Publications by authors named "Dan Yoon"

Unlabelled: With the advent of robot-assisted surgery, user-friendly technologies have been applied to the da Vinci surgical system (dVSS), and their efficacy has been validated in worldwide surgical fields. However, further improvements are required to the traditional manipulation methods, which cannot control an endoscope and surgical instruments simultaneously. This study proposes a speech recognition control interface (SRCI) for controlling the endoscope via speech commands while manipulating surgical instruments to replace the traditional method.

View Article and Find Full Text PDF

Background: Leber congenital amaurosis 1 (LCA1), caused by mutations in GUCY2D, is a rare inherited retinal disease that typically causes blindness in early childhood. The aim of this study was to evaluate the safety and preliminary efficacy of ascending doses of ATSN-101, a subretinal AAV5 gene therapy for LCA1.

Methods: 15 patients with genetically confirmed biallelic mutations in GUCY2D were included in this phase 1/2 study.

View Article and Find Full Text PDF
Article Synopsis
  • A study was conducted to explore how user experience and characteristics of polyps affect interactions with computer-aided detection (CADe) systems during colonoscopy.
  • The CADe system, built using YOLOv4 and trained on nearly 18,000 images, showed an improvement in polyp detection accuracy from 69.7% to 77.7% when assisted by CADe, although misdetections could decrease accuracy.
  • The results indicated that less experienced users (like nurses) benefited more from CADe assistance compared to experts, and while overall sensitivity improved for easier polyp detection, it was lower for more challenging lesions like sessile serrated lesions (SSLs).
View Article and Find Full Text PDF

Introduction: Timely diagnosis and prognostication of Alzheimer's disease (AD) and mild cognitive impairment (MCI) are pivotal for effective intervention. Artificial intelligence (AI) in neuroradiology may aid in such appropriate diagnosis and prognostication. This study aimed to evaluate the potential of novel diffusion model-based AI for enhancing AD and MCI diagnosis through superresolution (SR) of brain magnetic resonance (MR) images.

View Article and Find Full Text PDF
Article Synopsis
  • Patient isolation units (PIUs) are effective for infection control, but optimizing their design typically requires extensive computational resources, which this study aims to address using data-driven models.
  • The study used computational fluid dynamics (CFD) to examine how various PIU settings and room conditions impact ventilation and isolation, focusing on airflow patterns and particle dispersion from coughing.
  • Key findings indicate that while physical isolation alone isn't enough to stop particle spread, the addition of a fan filter unit (FFU) significantly improves isolation performance, with its positioning being the most crucial factor influencing PIU effectiveness.
View Article and Find Full Text PDF

Purpose: The NIGHT study aimed to assess the natural history of choroideremia (CHM), an X-linked inherited chorioretinal degenerative disease leading to blindness, and determine which outcomes would be the most sensitive for monitoring disease progression.

Design: A prospective, observational, multicenter cohort study.

Methods: Males aged ≥18 years with genetically confirmed CHM, visible active disease within the macular region, and best-corrected visual acuity (BCVA) ≥34 Early Treatment Diabetic Retinopathy Study (ETDRS) letters at baseline were assessed for 20 months.

View Article and Find Full Text PDF

Robot-assisted surgery platforms are utilized globally thanks to their stereoscopic vision systems and enhanced functional assistance. However, the necessity of ergonomic improvement for their use by surgeons has been increased. In surgical robots, issues with chronic fatigue exist owing to the fixed posture of the conventional stereo viewer (SV) vision system.

View Article and Find Full Text PDF

The intraoperative estimated blood loss (EBL), an essential parameter for perioperative management, has been evaluated by manually weighing blood in gauze and suction bottles, a process both time-consuming and labor-intensive. As the novel EBL prediction platform, we developed an automated deep learning EBL prediction model, utilizing the patch-wise crumpled state (P-W CS) of gauze images with texture analysis. The proposed algorithm was developed using animal data obtained from a porcine experiment and validated on human intraoperative data prospectively collected from 102 laparoscopic gastric cancer surgeries.

