A5101904806- Parkinson's Disease Mechanisms and Treatments
- Image Enhancement Techniques
- Advanced Vision and Imaging
- Dementia and Cognitive Impairment Research
- Advanced Image Processing Techniques
- Neurological Disease Mechanisms and Treatments
- Alzheimer's disease research and treatments
- Neurological disorders and treatments
- Ginkgo biloba and Cashew Applications
- Neuroinflammation and Neurodegeneration Mechanisms
- Advanced Image Fusion Techniques
- Oral health in cancer treatment
- Nutritional Studies and Diet
- Health, Environment, Cognitive Aging
- Breast Lesions and Carcinomas
- Anomaly Detection Techniques and Applications
- Functional Brain Connectivity Studies
- Crime Patterns and Interventions
- Cancer and Skin Lesions
- Cancer Diagnosis and Treatment
- Vascular Malformations and Hemangiomas
- Radiomics and Machine Learning in Medical Imaging
- Medical Imaging Techniques and Applications
- Cybercrime and Law Enforcement Studies
- Male Breast Health Studies
Korea Institute of Brain Science
2024
Korea Advanced Institute of Science and Technology
2021-2024
Yeungnam University
2018-2024
Yeungnam University College
2023-2024
Korea Institute of Science & Technology Information
2023
Simon Fraser University
2018-2022
Kookmin University
2020
Fraser Institute
2018
This paper investigates machine-learning-based crime prediction. In this work, Vancouver data for the last 15 years is analyzed using two different data-processing approaches. Machine-Learning predictive models, K-nearest-neighbour and boosted decision tree, are implemented a prediction accuracy between 39% to 44% obtained when predicting in Vancouver.
Abstract Background Considering the limited accessibility of amyloid position emission tomography (PET) in patients with dementia, we proposed a deep learning (DL)-based PET positivity classification model from images 2-deoxy-2-[fluorine-18]fluoro-D-glucose (2-[ 18 F]FDG). Methods We used 2-[ F]FDG datasets Alzheimer's Disease Neuroimaging Initiative and Korean Brain Aging Study for Early diagnosis prediction Alzheimer’s disease development. Moreover, an independent dataset another hospital....
Patients with Parkinson's disease (PD) exhibit widespread brain perfusion changes.This study investigated whether cerebral regions hypoperfusion and hyperperfusion have differential effects on motor cognitive symptoms in PD using early-phase 18 F-N-(3-fluoropropyl)-2β-carboxymethoxy-3β-(4-iodophenyl) nortropane (18 F-FP-CIT) positron emission tomography (PET) scans.We enrolled 394 patients newly diagnosed who underwent dual-phase F-FP-CIT PET scans. Indices reflecting associated changes...
Reflections often degrade the quality of images by obstructing background scenes. This is not desirable for everyday users, and it negatively impacts performance multimedia applications that process with reflections. Most current methods removing reflections utilize supervised learning models. These models require an extensive number image pairs same scenes without to perform well. However, collecting such challenging costly. Thus, most are trained on small datasets cannot cover numerous...
"Reserve" refers to the individual clinical differences in response a neuropathological burden. We explored behavioral reserve (BR) and associated neural substrates 40 participants with variant frontotemporal dementia (bvFTD) who were assessed frontal inventory (FBI) magnetic resonance imaging. Because neuroimaging abnormality showed high negative correlation FBI (but not positive) symptom scores, we developed linear model only calculate nBR (BR for symptoms) marker using abnormalities...
Osteoradionecrosis of the chest wall after radiation therapy for breast cancer is rare; however, it one most severe complications treatment. Radiologically, osteoradionecrosis can manifest as a focal lucent area in bone, periostitis, sclerosis, and cortical irregularity bones on X-ray or computed tomography; therefore, differentiation from bone metastasis be challenging. Associated insufficiency fractures, ulceration, skin necrosis may also occur. We encountered patient with left anterior...
To investigate whether the cingulate island sign (CIS) ratio (i.e., of regional uptake in posterior cortex relative to precuneus and cuneus on cerebral perfusion scans) is associated with early dementia conversion Parkinson's disease (PD).We enrolled 226 patients newly diagnosed PD 48 healthy controls who underwent dual-phase 18 F-FP-CIT PET scans. Patients were classified into three groups according CIS early-phase images: a group or high ratios (PD-CIS; n = 96), inverse low (PD-iCIS; 40),...
Reflections often degrade the quality of image by obstructing background scene. This is not desirable for everyday users, and it negatively impacts performance multimedia applications that process images with reflections. Most current methods removing reflections utilize supervised-learning models. However, these models require an extensive number pairs to perform well, especially on natural reflection, which difficult achieve in practice. In this paper, we propose a novel unsupervised...
We investigated whether hippocampal perfusion changes are associated with cognitive decline, motor deficits, and the risk of dementia conversion in patients Parkinson disease (PD).
Although early detection of individuals at risk dementia conversion is important in patients with Parkinson's disease (PD), there still no consensus on neuroimaging biomarkers for predicting future cognitive decline. We aimed to investigate whether cerebral perfusion patterns early-phase 18 F-N-(3-fluoropropyl)-2β-carboxymethoxy-3β-(4-iodophenyl) nortropane ( F-FP-CIT) PET have the potential serve as a predictor PD.
Individual variability exists in parkinsonian motor symptoms despite a similar degree of nigrostriatal dopamine depletion Parkinson's disease (PD), called reserve. We enrolled 397 patients newly diagnosed with PD who underwent dual-phase 18F-FP-CIT PET upon initial assessment. reserve was estimated based on and striatal transporter availability using residual model. Patients low (the lowest quartile group, n = 100) exhibited decreased uptake the occipital region compared to those high...
Reflections in videos are obstructions that often occur when taken behind reflective surfaces like glass. These reflections reduce the quality of such videos, lead to information loss and degrade accuracy many computer vision algorithms. A video containing is a combination background reflection layers. Thus, removal equivalent decomposing into two This, however, challenging ill-posed problem as there an infinite number valid decompositions. To address this problem, we propose user-assisted...
PURPOSE: To compare the accuracy of classifying prediabetes, include type 2 diabetes, predicted by hand-grip strength employing machine learning (ML) techniques in Korean obese adults. METHODS: The data 1230 adults (51.5% males, 19-65yrs) was retrieved from National Health and Nutrition Examination Survey (KNHANES) 2014-2015. Obesity identified standard BMI (BMI ≥ 25kg/m2) waist circumference (WC; Male: WC 90cm, Female: 85cm). A total 591 individuals with prediabetes diabetes diagnosed...
Reflections in videos are obstructions that often occur when taken behind reflective surfaces like glass. These reflections reduce the quality of such videos, lead to information loss and degrade accuracy many computer vision algorithms. A video containing is a combination background reflection layers. Thus, removal equivalent decomposing into two This, however, challenging ill-posed problem as there an infinite number valid decompositions. To address this problem, we propose user-assisted...