Background: and Purpose Accurate classification of ischemic stroke subtype is important for effective secondary prevention of stroke. We used diffusion-weighted image (DWI) and atrial fibrillation (AF) data to train a deep learning algorithm to classify stroke subtype. Methods: Model development was done in 2,988 patients with ischemic stroke from three centers by using U-net for infarct segmentation and EfficientNetV2 for subtype classification. Experienced neurologists (n=5) determined subtypes for external test datasets, while establishing a consensus for clinical trial datasets. Automatically segmented infarcts were fed into the model (DWI-only algorithm). Subsequently, another model was trained, with AF included as a categorical variable (DWI+AF algorithm). These models were tested: (1) internally against the opinion of the labeling experts, (2) against fresh external DWI data, and (3) against clinical trial dataset. Results: In the training-and-validation datasets, the mean (±standard deviation) age was 68.0±12.5 (61.1% male). In internal testing, compared with the experts, the DWI-only and the DWI+AF algorithms respectively achieved moderate (65.3%) and near-strong (79.1%) agreement. In external testing, both algorithms again showed good agreements (59.3%–60.7% and 73.7%–74.0%, respectively). In the clinical trial dataset, compared with the expert consensus, percentage agreements and Cohen’s kappa were respectively 58.1% and 0.34 for the DWI-only vs. 72.9% and 0.57 for the DWI+AF algorithms. The corresponding values between experts were comparable (76.0% and 0.61) to the DWI+AF algorithm. Conclusion Our model trained on a large dataset of DWI (both with or without AF information) was able to classify ischemic stroke subtypes comparable to a consensus of stroke experts.

Background: and PurposeThe first-line medications for the symptomatic treatment of rapid eye movement sleep behavior disorder (RBD) are clonazepam and melatonin taken at bedtime. We aimed to identify the association between depression and treatment response in patients with idiopathic RBD (iRBD). Methods: We reviewed the medical records of 123 consecutive patients (76 males; age, 66.0±7.7 years; and symptom duration, 4.1±4.0 years) with iRBD who were treated with clonazepam and/or melatonin. Clonazepam and melatonin were initially administered at 0.25–0.50 and 2 mg/day, respectively, at bedtime, and the doses were subsequently titrated according to the response of individual patients. Treatment response was defined according to the presence or absence of any improvement in dream-enacting behaviors or unpleasant dreams after treatment. Results: Forty (32.5%) patients were treated with clonazepam, 56 (45.5%) with melatonin, and 27 (22.0%) with combination therapy. The doses of clonazepam and melatonin at followup were 0.5±0.3 and 2.3±0.7 mg, respectively. Ninety-six (78.0%) patients reported improvement in their RBD symptoms during a mean follow-up period of 17.7 months. After adjusting for potential confounders, depression was significantly associated with a negative treatment response (odds ratio=3.76, 95% confidence interval=1.15–12.32, p=0.029). Conclusions We found that comorbid depression is significantly associated with a negative response to clonazepam and/or melatonin in patients with iRBD. Further research with larger numbers of patients is needed to verify our observations and to determine the clinical implications of comorbid depression in the pathophysiology of iRBD.

With increasing sensitivity, availability, and use of magnetic resonance imaging (MRI) in the past three decades, there is also an increase in incidental abnormal findings. The most common findings of these incidental abnormalities are white matter lesions that are interpreted as demyelinating based on radiological criteria. MRI findings suggestive of multiple sclerosis (MS) in patients without typical MS symptoms and with normal neurologic findings are now defined as a radiologically isolated syndrome (RIS) which reported relatively low incidence, especially hard to find case report in Korea. The natural history and pathophysiologic processes of RIS remain largely unknown. The nature, prevalence, and long-term prognosis of RIS, as well as the role of disease-modifying therapy should be established in the future.
Demyelinating Diseases ; Humans ; Incidence ; Korea ; Magnetic Resonance Imaging ; Multiple Sclerosis ; Natural History ; Neurologic Manifestations ; Prevalence ; Prognosis ; White Matter

No abstract available.
Magnetic Resonance Imaging ; Spine

No abstract available.
Asian Continental Ancestry Group ; Encephalitis, Japanese ; Humans ; Temporal Lobe

No abstract available.
Cluster Headache ; Frontal Sinus ; Frontal Sinusitis ; Headache ; Magnetic Resonance Imaging ; Sinusitis

