A5101863869- Lung Cancer Diagnosis and Treatment
- Radiomics and Machine Learning in Medical Imaging
- Pleural and Pulmonary Diseases
- Lung Cancer Treatments and Mutations
- Chronic Obstructive Pulmonary Disease (COPD) Research
- COVID-19 diagnosis using AI
- MRI in cancer diagnosis
- Radiology practices and education
- Advanced MRI Techniques and Applications
- Neutropenia and Cancer Infections
- Bacterial Identification and Susceptibility Testing
- Cardiac, Anesthesia and Surgical Outcomes
- Body Composition Measurement Techniques
- Interstitial Lung Diseases and Idiopathic Pulmonary Fibrosis
- Nutrition and Health in Aging
- Pericarditis and Cardiac Tamponade
- Antifungal resistance and susceptibility
- Hepatocellular Carcinoma Treatment and Prognosis
- Advanced X-ray and CT Imaging
- Medical Imaging Techniques and Applications
- Glioma Diagnosis and Treatment
- Lanthanide and Transition Metal Complexes
- Advanced Neuroimaging Techniques and Applications
- Healthcare Systems and Technology
- Tuberculosis Research and Epidemiology
Seoul National University Hospital
2017-2025
Seoul National University
2017-2024
Suwon Research Institute
2021
National University College
2020
BackgroundThe performance of a deep learning (DL) algorithm should be validated in actual clinical situations, before its implementation.PurposeTo evaluate the DL for identifying chest radiographs with clinically relevant abnormalities emergency department (ED) setting.Materials and MethodsThis single-center retrospective study included consecutive patients who visited ED underwent initial radiography between January 1 March 31, 2017. Chest were analyzed commercially available algorithm. The...
Background It remains unclear whether 5 years of stability is sufficient to establish the benign behavior subsolid nodules (SSNs) lung. There are no guidelines for length follow-up needed these SSNs. Purpose To investigate incidence interval growth pulmonary SSNs 6 mm or greater in diameter after and their clinical outcome. Materials Methods This retrospective study assessed that were stable detection (January 2002 December 2018). The radiologic features investigated. Clinical stage shifts...
Background: Artificial intelligence (AI) tools for evaluating low-dose CT (LDCT) lung cancer screening examinations are used predominantly assisting radiologists' interpretations. Alternate utilization scenarios (e.g., use of AI as a prescreener or backup) warrant consideration. Objective: To evaluate the impact different on diagnostic outcomes and interpretation times LDCT screening. Methods: This retrospective study included 366 individuals (358 male, 8 female; mean age, 64 years) who...
Background A computer-aided detection (CAD) system may help surveillance for pulmonary metastasis at chest radiography in situations where there is limited access to CT. Purpose To evaluate whether a deep learning (DL)-based CAD can improve diagnostic yield newly visible lung on radiographs patients with cancer. Materials and Methods regulatory-approved nodules was implemented interpret from referred by the medical oncology department clinical practice. In this retrospective cohort study,...
To compare image qualities between vendor-neutral and vendor-specific hybrid iterative reconstruction (IR) techniques for abdominopelvic computed tomography (CT) in young patients.In phantom study, we used an anthropomorphic pediatric phantom, age-equivalent to 5-year-old, reconstructed CT data using traditional filtered back projection (FBP), IR (ClariCT; ClariPI) various radiation doses. Noise, low-contrast detectability subjective spatial resolution were compared FBP, (i.e., iDose1 5;...
<h3>BACKGROUND AND PURPOSE:</h3> Glioblastoma is the most common primary brain malignancy and differentiation of true progression from pseudoprogression clinically important. Our purpose was to compare diagnostic performance dynamic contrast-enhanced pharmacokinetic parameters using fixed T1 measured on differentiating glioblastoma after chemoradiation with temozolomide. <h3>MATERIALS METHODS:</h3> This retrospective study included 37 patients histopathologically confirmed new enhancing...
Background Tumor stiffness (TS), measured by magnetic resonance elastography (MRE), could be associated with tumor mechanical properties and grade. Purpose To determine whether TS obtained using MRE is survival in patients single nodular hepatocellular carcinoma (HCC) after hepatic resection (HR). Study Type Retrospective. Population In all, 95 pathologically confirmed HCCs. Field Strength/Sequence 1.5T/ 3D spin‐echo echo‐planar imaging MRE. Assessment values of the whole (TS‐WT) a solid...
This study evaluated the possibility of accelerated gadolinium accumulation in irradiated brain parenchyma where blood-brain barrier was weakened.From January 2010 to June 2015, 44 patients with supratentorial glioblastoma were retrospectively identified who underwent pre- and post-radiation MR imaging, including R1 mapping. The mean dose administered gadobutrol (Gadovist, Bayer, Germany) 5.1 vials. Regions interest (ROIs) drawn around tumors that located within 50-100% iso-dose lines...