View Article and Find Full Text PDF

Recognizing anatomical sections during colonoscopy is crucial for diagnosing colonic diseases and generating accurate reports. While recent studies have endeavored to identify anatomical regions of the colon using deep learning, the deformable anatomical characteristics of the colon pose challenges for establishing a reliable localization system. This study presents a system utilizing 100 colonoscopy videos, combining density clustering and deep learning.

View Article and Find Full Text PDF
Article Synopsis
  • Airway procedures are critical for saving lives, and video laryngoscopy (VL) is essential for endotracheal intubation (ETI) in emergencies.
  • This study developed an AI algorithm using the YOLOv4 model to detect vocal cords from VL images, analyzing a dataset of 20,161 images from 84 patients.
  • The algorithm showed strong performance with an F1 score of 0.906 during validation and 0.808 in the test set, indicating it could help ensure safe ETI.
View Article and Find Full Text PDF

Choroideremia is a rare, X-linked retinal degeneration resulting in progressive vision loss. A randomized, masked, phase 3 clinical trial evaluated the safety and efficacy over 12 months of follow-up in adult males with choroideremia randomized to receive a high-dose (1.0 × 10 vector genomes (vg); n = 69) or low-dose (1.

View Article and Find Full Text PDF

Objective: To develop an alert/verbal/painful/unresponsive (AVPU) scale assessment system based on automated video and speech recognition technology (AVPU-AVSR) that can automatically assess a patient's level of consciousness and evaluate its performance through clinical simulation.

Methods: We developed an AVPU-AVSR system with a whole-body camera, face camera, and microphone. The AVPU-AVSR system automatically extracted essential audiovisual features to assess the AVPU score from the recorded video files.

View Article and Find Full Text PDF

Background: Accurate interpretation of chest radiographs requires years of medical training, and many countries face a shortage of medical professionals to meet such requirements. Recent advancements in artificial intelligence (AI) have aided diagnoses; however, their performance is often limited due to data imbalance. The aim of this study was to augment imbalanced medical data using generative adversarial networks (GANs) and evaluate the clinical quality of the generated images via a multi-center visual Turing test.

View Article and Find Full Text PDF

Signaling of vision to the brain starts with the retinal phototransduction cascade which converts visible light from the environment into chemical changes. Vision impairment results when mutations inactivate proteins of the phototransduction cascade. A severe monogenically inherited blindness, Leber congenital amaurosis (LCA), is caused by mutations in the gene, leading to a molecular defect in the production of cyclic GMP, the second messenger of phototransduction We studied two patients with -LCA who were undergoing gene augmentation therapy.

View Article and Find Full Text PDF
Article Synopsis
  • Computer-aided detection (CADe) systems aim to improve the detection of polyps in colonoscopy, especially sessile serrated lesions (SSLs), which are often missed due to their flat appearance.
  • Current CADe systems struggle to detect SSLs effectively, prompting researchers to propose a new approach that leverages the morphological characteristics of SSLs.
  • They utilized a generative adversarial network (GAN) to create realistic, high-resolution endoscopic images for training the CADe system, resulting in a 17.5% increase in sensitivity for detecting these challenging polyps.
View Article and Find Full Text PDF

Inherited retinal diseases (IRDs) are a diverse group of degenerative diseases of the retina that can lead to significant reduction in vision and blindness. Because of the considerable phenotypic overlap among IRDs, genetic testing is a critical step in obtaining a definitive diagnosis for affected individuals and enabling access to emerging gene therapy-based treatments and ongoing clinical studies. While advances in molecular diagnostic technologies have significantly improved the understanding of IRDs and identification of disease-causing variants, training in genetic diagnostics among ophthalmologists is limited.

