- Cutaneous Melanoma Detection and Management
- Muscle activation and electromyography studies
- Sports injuries and prevention
- Phonocardiography and Auscultation Techniques
- Music and Audio Processing
- Lower Extremity Biomechanics and Pathologies
- Sports Performance and Training
- AI in cancer detection
- Digital Imaging in Medicine
- Renal cell carcinoma treatment
- Advanced X-ray and CT Imaging
- Osteoarthritis Treatment and Mechanisms
- Ultrasonics and Acoustic Wave Propagation
- Face recognition and analysis
- Renal and related cancers
- Infrared Thermography in Medicine
- Bladder and Urothelial Cancer Treatments
- Knee injuries and reconstruction techniques
- Acne and Rosacea Treatments and Effects
- Nonmelanoma Skin Cancer Studies
- Railway Engineering and Dynamics
- Digital Media Forensic Detection
- Advanced Chemical Sensor Technologies
- Radiomics and Machine Learning in Medical Imaging
- Kidney Stones and Urolithiasis Treatments
Duke University
2022-2024
Seoul Metropolitan Government
2024
Seoul National University
2024
Boramae Medical Center
2024
Duke Medical Center
2022-2023
Duke University Hospital
2022-2023
Yonsei University
2023
Christ University
2023
Georgia Institute of Technology
2016-2021
University of Southampton
2016
Objective: We designed and validated a portable electrical bioimpedance (EBI) system to quantify knee joint health. Methods: Five separate experiments were performed demonstrate the: 1) ability of the EBI assess injury recovery; 2) interday variability measurements; 3) sensitivity small changes in interstitial fluid volume; 4) reducing error measurements using acceleration signals; 5) use with dry electrodes integrated wearable wrap. Results: The absolute difference resistance ( R) reactance...
Objective: We present a robust methodology for tracking ankle edema longitudinally based on bioimpedance spectroscopy (BIS). Methods: designed miniaturized BIS measurement system and employed novel calibration method that enables accurate, high-resolution measurements with substantially lower power consumption than conventional approaches. Using this state-of-the-art wearable system, we developed differential technique assessment of edema. This addresses many the major challenges in...
The image quality received for clinical evaluation is often suboptimal. goal to develop an analysis tool assess patient- and primary care physician–derived images using deep learning model. Dataset included from August 21, 2018 June 30, 2022 with 4 unique labels. VGG16 model was fine tuned input data, optimal threshold determined by Youden's index. Ordinal labels were transformed binary a majority vote because distinguishes between 2 categories (good vs bad). At of 0.587, area under the...
Knee-joint sounds could potentially be used to noninvasively probe the physical and/or physiological changes in knee associated with rehabilitation following acute injury. In this paper, a system and methods for investigating consistency of knee-joint during complex motions silent loud background settings are presented. The wearable hardware component consists microelectromechanical systems microphone inertial rate sensors interfaced field programmable gate array-based real-time processor...
In this paper, we investigate the effects of increasing mechanical stress on knee joints by recording acoustical emissions and analyze them using an unsupervised graph mining algorithm. We placed miniature contact microphones four different locations: lateral medial sides patella superficial to meniscus. extracted audio features in both time frequency domains from signals calculated community factor (GCF): index heterogeneity (variation) sounds due loading conditions enforced knee. To...
The identification of patients at risk progressing from intermediate age-related macular degeneration (iAMD) to geographic atrophy (GA) is essential for clinical trials aimed preventing disease progression. DeepGAze a fully automated and accurate convolutional neural network-based deep learning algorithm predicting progression iAMD GA within 1 year spectral-domain optical coherence tomography (SD-OCT) scans.
Sounds produced by the articulation of joints have been shown to contain information characteristic underlying joint health, morphology, and loading. In this work, we explore use a novel form factor for non-invasively acquiring acoustic/vibrational signals from knee joint: an instrumented glove with fingertip-mounted accelerometer. We validated glove-based approach comparing it conventional mounting techniques (tape foam microphone pads) in experimental framework previously reliably alter...
Tendons are essential components of the musculoskeletal system and, as with any mechanical structure, can fail under load. Tendon injuries common and be debilitating, research suggests that a better understanding their loading conditions could help mitigate injury risk improve rehabilitation. To end, we present novel method noninvasively assessing parameters related to load in Achilles tendon using burst vibrations.These vibrations, produced by small vibration motor on skin superficial...
