A5100644329- Advanced MRI Techniques and Applications
- Computational Drug Discovery Methods
- Medical Imaging Techniques and Applications
- Intracerebral and Subarachnoid Hemorrhage Research
- Medical Image Segmentation Techniques
- Machine Learning in Materials Science
- Brain Tumor Detection and Classification
- Supercapacitor Materials and Fabrication
- Engineering Applied Research
- Radiomics and Machine Learning in Medical Imaging
- Advanced Graph Neural Networks
- Advanced Image Processing Techniques
- Image Processing Techniques and Applications
- Complex Network Analysis Techniques
- HER2/EGFR in Cancer Research
- Acute Ischemic Stroke Management
- Monoclonal and Polyclonal Antibodies Research
- Advanced battery technologies research
- Quantum Dots Synthesis And Properties
- Medical Imaging and Analysis
- Ultrasound Imaging and Elastography
- Advancements in Battery Materials
- Mechanical Engineering and Vibrations Research
- Advanced Photocatalysis Techniques
- Plant biochemistry and biosynthesis
Yonsei University
2020-2024
International Graduate School of English
2024
Korea Advanced Institute of Science and Technology
2021-2024
Asan Medical Center
2022-2023
University of Ulsan
2022
Ulsan College
2022
Ewha Womans University
2015-2018
Ewha Womans University Medical Center
2018
Seoul Institute
2018
Samsung Medical Center
2017
Summary Plants, as a sessile organism, produce various secondary metabolites to interact with the environment. These chemicals have fascinated plant science community because of their ecological significance and notable biological activity. However, predicting complete biosynthetic pathways from target molecules metabolic building blocks remains challenge. Here, we propose retrieval‐augmented dual‐view retrosynthesis (READRetro) practical bio‐retrosynthesis tool predict natural products....
Abstract A universal methodology to efficiently improve the photocatalyst performance of semiconductors was developed by employing exfoliated RuO 2 two‐dimensional nanosheets as a conducting hybridization matrix. The with nanosheet is easily achieved crystal growth or electrostatically derived anchoring semiconductor nanocrystals on nanosheet. An enhanced chemical interaction inorganic hydrophilic fairly effective in optimizing their photocatalytic activity and photostability enhancement...
Magnetic Resonance Imaging (MRI) is sensitive to motion caused by patient movement due the relatively long data acquisition time. This could cause severe degradation of image quality and therefore affect overall diagnosis. In this paper, we develop an efficient retrospective 2D deep learning method called stacked U-Nets with self-assisted priors address problem rigid artifacts in 3D brain MRI. The proposed work exploits usage additional knowledge from corrupted images themselves without need...
An effective way to optimize the electrode performance of metal oxide was developed by employing exfoliated 2D RuO2 nanosheet as a conducting additive. The easily incorporated into Li–MnO2 nanocomposite via simple mixing and MnO2 nanosheets, followed restacking with Li+ ions. incorporation found be quite in increasing surface area restacked nanocomposite. obtained heterolayered Li–MnO2–RuO2 nanocomposites delivered much greater specific capacitances than do pristine Li–RuO2 nanocomposites....
Generating graph-structured data requires learning the underlying distribution of graphs. Yet, this is a challenging problem, and previous graph generative methods either fail to capture permutation-invariance property graphs or cannot sufficiently model complex dependency between nodes edges, which crucial for generating real-world such as molecules. To overcome limitations, we propose novel score-based with continuous-time framework. Specifically, new diffusion process that models joint...
Abstract An efficient chemical way to finely control the layer‐by‐layer stacking of inorganic nanosheets (NS) is developed by tuning type and composition intercalant ion, reaction temperature for restacking process. The controlled NS relies on a kinetic self‐assembly in presence coordinating organic cations. A critical role cations this assembly highlights importance appropriate activation energy. Of prime that fine‐control interstratification 2D highly effective not only tailoring its pore...
Human epidermal growth factor receptors (HERs) are the primary targets of many directed cancer therapies. However, reason a specific dimer HERs generates stronger proliferative signal than other permutations remains unclear. Here, we used single-molecule immunoprecipitation to develop biochemical assay for endogenously-formed, entire HER2-HER3 heterodimers. We observed unexpected, large conformational fluctuations in juxta-membrane and kinase domains heterodimer. Nevertheless, individual...
<italic>In situ</italic> spectroscopic investigation elucidates the crucial role of local structural order in excellent electrocatalytic activity crystalline MnO<sub>2</sub>.
Colorectal cancer is reported to have the highest mortality rate among human malignancies. Although many research results for treatment of colorectal been reported, there no suitable when resistance has developed. Therefore, it necessary develop new therapeutic agents. Janus kinase (JAK)/signal transducer and activator transcription (STAT) signaling plays an essential role in cell differentiation, proliferation, survival. Abnormal activation JAK/STAT pathway, by gene mutation or...
Abstract An efficient chemical way to finely control the layer‐by‐layer stacking of inorganic nanosheets (NS) is developed by tuning type and composition intercalant ion, reaction temperature for restacking process. The controlled NS relies on a kinetic self‐assembly in presence coordinating organic cations. A critical role cations this assembly highlights importance appropriate activation energy. Of prime that fine‐control interstratification 2D highly effective not only tailoring its pore...
Abstract A universal methodology to efficiently improve the photocatalyst performance of semiconductors was developed by employing exfoliated RuO 2 two‐dimensional nanosheets as a conducting hybridization matrix. The with nanosheet is easily achieved crystal growth or electrostatically derived anchoring semiconductor nanocrystals on nanosheet. An enhanced chemical interaction inorganic hydrophilic fairly effective in optimizing their photocatalytic activity and photostability enhancement...
Background Cerebral microbleeds (CMBs) are microscopic brain hemorrhages with implications for various diseases. Automated detection of CMBs is a challenging task due to their wide distribution throughout the brain, small size, and visual similarity mimics. For this reason, most previously proposed methods have been accomplished through two distinct stages, which may lead difficulties in integrating them into clinical workflows. Purpose To develop clinically feasible end‐to‐end network...
Robot's appearance types could be classified into human-oriented robot and product-oriented robot. Human-oriented resembles human's behavior whereas is an intelligent product that laden with robotic technologies based on the existing [1]. In Kwak et al.'s study [1], customers categorized a as one of categories, was more effective than for consumers' evaluation purchase intention toward robots. On basis this, we developed several products including slippers, Christmas tree blocks, piggy bank,...
To enable acceleration in 3D multi-echo gradient echo (mGRE) acquisition for myelin water imaging (MWI) by combining joint parallel (JPI) and deep learning (JDL).We implemented a multistep reconstruction process using both advanced network which can utilize spatiotemporal components between the images to further accelerate mGRE MWI. In first step, JPI was performed estimate missing k-space lines. Next, JDL reduce residual artifacts produce high-fidelity variable splitting optimization...
A well-known limitation of existing molecular generative models is that the generated molecules highly resemble those in training set. To generate truly novel may have even better properties for de novo drug discovery, more powerful exploration chemical space necessary. this end, we propose Molecular Out-Of-distribution Diffusion(MOOD), a score-based diffusion scheme incorporates out-of-distribution (OOD) control stochastic differential equation (SDE) with simple hyperparameter, thus...
Patient movement during MRI scan can cause severe degradation of image quality. In Susceptibility-Weighted Imaging (SWI), several echoes are measured a single repetition period, where the earliest show less contrast between various tissues, while higher more susceptible to artifacts and signal dropout. This paper proposes data-driven retrospective deep learning method by taking advantage interactively multiple together through sharing their knowledge using unified training parameters. The...