A5057920247- Radiomics and Machine Learning in Medical Imaging
- COVID-19 diagnosis using AI
- Hepatocellular Carcinoma Treatment and Prognosis
- Quantum Dots Synthesis And Properties
- Advanced Radiotherapy Techniques
- Educational Systems and Policies
- Chalcogenide Semiconductor Thin Films
- AI in cancer detection
- Semiconductor materials and devices
- Lung Cancer Diagnosis and Treatment
- Educational Research and Pedagogy
- Medical Imaging Techniques and Applications
- Education and Learning Interventions
- Coronary Interventions and Diagnostics
- Liver Disease and Transplantation
- Nanowire Synthesis and Applications
- Cardiac Imaging and Diagnostics
- Privacy-Preserving Technologies in Data
- Pneumonia and Respiratory Infections
- Luminescence Properties of Advanced Materials
- Artificial Intelligence in Healthcare and Education
- Liver Disease Diagnosis and Treatment
- ZnO doping and properties
- Thin-Film Transistor Technologies
- Renal cell carcinoma treatment
Yonsei University
2003-2025
Korea Advanced Institute of Science and Technology
2012-2024
Korea Institute of Brain Science
2019-2023
Myongji Hospital
2012-2022
Hanyang University Medical Center
2022
Seoul National University Hospital
2017-2021
Chungbuk National University Hospital
2021
National University College
2021
New Generation University College
2015-2021
Gachon University
2012-2019
Under the global pandemic of COVID-19, use artificial intelligence to analyze chest X-ray (CXR) image for COVID-19 diagnosis and patient triage is becoming important. Unfortunately, due emergent nature pandemic, a systematic collection CXR data set deep neural network training difficult. To address this problem, here we propose patch-based convolutional approach with relatively small number trainable parameters diagnosis. The proposed method inspired by our statistical analysis potential...
Alpha-fetoprotein (AFP), Lens culinaris-agglutinin-reactive fraction of AFP (AFP-L3), and protein induced by vitamin K absence or antagonist-II (PIVKA-II) are widely used as tumor markers for the diagnosis hepatocellular carcinoma (HCC). This study compared diagnostic values AFP, AFP-L3, PIVKA-II individually in combination to find best biomarker panel. Seventy-nine patients with newly diagnosed HCC 77 non-HCC control liver cirrhosis were enrolled. measured same serum samples using microchip...
Although deep learning-based computer-aided diagnosis systems have recently achieved expert-level performance, developing a robust learning model requires large, high-quality data with manual annotation, which is expensive to obtain. This situation poses the problem that chest x-rays collected annually in hospitals cannot be used due lack of labeling by experts, especially deprived areas. To address this, here we present novel framework uses knowledge distillation through self-supervised and...
Target volume contouring for radiation therapy is considered significantly more challenging than the normal organ segmentation tasks as it necessitates utilization of both image and text-based clinical information.Inspired by recent advancement large language models (LLMs) that can facilitate integration textural information images, here we present an LLM-driven multimodal artificial intelligence (AI), namely LLMSeg, utilizes applicable to task 3-dimensional context-aware target delineation...
The aim of this study was to investigate whether the computed tomography (CT) texture features primary tumors are associated with overall survival (OS) non-small cell lung cancer (NSCLC) patients undergoing definitive concomitant chemoradiotherapy (CCRT).In retrospective study, 98 (83 men and 15 women; mean age, 61.9 ± 8.0 years) unresectable NSCLCs (stage IIIA, 45; stage IIIB, 53) underwent CCRT at our institution from January 2006 December 2011. Patients were followed up for 3 years or...
We fabricated metallic nanostructures directly on Si substrates through a hybrid nanoprocess combining atomic layer deposition (ALD) and self-assembled anodic aluminum oxide (AAO) nanotemplate. ALD Ru films with Ru(DMPD)(EtCp) as precursor O2 reactant exhibited high purity low resistivity negligible nucleation delay roughness. These good growth characteristics resulted in the excellent conformality for nanometer-scale vias trenches. Additionally, AAO nanotemplates were Ti/Si multiple...
Abstract A novel 3D nnU-Net-based of algorithm was developed for fully-automated multi-organ segmentation in abdominal CT, applicable to both non-contrast and post-contrast images. The trained using dual-energy CT (DECT)-obtained portal venous phase (PVP) spatiotemporally-matched virtual images, tested a single-energy (SE) dataset comprising PVP true (TNC) showed robust accuracy segmenting the liver, spleen, right kidney (RK), left (LK), with mean dice similarity coefficients (DSCs)...
Groucho function is essential for Drosophila development, acting as a corepressor specific transcription factors that are downstream targets of various signaling pathways. Here we provide evidence phosphorylated by the DHIPK2 protein kinase. Phosphorylation modulates activity attenuating its protein-protein interaction with DNA-bound factor. During eye modifies activity, and phenotypes generated overexpression differ depending on phosphorylation state. Moreover, analysis nuclear extracts...
To evaluate the feasibility and effectiveness of endovascular stent-graft repair infected aortic arterial aneurysms.Eight patients (5 men; mean age 56.6 years, range 30-85) with saccular aneurysms in brachiocephalic artery (n=1), proximal descending thoracic aorta infrarenal abdominal (n=3), common iliac femoral (n=2) were treated placement intravenous antibiotic treatment for at least 6 weeks followed by case-specific administration oral suppressive antibiotics. All considered to be...