Search

Your search keyword '"Kim, Jae-Seong"' showing total 11 results
Start Over Author "Kim, Jae-Seong" Publication Year Range Last 3 years
11 results on '"Kim, Jae-Seong"'

2. Deep Learning-based Synthetic High-Resolution In-Depth Imaging Using an Attachable Dual-element Endoscopic Ultrasound Probe

Author

Lew, Hah Min, Kim, Jae Seong, Lee, Moon Hwan, Park, Jaegeun, Youn, Sangyeon, Kim, Hee Man, Kim, Jihun, and Hwang, Jae Youn

Subjects
Electrical Engineering and Systems Science - Image and Video Processing, Electrical Engineering and Systems Science - Systems and Control
Abstract

Endoscopic ultrasound (EUS) imaging has a trade-off between resolution and penetration depth. By considering the in-vivo characteristics of human organs, it is necessary to provide clinicians with appropriate hardware specifications for precise diagnosis. Recently, super-resolution (SR) ultrasound imaging studies, including the SR task in deep learning fields, have been reported for enhancing ultrasound images. However, most of those studies did not consider ultrasound imaging natures, but rather they were conventional SR techniques based on downsampling of ultrasound images. In this study, we propose a novel deep learning-based high-resolution in-depth imaging probe capable of offering low- and high-frequency ultrasound image pairs. We developed an attachable dual-element EUS probe with customized low- and high-frequency ultrasound transducers under small hardware constraints. We also designed a special geared structure to enable the same image plane. The proposed system was evaluated with a wire phantom and a tissue-mimicking phantom. After the evaluation, 442 ultrasound image pairs from the tissue-mimicking phantom were acquired. We then applied several deep learning models to obtain synthetic high-resolution in-depth images, thus demonstrating the feasibility of our approach for clinical unmet needs. Furthermore, we quantitatively and qualitatively analyzed the results to find a suitable deep-learning model for our task. The obtained results demonstrate that our proposed dual-element EUS probe with an image-to-image translation network has the potential to provide synthetic high-frequency ultrasound images deep inside tissues., Comment: 10 pages, 9 figures

Published
2023

5. Label-free single-cell antimicrobial susceptibility testing in droplets with concentration gradient generation.

Author

Kim, Jae Seong, Kim, Jingyeong, Kim, Jae-Seok, Kim, Wooseong, and Lee, Chang-Soo

Subjects
*MICROBIAL sensitivity tests, *ESCHERICHIA coli, *DRUG resistance in bacteria, *CONCENTRATION gradient, *GRAM-negative bacteria
Abstract

Bacterial communities exhibit significant heterogeneity, resulting in the emergence of specialized phenotypes that can withstand antibiotic exposure. Unfortunately, the existence of subpopulations resistant to antibiotics often goes unnoticed during treatment initiation. Thus, it is crucial to consider the concept of single-cell antibiotic susceptibility testing (AST) to tackle bacterial infections. Nevertheless, its practical application in clinical settings is hindered by its inability to conduct AST efficiently across a wide range of antibiotics and concentrations. This study introduces a droplet-based microfluidic platform designed for rapid single-cell AST by creating an antibiotic concentration gradient. The advantage of a microfluidic platform is achieved by executing bacteria and antibiotic mixing, cell encapsulation, incubation, and enumeration of bacteria in a seamless workflow, facilitating susceptibility testing of each antibiotic. Firstly, we demonstrate the rapid determination of minimum inhibitory concentration (MIC) of several antibiotics with Gram-negative E. coli and Gram-positive S. aureus, which enables us to bypass the time-consuming bacteria cultivation, speeding up the AST in 3 h from 1 to 2 days of conventional methods. Additionally, we assess 10 clinical isolates including methicillin-resistant Staphylococcus aureus (MRSA) and multidrug-resistant Staphylococcus aureus (MDRSA) against clinically important antibiotics for analyzing the MIC, compared to the gold standard AST method from the United States Clinical and Laboratory Standards Institute (CLSI), which becomes available only after 48 h. Furthermore, by monitoring single cells within individual droplets, we have found a spectrum of resistance levels among genetically identical cells, revealing phenotypic heterogeneity within isogenic populations. This discovery not only advances clinical diagnostics and treatment strategies but also significantly contributes to the field of antibiotic stewardship, underlining the importance of our approach in addressing bacterial resistance. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results