.
- Two models, 2D UNet and SE-Unet, were trained and validated using FLAIR MRI images, with performance measured against a human-segmented gold standard using various statistical metrics.
- Results showed that while both models had good performance, the SE-Unet outperformed the UNet with higher average Dice Similarity Coefficients (DSCs) in both internal and external validations, indicating it was more reliable for WMH segmentation.
Labeling errors can significantly impact the performance of deep learning models used for screening chest radiographs. The deep learning model for detecting pulmonary nodules is particularly vulnerable to such errors, mainly because normal chest radiographs and those with nodules obscured by ribs appear similar. Thus, high-quality datasets referred to chest computed tomography (CT) are required to prevent the misclassification of nodular chest radiographs as normal.
View Article and Find Full Text PDFArticle Synopsis
- - This study compared two software packages, RAPID and JLK-CTP, for estimating ischemic core and hypoperfused tissue volumes in stroke patients using computed tomography perfusion (CTP) scans.
- - Researchers analyzed data from 327 patients, finding that both software packages showed excellent agreement in estimating ischemic core volumes, particularly at a blood flow threshold of less than 30%.
- - Overall, JLK-CTP and RAPID proved to be reliable tools for assessing ischemic core volumes early after stroke onset, although there were some indications that they might slightly overestimate these volumes.
Article Synopsis
- Accurate classification of ischemic stroke subtypes is crucial for effective prevention strategies, and a deep learning algorithm was developed using diffusion-weighted imaging (DWI) and atrial fibrillation (AF) data for this purpose.
- The study involved training models on a dataset of 2,988 stroke patients using two algorithms: one based solely on DWI and another incorporating AF as a factor.
- Results showed that the DWI+AF algorithm achieved higher agreement rates with expert opinions compared to the DWI-only method, indicating its effectiveness in accurately classifying stroke subtypes.
Background: Early identification of large vessel occlusion (LVO) in patients with ischemic stroke is crucial for timely interventions. We propose a machine learning-based algorithm (JLK-CTL) that uses handcrafted features from noncontrast computed tomography to predict LVO.
Methods: We included patients with ischemic stroke who underwent concurrent noncontrast computed tomography and computed tomography angiography in seven hospitals.
Article Synopsis
- - The study reviews how dual antiplatelet therapy (DAPT-AC) with aspirin and clopidogrel has been increasingly used among stroke patients who didn't qualify for major clinical trials, particularly after the CHANCE trial results became available in 2013.
- - Analysis of data from over 32,000 patients from 2008 to 2022 showed that the usage of DAPT-AC rose significantly from 33% in 2008 to 78% in 2022, while the use of other antiplatelet medications decreased.
- - Despite this increase in DAPT-AC usage, clinical outcomes, including stroke rates and mortality, improved only slightly, indicating ongoing efforts are needed to enhance recovery
Introduction: Detection of atrial fibrillation (AF) is crucial for preventing recurrence in patients with ischemic stroke. We aimed to examine whether the left atrial volume index (LAVI) and global longitudinal peak strain (GLPS) are associated with AF in patients with ischemic stroke.
Methods: We prospectively analyzed 678 consecutive patients with ischemic stroke.
Background And Purpose: Multiple attempts at intracranial hemorrhage (ICH) detection using deep-learning techniques have been plagued by clinical failures. We aimed to compare the performance of a deep-learning algorithm for ICH detection trained on strongly and weakly annotated datasets, and to assess whether a weighted ensemble model that integrates separate models trained using datasets with different ICH improves performance.
Methods: We used brain CT scans from the Radiological Society of North America (27,861 CT scans, 3,528 ICHs) and AI-Hub (53,045 CT scans, 7,013 ICHs) for training.
Background And Purpose: The influence of imaging features of brain frailty on outcomes were investigated in acute ischemic stroke patients with minor symptoms and large-vessel occlusion (LVO).
Methods: This was a retrospective analysis of a prospective, multicenter, nationwide registry of consecutive patients with acute (within 24 h) minor (National Institutes of Health Stroke Scale score=0-5) ischemic stroke with anterior circulation LVO (acute minor LVO). Brain frailty was stratified according to the presence of an advanced white-matter hyperintensity (WMH) (Fazekas grade 2 or 3), silent/old brain infarct, or cerebral microbleeds.
Article Synopsis
- Ischemic strokes vary in type, which may affect how low-density lipoprotein (LDL) cholesterol levels relate to early health outcomes like stroke recurrence, heart attacks, and overall mortality.
- A study involving over 38,500 acute ischemic stroke patients found that those with the lowest LDL cholesterol levels (<70 mg/dl) had the highest rates of adverse outcomes within three months.
- The research revealed that the relationship between LDL cholesterol levels and mortality differed by stroke subtype, indicating that both high and low LDL levels present different risks depending on the stroke type.
Article Synopsis
- The study examined nonhypertensive white matter hyperintensity (WMH) as a risk factor in acute ischemic strokes and transient ischemic attacks, involving over 3,000 patients, half with hypertension and half without.
- Approximately 35% of nonhypertensive patients showed moderate-to-severe WMH, linked to factors like age and previous strokes, while hypertensive patients exhibited different WMH patterns and a stronger correlation to small vessel occlusions.
- The findings indicated that WMH significantly affects functional outcomes after 3 months and is associated with cumulative risks of recurrent stroke and mortality, although its impact varied based on hypertension status.
Background: There is limited information on the delivery of acute stroke therapies and secondary preventive measures and clinical outcomes over time in young adults with acute ischemic stroke. This study investigated whether advances in these treatments improved outcomes in this population.
Methods: Using a prospective multicenter stroke registry in Korea, young adults (aged 18-50 years) with acute ischemic stroke hospitalized between 2008 and 2019 were identified.