A5032202086- Medical Imaging and Analysis
- Body Composition Measurement Techniques
- IoT and Edge/Fog Computing
- Smart Cities and Technologies
- Human Mobility and Location-Based Analysis
- Nutrition and Health in Aging
- COVID-19 diagnosis using AI
- Phonocardiography and Auscultation Techniques
- Radiation Dose and Imaging
- Data Visualization and Analytics
- Glioma Diagnosis and Treatment
- AI in cancer detection
- Hepatocellular Carcinoma Treatment and Prognosis
- Infrared Thermography in Medicine
- Ultrasound in Clinical Applications
- Software-Defined Networks and 5G
- Interconnection Networks and Systems
- Advanced X-ray and CT Imaging
- Brain Tumor Detection and Classification
- Tuberculosis Research and Epidemiology
- Caching and Content Delivery
- Radiomics and Machine Learning in Medical Imaging
- Cloud Computing and Resource Management
- Advanced Optical Network Technologies
- Meningioma and schwannoma management
Seoul Medical Center
2022
Syneos Health (South Korea)
2020
Dongseo University
2018-2019
Background & aimsBody composition analysis on CT images is a valuable tool for sarcopenia assessment. We aimed to develop and validate deep neural network applicable whole-body of PET-CT scan the automatic volumetric segmentation body composition.MethodsFor model development, one hundred or torso 18F-fluorodeoxyglucose PET–CT scans 100 patients were retrospectively included. Two radiologists semi-automatically labeled following seven components in every image slice, providing total 46,967...
Background Accurate and rapid measurement of the MRI volume meningiomas is essential in clinical practice to determine growth rate tumor. Imperfect automation disappointing performance for small previous automated volumetric tools limit their use routine practice. Purpose To develop validate a computational model fully meningioma segmentation on contrast‐enhanced scans using deep learning. Study Type Retrospective. Population A total 659 intracranial patients (median age, 59.0 years;...
Background Total lung capacity (TLC) has been estimated with use of chest radiographs based on time-consuming methods, such as planimetric techniques and manual measurements. Purpose To develop a deep learning–based, multidimensional model capable estimating TLC from demographic variables validate its technical performance clinical utility multicenter retrospective data sets. Materials Methods A learning was pretrained 50 000 consecutive CT scans performed between January 2015 June 2017. The...
This study aimed (I) to investigate the clinical implication of computed tomography (CT) cavity volume in tuberculosis (TB) and non-tuberculous mycobacterial pulmonary disease (NTM-PD), (II) develop a three-dimensional (3D) nnU-Net model automatically detect quantify on CT images.We retrospectively included conveniently sampled 206 TB 186 NTM-PD patients tertiary referral hospital, who underwent thin-section chest scans from 2012 through 2019. was microbiologically confirmed, diagnosed by...
Software-Defined Networking (SDN) simplifies hardware-centric network architecture by employing forwarding devices (switches), SDN controller, and applications. Depending on the application that manages controller can turn a switch to act as switch, router, firewall, etc. also enables access more information through controller. Our proposed consists of traffic monitoring module routing optimize network. Traffic will monitor switches' port utilization uses deep reinforcement learning agent...
Abstract Most intracranial meningiomas are small, asymptomatic, and incidentally found tumors. Since the growth of meningioma is principal indication treatment, accurate rapid measurement volume essential in clinical practice to determine rate tumor. It could be useful for management given their increasing incidence wait-and-see policy currently use asymptomatic meningiomas. The aim this study was develop validate a computational model fully automated segmentation on contrast-enhanced MR...
Abstract Body composition analysis on CT images is a valuable tool for sarcopenia assessment. We aimed to develop and validate deep neural network applicable whole-body of PET-CT scan the automatic volumetric segmentation body composition. Methods For model development, 100 patients who underwent or torso 18 F-fluorodeoxyglucose PET–CT were retrospectively included. Two radiologists semi-automatically labeled following seven components in every image slice, providing 39,268 training 3D...