A5102981929- Colorectal Cancer Screening and Detection
- Augmented Reality Applications
- Surgical Simulation and Training
- AI in cancer detection
- Dermatologic Treatments and Research
- Muscle activation and electromyography studies
- Sports injuries and prevention
- Soft Robotics and Applications
- Sports Performance and Training
- COVID-19 diagnosis using AI
- Facial Rejuvenation and Surgery Techniques
- Radiomics and Machine Learning in Medical Imaging
- Aerodynamics and Acoustics in Jet Flows
- Advanced Image and Video Retrieval Techniques
- Acute Ischemic Stroke Management
- Laser Applications in Dentistry and Medicine
- Infection Control and Ventilation
- Hair Growth and Disorders
- Virtual Reality Applications and Impacts
- Mental Health via Writing
- Anatomy and Medical Technology
- Artificial Intelligence in Healthcare and Education
- Dementia and Cognitive Impairment Research
- Diagnosis and Treatment of Venous Diseases
- Gastric Cancer Management and Outcomes
Seoul National University Hospital
2022-2024
Seoul National University
2015-2024
New Generation University College
2023
National University College
2023
Korea Advanced Institute of Science and Technology
2023
Smart hospitals involve the application of recent information and communications technology (ICT) innovations to medical services; however, concept a smart hospital has not been rigorously defined. In this study, we aimed derive definition service types investigate cases each type.
Abstract Computer-aided detection (CADe) systems have been actively researched for polyp in colonoscopy. To be an effective system, it is important to detect additional polyps that may easily missed by endoscopists. Sessile serrated lesions (SSLs) are a precursor colorectal cancer with relatively higher miss rate, owing their flat and subtle morphology. Colonoscopy CADe could help endoscopists; however, the current exhibit very low performance detecting SSLs. We propose system reflects...
Abstract Recognizing anatomical sections during colonoscopy is crucial for diagnosing colonic diseases and generating accurate reports. While recent studies have endeavored to identify regions of the colon using deep learning, deformable characteristics pose challenges establishing a reliable localization system. This study presents system utilizing 100 videos, combining density clustering learning. Cascaded CNN models are employed estimate appendix orifice (AO), flexures, "outside body,"...
Background Accurate interpretation of chest radiographs requires years medical training, and many countries face a shortage professionals to meet such requirements. Recent advancements in artificial intelligence (AI) have aided diagnoses; however, their performance is often limited due data imbalance. The aim this study was augment imbalanced using generative adversarial networks (GANs) evaluate the clinical quality generated images via multi-center visual Turing test. Methods Using six...
Robot-assisted surgery platforms are utilized globally thanks to their stereoscopic vision systems and enhanced functional assistance. However, the necessity of ergonomic improvement for use by surgeons has been increased. In surgical robots, issues with chronic fatigue exist owing fixed posture conventional stereo viewer (SV) system. A head-mounted display was adopted alleviate inconvenience, a virtual platform (VVP) is proposed in this study. The VVP can provide various critical data,...
Abstract This study developed a new convolutional neural network model to detect and classify gastric lesions as malignant, premalignant, benign. We used 10,181 white-light endoscopy images from 2606 patients in an 8:1:1 ratio. Lesions were categorized early cancer (EGC), advanced (AGC), dysplasia, benign ulcer (BGU), polyp, erosion. assessed the lesion detection classification using six-class, versus non-cancer, neoplasm non-neoplasm categories, well T-stage estimation (T1, T2-T4). The rate...
Endotracheal intubation (ETI) is critical to secure the airway in emergent situations. Although artificial intelligence algorithms are frequently used analyze medical images, their application evaluating intraoral structures based on images captured during ETI remains limited. The aim of this study develop an model for segmenting oral cavity using video laryngoscope (VL) images.From 54 VL videos, clinicians manually labeled that include motion blur, foggy vision, blood, mucus, and vomitus....
Background: Alzheimer’s disease (AD) is the most common form of dementia, which makes lives patients and their families difficult for various reasons. Therefore, early detection AD crucial to alleviating symptoms through medication treatment. Objective: Given that strongly induces language disorders, this study aims detect rapidly by analyzing characteristics. Materials Methods: The mini-mental state examination dementia screening (MMSE-DS), commonly used in South Korean public health...
