A5047691691- Dementia and Cognitive Impairment Research
- Forensic Anthropology and Bioarchaeology Studies
- Brain Tumor Detection and Classification
- Autopsy Techniques and Outcomes
- Functional Brain Connectivity Studies
- Human Pose and Action Recognition
- Acute Ischemic Stroke Management
- Cardiac tumors and thrombi
- Cerebral Venous Sinus Thrombosis
- Alzheimer's disease research and treatments
- Vascular Malformations Diagnosis and Treatment
- Educational Systems and Policies
- Meningioma and schwannoma management
- Lung Cancer Diagnosis and Treatment
- Radiomics and Machine Learning in Medical Imaging
- Musculoskeletal synovial abnormalities and treatments
- Acute Myeloid Leukemia Research
- Medical Image Segmentation Techniques
- Elbow and Forearm Trauma Treatment
- Pituitary Gland Disorders and Treatments
- Neurological Disease Mechanisms and Treatments
- Shoulder Injury and Treatment
- Ophthalmology and Eye Disorders
- Dermatoglyphics and Human Traits
- Advanced MRI Techniques and Applications
University of Ulsan
2021
Asan Medical Center
2021
Ulsan College
2021
St. Vincent's Hospital
2015-2018
Catholic University of Korea
2015
Background Previous studies assessing the effects of computer-aided detection on observer performance in reading chest radiographs used a sequential design that may have biased results because order or recall bias. Purpose To compare detecting and localizing major abnormal findings including nodules, consolidation, interstitial opacity, pleural effusion, pneumothorax without versus with deep learning–based (DLD) system assistance randomized crossover design. Materials Methods This study...
<h3>BACKGROUND AND PURPOSE:</h3> Limited evidence has suggested that a deep learning automatic brain segmentation and classification method, based on T1-weighted MR images, can predict Alzheimer disease. Our aim was to develop validate learning–based algorithm for the diagnosis of disease using 3D images. <h3>MATERIALS METHODS:</h3> A developed dataset images in consecutive patients with mild cognitive impairment. We 2-step convolutional neural network perform parcellation followed by 3...
To develop a deep-learning-based bone age prediction model optimized for Korean children and adolescents evaluate its feasibility by comparing it with Greulich-Pyle-based deep-learning model.A convolutional neural network was trained to predict according the development shown on hand radiograph (bone age) using 21036 radiographs of without known development-affecting diseases/conditions obtained between 1998 2019 (median [interquartile range {IQR}], 9 [7-12] years; male:female, 11794:9242)...
This study aims to analyze Korean connective endings for beginners that make up non-separable conjoined sentences, identify the reason and cause, suggest an effective teaching strategy based on results. When explaining sentences connected with language learners whose mother languages are typologically different from Korean, it can be explain by separating sentences. To achieve this goal, attempt was made separate beginner following criteria. First, when a sentence ending as center, must...
Purpose To validate the diagnostic performance of commercially available, deep learning-based automatic white matter hyperintensity (WMH) segmentation algorithm for classifying grades Fazekas scale and differentiating subcortical vascular dementia. Methods This retrospective, observational, single-institution study investigated a WMH volume to classify differentiate The VUNO Med-DeepBrain was used system. system designed with convolutional neural networks, in which input image comprised...
To evaluate the applicability of Greulich-Pyle (GP) standards to bone age (BA) assessment in healthy Korean children using manual and deep learning-based methods.We collected 485 hand radiographs aged 2-17 years (262 boys) between 2008 2017. Based on GP method, BA was assessed manually by two radiologists automatically (DLBAA), which estimated GP-assigned (original model) optimal (modified BAs. Estimated compared chronological (CA) intraclass correlation (ICC), Bland-Altman analysis, linear...
To describe the clinical and magnetic resonance imaging findings of ganglion cysts with effusion in flexor hallucis longus tendon sheath around hallux to evaluate their origin.Patients recurrent or painful who underwent surgical treatment at St. Vincent's Hospital from February 2007 August 2016 were investigated. Surgical indication was a mass caused by cystic lesions. Those without excluded. We assessed findings.Magnetic all patients showed several large fluid accumulations within sheath....
Objective: To evaluate the image characteristics of subtraction magnetic resonance venography (SMRV) from time-resolved contrast-enhanced MR angiography (TRMRA) compared with phase-contrast (PCMRV) and single-phase (CEMRV).Materials Methods: Twenty-one patients who underwent brain (MRV) using standard protocols (PCMRV, CEMRV, TRMRA) were included.SMRV was made by subtracting arterial phase data venous in TRMRA.Co-registration two volume done commercially available software.Image quality...
Objective A deep learning-based classification system (DLCS) which uses structural brain magnetic resonance imaging (MRI) to diagnose Alzheimer’s disease (AD) was developed in a previous recent study. Here, we evaluate its performance by conducting single-center, case-control clinical trial.Methods We retrospectively collected T1-weighted MRI scans of subjects who had an accompanying measure amyloid-beta (Aβ) positivity based on 18F-florbetaben positron emission tomography scan. The dataset...
Abstract Objective To investigate diagnostic performance of a deep learning-based classification system using structural brain MRI (DLCS) for Alzheimer’s disease (AD). Methods A single-center, case-control clinical trial was conducted. T1-weighted scans 188 patients with mild cognitive impairment or dementia due to AD and 162 cognitively normal controls were retrospectively collected. The amyloid beta (Aβ)-positive, whereas the Aβ-negative, on 18F-florbetaben positron emission tomography....