Joon Beom Seo

ORCID: 0000-0003-0271-7884
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Lung Cancer Diagnosis and Treatment
  • Chronic Obstructive Pulmonary Disease (COPD) Research
  • Radiomics and Machine Learning in Medical Imaging
  • COVID-19 diagnosis using AI
  • Advanced X-ray and CT Imaging
  • Interstitial Lung Diseases and Idiopathic Pulmonary Fibrosis
  • Medical Imaging Techniques and Applications
  • Atomic and Subatomic Physics Research
  • Respiratory Support and Mechanisms
  • Radiation Dose and Imaging
  • Asthma and respiratory diseases
  • Medical Imaging and Pathology Studies
  • Cardiac Imaging and Diagnostics
  • AI in cancer detection
  • Advanced MRI Techniques and Applications
  • Ultrasound in Clinical Applications
  • Lung Cancer Treatments and Mutations
  • Pleural and Pulmonary Diseases
  • Tracheal and airway disorders
  • Inhalation and Respiratory Drug Delivery
  • Sarcoidosis and Beryllium Toxicity Research
  • Radiology practices and education
  • Aortic Disease and Treatment Approaches
  • Artificial Intelligence in Healthcare and Education
  • Venous Thromboembolism Diagnosis and Management

University of Ulsan
2016-2025

Asan Medical Center
2016-2025

Ulsan College
2016-2025

Radboud University Medical Center
2024

Lenox Hill Hospital
2024

Radboud University Nijmegen
2024

University Medical Center
2024

University of Pennsylvania
2021-2024

Stanford University
2024

Research Institute of Radiology
2007-2023

Background Intratumor heterogeneity in lung cancer may influence outcomes. CT radiomics seeks to assess tumor features provide detailed imaging features. However, radiomic vary according the reconstruction kernel used for image generation. Purpose To investigate effect of different kernels on and whether conversion using a convolutional neural network (CNN) could improve reproducibility between kernels. Materials Methods In this retrospective analysis, patients underwent non–contrast...

10.1148/radiol.2019181960 article EN Radiology 2019-06-18

Pulmonary MRI provides structural and quantitative functional images of the lungs without ionizing radiation, but it has had limited clinical use due to low signal intensity from lung parenchyma. The lack radiation makes pulmonary an ideal modality for pediatric examinations, pregnant women, patients requiring serial longitudinal follow-up. Fortunately, recent techniques, including ultrashort echo time zero time, are expanding opportunities MRI. With multicoil parallel acquisitions...

10.1148/radiol.2020201138 article EN Radiology 2020-09-01

Background: In lung adenocarcinomas manifesting as part-solid lesions, evidence supports greater prognostic importance for the volume of solid component than whole nodule. However, assessments lesion growth rates have historically focused on doubling time (VDT) lesion. Objective: To compare utility VDT versus resected lesions chest CT. Methods: This retrospective study included 122 patients (mean age, 64.0 ± 8.2years; 53 men, 69 women) with adenocarcinoma a who underwent at least two...

10.2214/ajr.24.32470 article EN American Journal of Roentgenology 2025-02-12

To describe findings of pulmonary tuberculoma at 2-[fluorine 18]fluoro-2-deoxy-D-glucose (FDG) positron emission tomography (PET).Ten consecutive patients who underwent PET and subsequently were proved to have analyzed. Tuberculosis was histopathologically in eight by means wedge resection or lobectomy (n = 7) needle biopsy 1) two clinical follow-up for more than 2 years. scans evaluated using peak standardized uptake values. Computed tomographic (CT) histopathologic also reviewed.Nine 10...

10.1148/radiology.216.1.r00jl19117 article EN Radiology 2000-07-01

Purpose: To determine the clinical utility of dual-energy computed tomography (CT) in evaluating solitary pulmonary nodules (SPNs). Materials and Methods: This study was approved by institutional review board, informed consent obtained. CT scans were obtained before 3 minutes after contrast material injection 49 patients (26 men, 23 women; mean age, 60.39 years ± 12.24 [standard deviation]) using a scanner with technique. Image sets that included nonenhanced weighted average, enhanced...

10.1148/radiol.2492071956 article EN Radiology 2008-09-16

Institutional review board approval and written informed consent were obtained. Although xenon (Xe) ventilation CT has been introduced as a potential method with which to depict regional ventilation, quantification of Xe enhancement limited by the variability lung attenuation caused different volumes between scans. The purpose this study was assess feasibility dual-energy technique. Dual-energy performed in 12 subjects after inhalation. With use technique, component could be extracted...

10.1148/radiol.2482071482 article EN Radiology 2008-07-18

The purpose of this study was to prospectively evaluate the usefulness scoring perfusion defects on images at dual-energy CT for assessment severity pulmonary embolism.Thirty patients (13 men, 17 women; mean age, 55 +/- 15 [SD] years; range, 26-81 years) with thromboembolism underwent dual-source two voltages (140 and 80 kV). weighted average image acquisitions used angiograms, a color-coded iodine images. Two thoracic radiologists 6 years clinical experience independently assigned defect...

10.2214/ajr.09.2681 article EN American Journal of Roentgenology 2010-02-19

Background Evaluation of interstitial lung disease (ILD) at CT is a challenging task that requires experience and subject to substantial interreader variability. Purpose To investigate whether proposed content-based image retrieval (CBIR) similar chest images by using deep learning can aid in the diagnosis ILD readers with different levels experience. Materials Methods This retrospective study included patients confirmed after multidisciplinary discussion available identified between January...

10.1148/radiol.2021204164 article EN Radiology 2021-10-12

Background Previous studies assessing the effects of computer-aided detection on observer performance in reading chest radiographs used a sequential design that may have biased results because order or recall bias. Purpose To compare detecting and localizing major abnormal findings including nodules, consolidation, interstitial opacity, pleural effusion, pneumothorax without versus with deep learning–based (DLD) system assistance randomized crossover design. Materials Methods This study...

10.1148/radiol.2021202818 article EN Radiology 2021-03-23
Coming Soon ...