A5047329390- Railway Systems and Energy Efficiency
- Cultural and Historical Studies
- Electrical Contact Performance and Analysis
- HVDC Systems and Fault Protection
- Engineering Applied Research
- Radiomics and Machine Learning in Medical Imaging
- Power Systems and Technologies
- Microgrid Control and Optimization
- Electric and Hybrid Vehicle Technologies
- CNS Lymphoma Diagnosis and Treatment
- Nanoplatforms for cancer theranostics
- Internet of Things and Social Network Interactions
- Lymphoma Diagnosis and Treatment
- Power Quality and Harmonics
- Glioma Diagnosis and Treatment
- Frequency Control in Power Systems
- Lung Cancer Treatments and Mutations
- Power System Optimization and Stability
- Nanoparticle-Based Drug Delivery
- Railway Engineering and Dynamics
- High-Voltage Power Transmission Systems
- Power System Reliability and Maintenance
- Lung Cancer Diagnosis and Treatment
- Thermal Analysis in Power Transmission
- Maritime Transport Emissions and Efficiency
Korea Advanced Institute of Science and Technology
2014-2025
Semyung University
2018-2023
Gangnam Severance Hospital
2022-2023
Yonsei University
2019-2023
Creative Commons
2023
Severance Hospital
2023
Sungkyunkwan University
2015-2021
Seoul National University Bundang Hospital
2021
Korea Electric Power Corporation (South Korea)
2016-2021
Dankook University
2019-2020
Plankton image classification plays an important role in the ocean ecosystems research. Recently, a large scale database for plankton with over 3 million images annotated 100 classes was released. However, suffers from imbalanced class distribution which 90% of belong to only 5 classes. Due this class-imbalance problem, existing approaches are limited label data major classes, ignoring small-sized In paper, we propose fine-grained method based on convolutional neural networks (CNN). To...
Optically active nanomaterials have shown great promise as a nanomedicine platform for photothermal or photodynamic cancer therapies. Herein, we report gold-nanoclustered hyaluronan nanoassembly (GNc-HyNA) photothermally boosted tumor ablation. Unlike other supramolecular gold constructs based on nanoparticle building blocks, this system utilizes the of amphiphilic conjugates drug carrier hydrophobic therapy agent verteporfin, polymeric reducing agent, and an organic nanoscaffold upon which...
This paper proposes an application of superconducting flywheel energy storages (SFESs) to compensate the power fluctuation large scale wind farm. Based on global interest against warming, capacity renewable generation, especially has been increased steeply. However, since generations depend natural speed completely, output cannot be controlled. The caused by non-controllable characteristic may create voltage problem for local system and frequency whole system. To solve those problems, hybrid...
Introduction: Hyaluronic acid (HA) has emerged as a promising applicant for the tumor-targeted delivery of various therapeutic agents. Because its biocompatibility, biodegradability and receptor-binding properties, HA been extensively investigated drug carrier. In this review, recent advances in HA-based nanomedicines are discussed.
In dental X-ray images, an accurate detection of cephalometric landmarks plays important role in clinical diagnosis, treatment and surgical decisions for problems. this work, we propose end-to-end deep learning system landmark using convolutional neural networks (CNN). For detecting 19 develop a CNN-based coordinate-wise regression systems. By viewing x- y-coordinates all as 38 independent variables, multiple systems are constructed to predict the coordinate variables from input images....
Segmentation of cervical cells in microscopic images is an important task for computer-aided diagnosis cancer. However, their segmentation challenging due to inhomogeneous cell cytoplasm and the overlap between cells. In this paper, we propose automatic method multiple overlapping using superpixel partitioning cell-wise contour refinement. First, masses are detected by generation triangle thresholding. Then, nuclei extracted local thresholding outlier removal. Finally, initially segmented...
Abstract Extracellular vesicles (EVs) are essential mediators in intercellular communication that have emerged as natural therapeutic nanomedicines for the treatment of intractable diseases. Their applications, however, been limited by unpredictable vivo biodistribution after systemic administration. To control fate EVs, their surfaces should be properly edited, depending on target site action. Herein, based bioorthogonal copper‐free click chemistry (BCC), surface‐edited EVs were prepared...
Mesoporous silica nanoparticles (MSNs) with stimuli-responsive gatekeepers have been extensively investigated for controlled drug delivery at the target sites.
Owing to the consistent increase in energy efficiency issues, studies for improving charging and density of batteries have been receiving attention electric vehicle transportation sector. This paper deals with an online (OLEV) system which utilizes dc power reducing loss as well size required battery capacity. Intensive research on grid integration OLEV has not performed until recently it is necessary calculate flow analysis considering unique characteristics commercialization this new...
The interaction of programmed death-1 protein (PD-1) and ligand (PD-L1) produces immunosuppressive activity, protecting tumor cells from anti-tumor immunity possibly releasing soluble PD-L1 (sPD-L1) expressing cells. Therefore, we measured serum levels sPD-L1 in patients with primary central nervous system lymphoma (PCNSL) explored its clinical implications.Sixty-eight newly diagnosed PCNSL had diffuse large B-cell were treated high-dose methotrexate-containing chemotherapy. measurement...
In this paper, we propose a method to address the class imbalance learning in classification of focal liver lesions (FLLs) from abdominal CT images. Class is significant challenge medical image analysis, making it difficult for machine models learn classify them accurately. To overcome this, class-wise combination mixture-based data augmentation (CCDA) that uses two techniques, MixUp and AugMix. These are applied at different ratios each adaptively features class. This tailored handle unique...
Breast cancer rarely metastasizes to the gastrointestinal tract, including stomach. Due rarity of this metastasis, it is occasionally confused with a primary stomach malignancy. However, discriminating characteristic features clinical implications may exist. The aim current study was analyze and prognosis breast gastric metastasis. Between January 1994 October 2016, 13 patients at Samsung Medical Center (Seoul, Korea) were clinically or pathologically determined have present retrospectively...
Abstract Purpose We propose a deep learning method that classifies focal liver lesions (FLLs) into cysts, hemangiomas, and metastases from portal phase abdominal CT images. synthetic data augmentation process to alleviate the class imbalance Lesion INformation Augmented (LINA) patch improve efficiency. Methods A dataset of 502 scans 1,290 FLLs was used. First, diversify training patterns, we suggest using DCGAN‐based lesion mask synthesis pix2pix‐based mask‐to‐image translation. Second,...
8521 Background: No standard treatment exists for patients with thymic epithelial tumor (TET) who progress after platinum-containing chemotherapy. We conducted a phase II study of pembrolizumab in TET to evaluate the efficacy and safety. Methods: Between March 2016 December 2016, histologically confirmed progressed chemotherapy were eligible. Patients excluded if they had an active autoimmune disease requiring systemic within past one year. received 200mg intravenously every 3 weeks until...