Bo-Kyung Je
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Bo-Kyung Je has a total of 95 co-authors. Here are the top co-authors by number of shared publications:
- Gayoung Choi
Department of Radiology, Korea University Ansan Hospital, Ansan, Korea, Republic of
6 shared publications Gayoung Choi
4 shared publicationsSeung Hwa Lee
Seon Jung Oh, Bo-Kyung Je, Seung Hwa Lee, Doran Hong, Department of Radiology, Korea University Hospital, Gyeonggi 15355, South Korea
4 shared publicationsSung-Bum Kim
Seon Jung Oh, Bo-Kyung Je, Seung Hwa Lee, Doran Hong, Department of Radiology, Korea University Hospital, Gyeonggi 15355, South Korea
4 shared publicationsBaek Hyun Kim
Department of Radiology, Korea University College of Medicine, Ansan Hospital, Ansan, Korea
3 shared publications- Byung Min Choi
Department of Pediatrics, Korea University College of Medicine, Seoul, Republic of Korea
3 shared publications
Latest Publications
- 22 October 2026
- Published by Springer Nature in Abdominal Radiology
- p. 1-9
CT assessment of colonic laterality in situs inversus and situs ambiguus: a multicenter retrospective study
Purpose To characterize proximal and distal colonic laterality and appendiceal-base location on CT in patients with situs inversus and situs ambiguus. Methods This retrospective multicenter study included 79 patients identified from abdominal CT reports at three tertiary hospitals between December 2003 and March 2025 (70 with situs inversus; 9 with situs ambiguus). A radiologist assessed thoracoabdominal organ arrangement, proximal and distal colonic laterality, combined proximal-distal colonic laterality pattern, and appendiceal-base location. The end of the cecum was used when the appendiceal base was not visible. Distributions of colonic laterality between the two situs types were compared using exact tests. Results In situs inversus, the proximal colon was left-sided in 66/70 patients (94.3%; 95% CI, 86.2–97.8), the distal colon was right-sided in 67/70 (95.7%; 95% CI, 88.1–98.5), and a left-proximal/right-distal combined colonic pattern occurred in 64/70 (91.4%; 95% CI, 82.5–96.0). The appendiceal base or cecal surrogate was in the left lower quadrant in 61/70 (87.1%; 95% CI, 77.3–93.1). In situs ambiguus, the proximal colon was midline-crossing in 7/9 patients (77.8%; 95% CI, 45.3–93.7), and the distal colon was left-sided in 6/9 (66.7%; 95% CI, 35.4–87.9). Locations of the appendiceal base or cecal surrogate were distributed across all abdominal regions. Distributions of segmental and combined colonic laterality differed between situs inversus and situs ambiguus (all exact p < .001). Conclusion Situs inversus usually shows mirror-image colonic laterality and a left-lower-quadrant appendiceal base, but exceptions occur. In this cohort, situs ambiguus showed greater variability. Colonic laterality and appendiceal-base location should be directly assessed on CT rather than inferred from situs classification alone.
- 22 October 2026
- Published by Springer Nature in Abdominal Radiology
- p. 1-9
CT assessment of colonic laterality in situs inversus and situs ambiguus: a multicenter retrospective study
Purpose To characterize proximal and distal colonic laterality and appendiceal-base location on CT in patients with situs inversus and situs ambiguus. Methods This retrospective multicenter study included 79 patients identified from abdominal CT reports at three tertiary hospitals between December 2003 and March 2025 (70 with situs inversus; 9 with situs ambiguus). A radiologist assessed thoracoabdominal organ arrangement, proximal and distal colonic laterality, combined proximal-distal colonic laterality pattern, and appendiceal-base location. The end of the cecum was used when the appendiceal base was not visible. Distributions of colonic laterality between the two situs types were compared using exact tests. Results In situs inversus, the proximal colon was left-sided in 66/70 patients (94.3%; 95% CI, 86.2–97.8), the distal colon was right-sided in 67/70 (95.7%; 95% CI, 88.1–98.5), and a left-proximal/right-distal combined colonic pattern occurred in 64/70 (91.4%; 95% CI, 82.5–96.0). The appendiceal base or cecal surrogate was in the left lower quadrant in 61/70 (87.1%; 95% CI, 77.3–93.1). In situs ambiguus, the proximal colon was midline-crossing in 7/9 patients (77.8%; 95% CI, 45.3–93.7), and the distal colon was left-sided in 6/9 (66.7%; 95% CI, 35.4–87.9). Locations of the appendiceal base or cecal surrogate were distributed across all abdominal regions. Distributions of segmental and combined colonic laterality differed between situs inversus and situs ambiguus (all exact p < .001). Conclusion Situs inversus usually shows mirror-image colonic laterality and a left-lower-quadrant appendiceal base, but exceptions occur. In this cohort, situs ambiguus showed greater variability. Colonic laterality and appendiceal-base location should be directly assessed on CT rather than inferred from situs classification alone.
