Search

Your search keyword '"You, Sun Kyoung"' showing total 134 results
Start Over Author "You, Sun Kyoung"
134 results on '"You, Sun Kyoung"'

3. Unpaired image denoising using a generative adversarial network in X-ray CT

Author

Park, Hyoung Suk, Baek, Jineon, You, Sun Kyoung, Choi, Jae Kyu, and Seo, Jin Keun

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

This paper proposes a deep learning-based denoising method for noisy low-dose computerized tomography (CT) images in the absence of paired training data. The proposed method uses a fidelity-embedded generative adversarial network (GAN) to learn a denoising function from unpaired training data of low-dose CT (LDCT) and standard-dose CT (SDCT) images, where the denoising function is the optimal generator in the GAN framework. This paper analyzes the f-GAN objective to derive a suitable generator that is optimized by minimizing a weighted sum of two losses: the Kullback-Leibler divergence between an SDCT data distribution and a generated distribution, and the $\ell_2$ loss between the LDCT image and the corresponding generated images (or denoised image). The computed generator reflects the prior belief about SDCT data distribution through training. We observed that the proposed method allows the preservation of fine anomalous features while eliminating noise. The experimental results show that the proposed deep-learning method with unpaired datasets performs comparably to a method using paired datasets. A clinical experiment was also performed to show the validity of the proposed method for noise arising in the low-dose X-ray CT.

Published
2019
Full Text
View/download PDF

7. Assessment of deep learning image reconstruction (DLIR) on image quality in pediatric cardiac CT datasets type of manuscript: Original research.

Author

Cho, Hyun-Hae, Lee, So Mi, and You, Sun Kyoung

Subjects
IMAGE reconstruction, COMPUTED tomography, DEEP learning, SIGNAL-to-noise ratio, ANGLES
Abstract

Bakground: To evaluate the quantitative and qualitative image quality using deep learning image reconstruction (DLIR) of pediatric cardiac computed tomography (CT) compared with conventional image reconstruction methods. Methods: Between January 2020 and December 2022, 109 pediatric cardiac CT scans were included in this study. The CT scans were reconstructed using an adaptive statistical iterative reconstruction-V (ASiR-V) with a blending factor of 80% and three levels of DLIR with TrueFidelity (low-, medium-, and high-strength settings). Quantitative image quality was measured using signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR). The edge rise distance (ERD) and angle between 25% and 75% of the line density profile were drawn to evaluate sharpness. Qualitative image quality was assessed using visual grading analysis scores. Results: A gradual improvement in the SNR and CNR was noted among the strength levels of the DLIR in sequence from low to high. Compared to ASiR-V, high-level DLIR showed significantly improved SNR and CNR (P<0.05). ERD decreased with increasing angle as the level of DLIR increased. Conclusion: High-level DLIR showed improved SNR and CNR compared to ASiR-V, with better sharpness on pediatric cardiac CT scans. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

34. Significance of sonographically detected bladder debris in children less than 2 years old with febrile urinary tract infection.

Author

You, Sun Kyoung, Lee, Jiwon M., Lee, Jeong‐Eun, Shin, Kyung Sook, Lee, So Mi, and Cho, Hyun‐Hae

Abstract

Purpose To investigate the relationship between bladder debris found on renal and bladder ultrasonography (RBUS) and the first febrile urinary tract infection (UTI) episode in children under 2 years old. Methods: We retrospectively reviewed the data of children aged <2 years with the first febrile UTI. We recorded bladder debris on RBUS and other findings (blood test, urinalysis, and urine culture). Other RBUS findings (renal pelvis debris, renal parenchymal change, wall thickening, and renal collecting system [RCS] dilatation) were recorded. Patients were divided into the debris (D) and non‐D groups. Results: Of 128 patients (boys: girls = 81:47, mean age = 5.6 ± 4.2 months), 24 (18.8%) had bladder debris. The mean C‐reactive protein (CRP) levels were higher in the D group (6.1 ± 4.0 vs 4.3 ± 3.5, P =.03). Twenty‐one patients in the D group (87.5%) had hematuria (odds ratio = 3.706, 95% confidence interval = 1.035‐13.267, P =.04). No significant differences were seen in the urine culture results between both groups. Significant associations were seen between bladder debris and other RBUS findings such as debris in renal pelvis, renal parenchymal change, and RCS wall thickening. Conclusion: Bladder debris on RBUS is a common finding in children aged <2 years during the first febrile UTI. Bladder debris was related to higher CRP levels, hematuria and sonographic findings, but not to urine culture results. [ABSTRACT FROM AUTHOR]

Published
2021
Full Text
View/download PDF

41. Optimal Timing of Spinal Ultrasound Evaluations for Sacral Dimples in Neonates: Earlier May Not Be Better.

Author

Cho, Hyun‐Hae, Lee, So Mi, and You, Sun Kyoung

Subjects
DIMPLES (Anatomy), NEWBORN infants, ULTRASONIC imaging, SPINAL cord, CAUDA equina
Abstract

Objectives: A spinal ultrasound (US) evaluation during the immediate postnatal period may have limited ability in evaluating filum thickness because of the spinal cord pulsation caused by a crowded subarachnoid space and the cerebrospinal fluid deficiency during this period. This study aimed to determine the optimal timing of spinal US to evaluate sacral dimples in neonates. Methods: This study included 585 neonates who had a clinically suspicious sacral dimple and underwent spinal US examinations between January 2015 and August 2017. Patients were classified into 1 of 2 groups based on whether measurements of all parameters were possible (group A) or not (group B). Neonatal and maternal clinical factors, including the antenatal history and US parameters, were compared between groups. Results: Group A included 443 patients, and group B included 82. Patients in group B were significantly younger (6.2 versus 31.0 days), had a younger corrective age (38.9 versus 42.5 weeks), and had a smaller body weight (3.1 versus 4.6 kg) than those in group A (all P < .005). However, no statistically significant differences were found in other patient or maternal factors (P > .05 for all). The pulsation of the conus medullaris and nerve roots of the cauda equina (14.6% versus 100%), thickening and echogenicity of the filum terminale (2.4% versus 100%), and the presence of a normal subarachnoid space (18.3% versus 100%) were significantly more difficult to detect in group B than in group A (all P < .001). Conclusions: For an accurate evaluation, which can reduce unnecessary confusion and costs, spinal US can be delayed until neonates grow beyond 31 days, with a corrected age of older than 42.5 weeks and body weight of greater than 4.6 kg. [ABSTRACT FROM AUTHOR]

Published
2019
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results