View Article and Find Full Text PDF

This study aimed to determine the ventilation conditions required for suitable indoor air quality management during cooking in a typical South Korean residential home. We measured the concentrations of particulate matter (PM) and fine particulate matter (PM) under different ventilation conditions during the cooking of different food materials in the kitchen of a multi-family house, which is the representative residential space in South Korea. Pork belly and mackerel, which are the staple meat and fish products of Korean people, were prepared (200 g of each) and cooked via roasting.

View Article and Find Full Text PDF

Precis: A meta-analysis shows that second glaucoma drainage implantation can be effective after a failed drainage implant. There is a need for continued glaucoma medications and the risk of corneal decompensation.

Purpose: Studies on second glaucoma drainage implantation are small and exploratory.

View Article and Find Full Text PDF

The aim of this study was to support management of airborne bacteria in facilities used by pollution-sensitive individuals (in daycares, medical facilities, elder care facilities, and postnatal care centers). A field survey was conducted on 11 facilities from October 2017 to April 2018. Elder care facilities in industrial, urban, and forested areas were excluded.

View Article and Find Full Text PDF

Currently, low-cost, sensor-based fine dust measurement devices are commercially available in South Korea. This study evaluated the reliability of three such devices-Yi Shan A4, Plantower PMS7003, and Plantower PMS7003-in comparison to long-term consecutive monitoring systems for discharge and prevention facilities regarding fine dust control. The performance of these devices for concentration intervals over time was examined through real-time comparison using a GRIMM (Model: 11-A, dust spectrometer from Grimm Technologies) as a reference; this included a correction factor (C-Factor), calculated by a gravimetric method and an equivalence test.

View Article and Find Full Text PDF

Purpose: we report a case of late spontaneous large detachment of Descemet's membrane in recurrent pellucid marginal degeneration after penetrating keratoplasty.

Observations: a 73-year-old man presented to clinic with spontaneous detachment of his Descemet's membrane 30 years after penetrating keratoplasty for pellucid marginal degeneration. Efforts were made to bubble the membrane back into place without success.

View Article and Find Full Text PDF

The purpose of this study is to provide basic data for the evaluation and management of health effects with respect to exposure to radon within residential environments in South Korea. It is part of a case-control study to develop a management plan based on indoor radon exposure levels and assess their impact on health. To investigate the long-term cumulative concentration levels of radon, 599 patients who have respiratory diseases were recruited in South Korea, and alpha track detectors were installed in their residences for a period of 3 months from mid-2015 to late 2016.

View Article and Find Full Text PDF

Purpose: To assess for change in intraocular pressure (IOP) in neovascular age-related macular degeneration patients switched to aflibercept after receiving previous treatments of intravitreal bevacizumab or ranibizumab.

Methods: This is a retrospective chart review of the first 53 patients (53 eyes) treated with at least 2 injections of 2 mg in 0.05 mL of aflibercept by March 6, 2013, after at least 2 previous injections of 0.

View Article and Find Full Text PDF

Purpose: The purpose of this study was to examine the inherent precision and accuracy of TearLab Osmolarity System using salt solutions, including solutions of very high osmolarity (>360 mOsm/L).

Materials And Methods: Ten salt solutions with osmolarity between 286 mOsm/L and 394 mOsm/L (increments of 12 mOsm/L) plus an additional solution of 400 mOsm/L were tested twice on both the TearLab osmometer and a freezing point depression osmometer. For precision, we compared the two repeated osmolarity measurements of 11 solutions obtained from TearLab.

View Article and Find Full Text PDF

This study investigated whether the presence of vitreomacular interface abnormalities (VMIAs) affects the improvement in visual acuity and edema of patients with diabetic macular edema (DME) who received three anti-vascular endothelial growth factor (VEGF) injections. Fifteen eyes of 11 patients with clinically significant macular edema were retrospectively divided into either the control group (only DME) or the experimental group (DME and VMIA) based on optical coherence tomography images. We defined VMIA patterns as epiretinal membrane and/or anomalous vitreomacular adhesion.

View Article and Find Full Text PDF