This paper explores the novel application of an automated b-value extraction algorithm for interpretation sounds produced by knee joint during movement. Acoustical emissions were recorded from a total eight subjects with acute injuries first time, within one week injury, then second four to six months following corrective surgery and rehabilitation. The data collected each subject using miniature electret microphones placed on medial lateral side patella flexion extension exercises. From...
An algorithm for performing activity classification a joint health assessment system using acoustical emissions from the knee is presented. The was refined based on linear acceleration data shank and thigh sampled at 100 Hz/ch collected eight healthy subjects unloaded flexion-extension sit-to-stand motions. implemented field-programmable gate array (FPGA)-based processor has been validated in realtime subject two minutes of activities consisting flexion-extension, sit-to-stand, other motions...
Considering the knee as a fluid-lubricated system, articulating surfaces undergo different lubrication modes and generate joint acoustic emissions (JAEs). The goal of this study is to compare biomechanical signals against synchronously recorded sounds assess hypothesis that JAEs are attributed tribological origins.JAE, electromyography, ground reaction force signals, motion capture markers were from ten healthy subjects while performing two-leg one-leg squat exercises. processed calculate...
<i>Objective</i>: Osteoarthritis is the most common type of knee arthritis that can be affected by excessive and compressive loads affect one or more compartments knee: medial, lateral, patellofemoral. The medial compartment tends to vulnerable injuries research suggests a better understanding lateral load distribution conditions could provide insights quantitative usage in activities daily life. <i>Methods</i>: Prior study an osteoarthritic clinical population which may present with various...
Each year, millions of Americans endure knee injuries, ranging from simple sprains to ligament tears requiring surgical intervention. Our team is investigating wearable rehabilitation assessment technologies for patients recovering injuries based on the measurement and analysis acoustical emissions knees. Using miniature electret microphones combined with piezoelectric sensors placed surface skin at knee, we measure sounds joint as subjects perform basic flexion/extension exercises...
You have accessJournal of UrologyStone Disease: Surgical Therapy (Including ESWL) III (MP29)1 May 2024MP29-18 DEVELOPMENT OF AN AUTOMATED URINARY STONE DETECTION AND DIAGNOSIS SYSTEM USING ARTIFICIAL INTELLIGENCE Junghoon Lee, Sangjun Yoo, Min Chul Cho, Hyeon Jeong, Hwancheol Son, Minsoo Choo, and Dongjak-gu LeeJunghoon Lee , YooSangjun Yoo ChoMin Cho JeongHyeon Jeong SonHwancheol Son ChooMinsoo Choo View All Author Informationhttps://doi.org/10.1097/01.JU.0001008680.67760.37.18AboutPDF...
Unobtrusive monitoring of physio-behavioral variables from animals can minimize variability in preclinical research and thereby maximize the potential for clinical translation. In this paper, we present design, implementation, validation an instrumented nest providing continuous recordings seismocardiogram (SCG) signals skin temperature. SCG represents chest-wall vibrations associated with heartbeat, potentially provide a measure by which individual heartbeats be detected without need...
Musculoskeletal disorders and injuries are one of the most prevalent medical conditions across age groups. Due to a high load-bearing function, knee is particularly susceptible such as meniscus tears. Imaging techniques commonly used assess injuries, though this approach suffers from limitations including cost, need for skilled personnel, confinement laboratory or clinical settings. Vibration-based structural monitoring methods in form acoustic emission analysis vibration stimulation have...
Porous materials have recently been used in absorptive treatments around railway tracks to reduce noise emissions. To investigate the effect of porous materials, a finite element model has developed. 2D models for considered either as an equivalent fluid or poroelastic material based on Biot theory. The two validated and compared with each other check skeleton vibration. FE coupled acoustic boundary use applications. results show that it may be necessary include frame vibration, especially...
<sec> <title>BACKGROUND</title> The quality of the images received for Teledermatology evaluation is often suboptimal, with up to 50% patients providing that are poorly lit, off-center, or blurry. To ensure a similar level care in-person consultations, high-quality essential. </sec> <title>OBJECTIVE</title> aim this project develop an image analysis (IQA) tool assess patient and primary physicians derived using deep learning model, leveraging multiple instance ordinal regression model...
Background The quality of the images received for teledermatology evaluation is often suboptimal, with up to 50% patients providing that are poorly lit, off-center, or blurry. To ensure a similar level care in-person consultations, high-quality essential. Objective aim this study develop an image analysis tool assess patient- and primary physician (PCP)–derived using deep learning model leveraging multiple instance ordinal regression predictions. Methods data set used was acquired from...