Yoon, Soon Ho
Seoul National University · Medicine
About the Lab
Professor Yoon Soon Ho's research lab specializes in diagnostic radiology and medical imaging, with a strong focus on thoracic and abdominal radiology. The lab investigates advanced imaging techniques for early detection and characterization of lung and liver diseases, particularly using CT and PET-CT. Key research directions include the radiological features of COVID-19 pneumonia, sarcopenia assessment via deep learning on whole-body CT, and improving the safety and accuracy of percutaneous lung biopsies. The lab also develops AI-driven tools for automated segmentation of body composition, enhancing personalized medicine and clinical decision-making.
Research Overview
Research Output Trend
Figures are computed from collected data and may differ slightly.
Selected Papers
15COVID-19 pneumonia in Korea primarily manifested as pure to mixed ground-glass opacities with a patchy to confluent or nodular shape in the bilateral peripheral posterior lungs. A considerable proportion of patients with COVID-19 pneumonia had normal chest radiographs.
http://radiology.rsna.org/lookup/suppl/doi:10.1148/radiol.11101133/-/DC1.
The prevalent enhancement patterns of HCC smaller than 3 cm on multiphasic MDCT scans differed depending on tumor size and cellular differentiation. HCCs smaller than 2 cm and well-differentiated HCCs frequently had atypical enhancement patterns.
BACKGROUND & AIMS: Body composition analysis on CT images is a valuable tool for sarcopenia assessment. We aimed to develop and validate a deep neural network applicable to whole-body CT images of PET-CT scan for the automatic volumetric segmentation of body composition. METHODS: F-fluorodeoxyglucose PET-CT scans of 100 patients were retrospectively included. Two radiologists semi-automatically labeled the following seven body components in every CT image slice, providing a total of 46,967 image
Hemoptysis occurred less frequently with CT-based guidance modalities in comparison with fluoroscopy. Although pneumothorax requiring chest tube insertion showed a similar incidence, pneumothorax was more frequently detected using CT-based guidance modalities.
Percutaneous transthoracic needle biopsy (PTNB) is one of the essential diagnostic procedures for pulmonary lesions. Its role is increasing in the era of CT screening for lung cancer and precision medicine. The Korean Society of Thoracic Radiology developed the first evidence-based clinical guideline for PTNB in Korea by adapting pre-existing guidelines. The guideline provides 39 recommendations for the following four main domains of 12 key questions: the indications for PTNB, pre-procedural eva
Background CT manifestations of SARS-CoV-2 may differ among variants. Purpose To compare the chest CT findings of SARS-CoV-2 between the Delta and Omicron variants. Materials and Methods This retrospective study collected consecutive baseline chest CT images of hospitalized patients with SARS-CoV-2 from a secondary referral hospital when the Delta and Omicron variants were predominant. Two radiologists categorized CT images according to the RSNA classification system for COVID-19 and visually gr
Purpose To evaluate histogram and texture parameters on pretreatment dynamic contrast material-enhanced (DCE) magnetic resonance (MR) images in lung cancer in terms of temporal change, optimal time for analysis, and prognostic potential. Materials and Methods This retrospective study was approved by the institutional review board, and the requirement to obtain informed consent was waived. Thirty-eight patients with pathologically proved lung cancer undergoing standard pretreatment DCE MR imaging
INTRODUCTION: Conflicting results exist regarding whether preoperative transthoracic biopsy increases the risk of pleural recurrence in early lung cancer. We conducted a systematic, patient-level meta-analysis to evaluate the risk of pleural recurrence in stage I lung cancer after percutaneous transthoracic lung biopsy. METHODS: A systematic search of OVID-MEDLINE, Embase and the Cochrane Database of Systematic Reviews was performed through October 2018. Eligible studies were original articles o
OBJECTIVE: This study aimed to develop an open-source multimodal large language model (CXR-LLaVA) for interpreting chest X-ray images (CXRs), leveraging recent advances in large language models (LLMs) to potentially replicate the image interpretation skills of human radiologists. MATERIALS AND METHODS: For training, we collected 592,580 publicly available CXRs, of which 374,881 had labels for certain radiographic abnormalities (Dataset 1) and 217,699 provided free-text radiology reports (Dataset
Various designs of positron emission tomography/magnetic resonance imaging (PET/MRI) systems have been recently introduced to clinical practice, which have overcome preexisting technical challenges concerning the fusion of PET and MRI systems. Although further improvements are still necessary especially for bony lesions, quantification using current MRI-based attenuation correction techniques has been shown to be comparable to that of PET/computed tomography (CT) systems. On the basis of the res
Research Areas
Dive deeper into Yoon, Soon Ho's research on Nubint
Open this lab's papers in the app to read with AI, summarize, and cite in your writing.