Spontaneous intracranial hypotension (SIH) is characterized by orthostatic headache, diffuse dural thickening, and enhancement in magnetic resonance imaging. Cerebral venous thrombosis (CVT) has been reported to be a rare complication of SIH. There is no consensus in anticoagulation treatment of CVT secondarily caused by SIH. We report a female patient with SIH complicated by CVT and spontaneously regressed CVT not by anticoagulation but by epidural blood patch.
Blood Patch, Epidural ; Consensus ; Female ; Headache ; Humans ; Intracranial Hypotension ; Magnetic Resonance Imaging ; Venous Thrombosis

BACKGROUND AND OBJECTIVES: It is controversial that decreased left ventricular function could predict poststroke outcomes. The purpose of this study is to elucidate whether left ventricular ejection fraction (LVEF) can predict cardiovascular events and mortality in acute ischemic stroke (AIS) without atrial fibrillation (AF) and coronary heart disease (CHD). METHODS: Transthoracic echocardiography was conducted consecutively in patients with AIS or transient ischemic attack at Soonchunhyang University Hospital between January 2008 and July 2016. The clinical data and echocardiographic LVEF of 1,465 patients were reviewed after excluding AF and CHD. Poststroke disability, major adverse cardiac events (MACE; nonfatal stroke, nonfatal myocardial infarction, and cardiovascular death) and all-cause mortality during 1 year after index stroke were prospectively captured. Cox proportional hazards regressions analysis were applied adjusting traditional risk factors and potential determinants. RESULTS: The mean follow-up time was 259.9±148.8 days with a total of 29 non-fatal strokes, 3 myocardial infarctions, 33 cardiovascular deaths, and 53 all-cause mortality. The cumulative incidence of MACE and all-cause mortality were significantly higher in the lowest LVEF ( < 55) group compared with the others (p=0.022 and 0.009). In prediction models, LVEF (per 10%) had hazards ratios of 0.54 (95% confidence interval [CI], 0.36–0.80, p=0.002) for MACE and 0.61 (95% CI, 0.39–0.97, p=0.037) for all-cause mortality. CONCLUSIONS LVEF could be an independent predictor of cardiovascular events and mortality after AIS in the absence of AF and CHD.

BACKGROUND AND OBJECTIVES: It is controversial that decreased left ventricular function could predict poststroke outcomes. The purpose of this study is to elucidate whether left ventricular ejection fraction (LVEF) can predict cardiovascular events and mortality in acute ischemic stroke (AIS) without atrial fibrillation (AF) and coronary heart disease (CHD). METHODS: Transthoracic echocardiography was conducted consecutively in patients with AIS or transient ischemic attack at Soonchunhyang University Hospital between January 2008 and July 2016. The clinical data and echocardiographic LVEF of 1,465 patients were reviewed after excluding AF and CHD. Poststroke disability, major adverse cardiac events (MACE; nonfatal stroke, nonfatal myocardial infarction, and cardiovascular death) and all-cause mortality during 1 year after index stroke were prospectively captured. Cox proportional hazards regressions analysis were applied adjusting traditional risk factors and potential determinants. RESULTS: The mean follow-up time was 259.9±148.8 days with a total of 29 non-fatal strokes, 3 myocardial infarctions, 33 cardiovascular deaths, and 53 all-cause mortality. The cumulative incidence of MACE and all-cause mortality were significantly higher in the lowest LVEF ( < 55) group compared with the others (p=0.022 and 0.009). In prediction models, LVEF (per 10%) had hazards ratios of 0.54 (95% confidence interval [CI], 0.36–0.80, p=0.002) for MACE and 0.61 (95% CI, 0.39–0.97, p=0.037) for all-cause mortality. CONCLUSIONS: LVEF could be an independent predictor of cardiovascular events and mortality after AIS in the absence of AF and CHD.
Atrial Fibrillation ; Coronary Disease ; Echocardiography ; Follow-Up Studies ; Humans ; Incidence ; Ischemic Attack, Transient ; Mortality ; Myocardial Infarction ; Prospective Studies ; Risk Factors ; Stroke ; Stroke Volume ; Ventricular Function, Left

No abstract available.
Amnesia, Transient Global* ; Posterior Leukoencephalopathy Syndrome*