In the context of stroke rehabilitation, simple structures and user-intent driven actuation are relevant features to facilitate neuroplasticity as well deliver a sufficient number repetitions during single therapy session. A novel robotic treatment device for distal upper limb rehabilitation in patients was developed, usability test performed assess its clinical feasibility. The robot designed two-axis exoskeleton actuated by electric motors, consisting forearm supination/pronation hand...
Abstract Robotic surgery is preferred over open or laparoscopic surgeries due to its intuitiveness and convenience. However, prolonged use of surgical robots can cause neck pain joint fatigue in wrist fingers. Also, input systems are bulky difficult maintain. To resolve these issues, we propose a novel module based on real-time 3D hand tracking driven by RGB images MediaPipe framework control such as patient side manipulator (PSM) endoscopic camera (ECM) da Vinci research kit. In this paper,...
Timely diagnosis and prognostication of Alzheimer's disease (AD) mild cognitive impairment (MCI) are pivotal for effective intervention. Artificial intelligence (AI) in neuroradiology may aid such appropriate prognostication. This study aimed to evaluate the potential novel diffusion model-based AI enhancing AD MCI through superresolution (SR) brain magnetic resonance (MR) images. 1.5T MR scans patients with or healthy controls (NC) from Disease Neuroimaging Initiative 1 (ADNI1) were...
Muscle strength assessments are vital in rehabilitation, orthopedics, and sports medicine. However, current methods used clinical settings, such as manual muscle testing hand-held dynamometers, often lack reliability, isokinetic dynamometers (IKD), while reliable, not easily portable. The aim of this study was to design validate a wearable dynamometry system with high accessibility, accuracy, the device. Therefore, we designed (WDS) equipped knee joint torque sensors. To WDS, measured...
This study aimed to evaluate the number of laser irradiation sessions, process duration, and hair removal rate required for robot-assisted automatic versus physician-directed removal.This research group previously developed tested an (LHR) system provide uniform treatment distribution.Six subjects 20-40 years age, with skin types III-IV completed this study. A home-use LHR device 810 nm diode was used treat equal-sized areas both upper thighs; a random computer generator determined use or on...
Cecal intubation time is an important component for quality colonoscopy. Cecum the turning point that determines insertion and withdrawal phase of colonoscope. For this reason, obtaining information related with location cecum in endoscopic procedure very useful. Also, it necessary to detect direction colonoscope's movement time-location cecum.In order analysis scope's movement, Horn-Schunck algorithm was used compute pixel's motion change between consecutive frames. Horn-Schunk-algorithm...
Objective: This study aims to improve the performance of an automatic laser hair removal (LHR) system by applying algorithm that considers curve and slant skin surface. Background data: In earlier research, a robot-assisted LHR has been developed validated for almost flat or relatively smooth curved part skin. For practical clinical applications, feature is extended real skins. Methods: A novel pose-measurement applied system. detects six-degree freedom (DOF) pose surface using algorithm....
We aimed to develop and validate a novel computer-assisted automated hair counting system for the quantitative evaluation of laser removal (LHR).We developed computer-aided image processing count hairs on shaved skin validated its performance through clinical trials. Five volunteers Fitzpatrick type III-IV volunteered were tested both thighs. The automatically detects places "+" sign each site every positive detection. This method allows clinicians check whether has been counted or not....
Background and objective: Many laser devices have been developed over the past decades for various skin conditions. However, variations in technical skill of physicians treatment delivery not yet evaluated. This study evaluates differences omission overlap percentages during simulated hair removal treatments among at two clinics. Materials methods: A beam detection kit was to record collect irradiation from a diode device. Eight (primary private clinic 4, tertiary referral hospital 4) were...
Abstract Monitoring ankle strength is crucial for assessing daily activities, functional ability, and preventing lower extremity injuries. However, the current methods measuring are often unreliable or not easily portable to be used in clinical settings. Therefore, this study proposes a dynamometer with high reliability capable of dorsiflexion plantar flexion. The proposed comprised plates made aluminum alloy 6061 miniature tension–compression load cell. A total 41 healthy adult participants...
Abstract With the advent of robot-assisted surgery, user-friendly technologies have been applied to da Vinci surgical system (dVSS), and their efficacy has validated in worldwide fields. However, further improvements are required traditional manipulation methods, which cannot control an endoscope instruments simultaneously. This study proposes a speech recognition interface (SRCI) for controlling via commands while manipulating replace method. The usability-focused comparisons newly proposed...