To evaluate the accuracy of a deep learning-based computer-aided detection (CAD) system in identifying active pulmonary tuberculosis on chest radiographs (CRs) patients with positive interferon-gamma release assay (IGRA) results different scenarios clinical implementation.We collected CRs consecutive IGRA results. Findings were independently evaluated by CAD and thoracic radiologist, followed interpretation using CAD. Sensitivity specificity scenarios: (a) radiologists' interpretation, (b)...
Abstract Various methods were suggested to measure skeletal muscle areas (SMAs) using chest low-dose computed tomography (chest LDCT) as a substitute for SMA at 3rd lumbar vertebra level (L3-SMA). In this study, four SMAs (L1-SMA, T12-erector spinae areas, wall area carina level, pectoralis aortic arch level) segmented semi-automatically in 780 individuals taking concurrent and abdomen LDCT healthcare screening. Four compared L3-SMA annual changes calculated from with multiple examinations...
Abstract Objective To investigate the association of smoking with outcomes percutaneous transthoracic needle biopsy (PTNB). Methods In total, 4668 PTNBs for pulmonary lesions were retrospectively identified. The associations status (never, former, current smokers) and intensity (≤ 20, 21–40, > 40 pack-years) diagnostic results (malignancy, non-diagnostic pathologies, false-negative in pathologies) complications (pneumothorax hemoptysis) assessed using multivariable logistic regression...
Objective To determine the optimum definition of growth for indeterminate pulmonary nodules detected in lung cancer screening. Materials and methods Individuals with as defined by volume 50–500 mm 3 (solid nodules) solid component or average diameter non-solid ≥8 (part-solid on baseline screening low-dose chest CT (LDCT) were included. The diameters volumes measured follow-up LDCTs semi-automated segmentation. Sensitivities specificities diagnosis nodule a) percentage ≥25% (defined NELSON...
Abstract Background Diagnosis of pneumonia is critical in managing patients with febrile neutropenia (FN), however, chest X-ray (CXR) has limited performance the detection pneumonia. We aimed to evaluate a deep learning-based computer-aided (CAD) system CXRs consecutive FN and investigated whether CAD could improve radiologists’ diagnostic when used as second reader. Methods (a body temperature ≥ 38.3 °C, or sustained 38.0 °C for an hour; absolute neutrophil count < 500/mm 3 ) obtained...
Abstract Temporal and spatial resolution of dynamic contrast-enhanced MR imaging (DCE-MRI) is critical to reproducibility, the reproducibility high-resolution (HR) DCE-MRI was evaluated. Thirty consecutive patients suspected have brain tumors were prospectively enrolled with written informed consent. All underwent both HR-DCE (voxel size, 1.1 × mm 3 ; scan interval, 1.6 s) conventional DCE (C-DCE; voxel 1.25 3.0 4.0 MRI. Regions interests (ROIs) for enhancing lesions segmented twice in each...
Objectives To validate the performances of two prediction models (Brock and Lee models) for differentiation minimally invasive adenocarcinoma (MIA) pulmonary (IPA) from preinvasive lesions among subsolid nodules (SSNs). Design A retrospective cohort study. Setting tertiary university hospital in South Korea. Participants 410 patients with incidentally detected SSNs who underwent surgical resection spectrum between 2011 2015. Primary secondary outcome measures Using clinical radiological...
To investigate the incidence and timing of late growth subsolid nodules (SSNs) ≥6 mm after initial 5-year stability, its clinical implications, appropriate follow-up strategy.
Association between smoking intensity and the quantity quality of thoracic skeletal muscles (TSMs) remains unexplored. Skeletal muscle index (SMI; area/height2) percentage normal attenuation area (NAMA%) were measured to represent muscles, respectively, quantification was performed in pectoralis at aortic arch (AA-PM), TSM carina (C-TSM), erector spinae T12 (T12-ESM), L1 (L1-SM). Among 258 men (median age, 62 years [IQR: 58-69]), 183 current smokers intensity, 40 pack-years 30-46]). SMI...
Background Pulmonary infection is a major cause of morbidity and mortality in immunocompromised patients, whom diagnostic yields cone-beam computed tomography (CBCT)-guided percutaneous transthoracic needle biopsies (PTNBs) have not been evaluated so far. Purpose To evaluate complications CBCT-guided PTNBs patients. Material Methods From January 2015 to 2018, 43 patients (25 men, 18 women; mean age 54.1 ± 16.4 years) who were suspected having pulmonary infections included this retrospective...