Seoul National University · 医学
Professor Jong Hyuk Lee's research lab specializes in medical imaging and artificial intelligence, with a focus on lung disease detection, particularly in the context of COVID-19 sequelae and lung cancer. The lab investigates the integration of deep learning algorithms in chest radiography to improve diagnostic accuracy and explores how radiologists interact with AI-assisted reading. Additionally, the lab examines long-term outcomes of pulmonary nodules and the radiologic-pathologic correlations in interstitial lung diseases.
Figures are computed from collected data and may differ slightly.
A substantial number of COVID-19 survivors displayed pulmonary sequelae as part of PACS. Except for restrictive pulmonary dysfunction, the prevalence of these sequelae did not decrease until 1 year after initial infection. Considering the association between the severity of acute COVID-19 and risk of pulmonary sequelae, patients who recover from severe COVID-19 require close respiratory follow-up. Systematic review registration number PROSPERO CRD42021234357.
Background The performance of a deep learning algorithm for lung cancer detection on chest radiographs in a health screening population is unknown. Purpose To validate a commercially available deep learning algorithm for lung cancer detection on chest radiographs in a health screening population. Materials and Methods Out-of-sample testing of a deep learning algorithm was retrospectively performed using chest radiographs from individuals undergoing a comprehensive medical check-up between July 2
This study examined causal relationships among news values, media coverage, and audience attention. News values—deviance and social significance—for 104 news events were measured. Then, media coverage of and audience attention to the events were obtained from Pew Research Center's two data sources. A structural equation model showed a significant effect of news values on the amount of media coverage and also a significant effect of media coverage on audience attention. Further, news values indir
Background The factors affecting radiologists’ diagnostic determinations in artificial intelligence (AI)–assisted image reading remain underexplored. Purpose To assess how AI diagnostic performance and reader characteristics influence detection of malignant lung nodules during AI-assisted reading of chest radiographs. Materials and Methods This retrospective study consisted of two reading sessions from April 2021 to June 2021. Based on the first session without AI assistance, 30 readers were ass
Background It remains unclear whether 5 years of stability is sufficient to establish the benign behavior of subsolid nodules (SSNs) of the lung. There are no guidelines for the length of follow-up needed for these SSNs. Purpose To investigate the incidence of interval growth of pulmonary SSNs 6 mm or greater in diameter after 5 years of stability and their clinical outcome. Materials and Methods This retrospective study assessed SSNs 6 mm or greater that were stable for 5 years after detection
This article reviews the radiologic and pathologic findings of the epithelial and endothelial injuries in COVID-19 pneumonia to help radiologists understand the fundamental nature of the disease. The radiologic and pathologic manifestations of COVID-19 pneumonia result from epithelial and endothelial injuries based on viral toxicity and immunopathologic effects. The pathologic features of mild and reversible COVID-19 pneumonia involve nonspecific pneumonia or an organizing pneumonia pattern, whi
• The pooled incidence of symptomatic air embolism after percutaneous transthoracic lung biopsy was 0.08%, and one-third of patients with symptomatic air embolism had sequelae or died. • The risk factors for symptomatic air embolism were the presence of an underlying disease, the use of a ≥ 19-gauge needle, and coronary or intracranial air embolism. • Sequelae and death in patients with symptomatic air embolism were associated with the use of aspiration biopsy and coronary or intracranial locati
This study examined whether news value indicators influenced sports coverage of the 2002 World Cup soccer games by using a newsworthiness model. The model hypothesized that the more significant and the more deviant an event is, the more prominently the event is covered by the media. Significance and deviance of each match in the World Cup games are operationally defined by using world rankings such as FIFA points, William Hill betting points, and CNN power rankings. Prominence of media coverage
Background A deep learning (DL) model to identify lung cancer screening candidates based on their chest radiographs requires external validation with a recent real-world non-U.S. sample. Purpose To validate the DL model and identify added benefits to the 2021 U.S. Preventive Services Task Force (USPSTF) recommendations in a health check-up sample. Materials and Methods This single-center retrospective study included consecutive current and former smokers aged 50-80 years who underwent chest radi
This study examines mobile divide by gender, age, social economic status (SES), and social capital using a conceptual model of mobile divide. This model is composed of eight components of mobile divide which are divided into the following three groups: two antecedents of mobile use including innovativeness and competence, two types of actual mobile use (talk and non-talk), and consequences of mobile use including life management, resource use, network management, and personal identity display. T
High VFA was associated with long-term mortality and low-grade inflammation. VFA can further stratify the current SO by BMI or VFI, and SO defined by VFA can identify individuals who are most vulnerable to long-term mortality.
Open papers in the app to read, cite, and organize with AI.