- Open Access
- 17 March 2026
- Published by Springer Nature in Scientific Reports
- Vol. 16
AI-powered ultrasound radiofrequency analysis for non-invasive pediatric liver fat quantification
Metabolic dysfunction-Associated Steatotic Liver Disease (MASLD) affects 30–50% of obese children, yet accurate non-invasive quantification remains challenging. While magnetic resonance imaging-proton density fat fraction (MRI-PDFF) represents the reference standard, its limited accessibility necessitates alternative approaches. Forty pediatric patients (age 12.16 ± 2.56 years) referred for MASLD were prospectively enrolled for same-day ultrasound radiofrequency (RF) data acquisition and MRI-PDFF examination. Two artificial intelligence (AI) approaches using multiple input combinations of RF data, ultrasound-guided attenuation parameters (UGAP), and clinical parameters were developed for non-invasive pediatric liver fat quantification: radiomics-based models and deep learning models. The best radiomics model (XGBoost) and the best deep learning model (Mod-MHDNet) achieved optimal performance with multimodal inputs (R2 = 0.81 and 0.76, respectively). Bland–Altman analysis demonstrated excellent agreement with MRI-PDFF, with a mean bias of < 0.4% points for both approaches. AI analysis of ultrasound RF data enables accurate and accessible quantification of pediatric liver fat, offering a practical alternative for MASLD evaluation.
- 17 March 2026
- Published by Springer Nature in Scientific Reports
- Vol. 16
Open AccessAI-powered ultrasound radiofrequency analysis for non-invasive pediatric liver fat quantification
Metabolic dysfunction-Associated Steatotic Liver Disease (MASLD) affects 30–50% of obese children, yet accurate non-invasive quantification remains challenging. While magnetic resonance imaging-proton density fat fraction (MRI-PDFF) represents the reference standard, its limited accessibility necessitates alternative approaches. Forty pediatric patients (age 12.16 ± 2.56 years) referred for MASLD were prospectively enrolled for same-day ultrasound radiofrequency (RF) data acquisition and MRI-PDFF examination. Two artificial intelligence (AI) approaches using multiple input combinations of RF data, ultrasound-guided attenuation parameters (UGAP), and clinical parameters were developed for non-invasive pediatric liver fat quantification: radiomics-based models and deep learning models. The best radiomics model (XGBoost) and the best deep learning model (Mod-MHDNet) achieved optimal performance with multimodal inputs (R2 = 0.81 and 0.76, respectively). Bland–Altman analysis demonstrated excellent agreement with MRI-PDFF, with a mean bias of < 0.4% points for both approaches. AI analysis of ultrasound RF data enables accurate and accessible quantification of pediatric liver fat, offering a practical alternative for MASLD evaluation.
- Open Access
- 1 January 2026
- Published by XMLink in Journal of the Korean Society of Radiology
- Vol. 87 (3) , 391
Preface for Special Issue on ‘Pediatric Head and Neck Imaging’
제보경, et al. J Korean Soc Radiol. 2026 May;87(3):391. https://doi.org/10.3348/jksr.2026.0040
- 1 January 2026
- Published by XMLink in Journal of the Korean Society of Radiology
- Vol. 87 (3) , 391
Open AccessPreface for Special Issue on ‘Pediatric Head and Neck Imaging’
제보경, et al. J Korean Soc Radiol. 2026 May;87(3):391. https://doi.org/10.3348/jksr.2026.0040
- Open Access
- 1 January 2026
- Published by XMLink in Journal of the Korean Society of Radiology
- Vol. 87 (3) , 416-434
Imaging for Pediatric Head and Neck Emergencies: Critical Insights
최가영, et al. J Korean Soc Radiol. 2026 May;87(3):416-434. https://doi.org/10.3348/jksr.2026.0019
- 1 January 2026
- Published by XMLink in Journal of the Korean Society of Radiology
- Vol. 87 (3) , 416-434
Open AccessImaging for Pediatric Head and Neck Emergencies: Critical Insights
최가영, et al. J Korean Soc Radiol. 2026 May;87(3):416-434. https://doi.org/10.3348/jksr.2026.0019
- Open Access
- 4 January 2025
- Published by Springer Nature in Pediatric Radiology
- Vol. 55 (2) , 324-333
Cerebellar hemorrhage in neonates: pattern analysis by ultrasonography and magnetic resonance imaging
Background: Cerebellar hemorrhage in neonates is increasingly being identified but is still underdiagnosed. While magnetic resonance imaging (MRI) is the optimal imaging modality for cerebellar hemorrhage evaluation, ultrasonography (US) is commonly used for screening. Characterizing the patterns and distribution of cerebellar hemorrhage lesions can help facilitate its detection by aiding to focus on prevailing type of cerebellar hemorrhage. Objective: This study aimed to analyze the patterns of cerebellar hemorrhage in neonates, comparing US findings with MRI. Materials and methods: This was a retrospective study of 765 neonatal intensive care unit (NICU)-admitted neonates who underwent brain MRI due to various clinical and radiological requirements. Two pediatric radiologists reviewed brain MRI and US in consensus, and cerebellar hemorrhage patterns were classified based on MRI findings: type 1, punctate cerebellar hemorrhage without cerebellar volume loss; type 2, focal cerebellar hemorrhage with cerebellar volume loss; type 3, ovoid/crescent cerebellar hemorrhage in the periphery of the cerebellar hemisphere; type 4, isolated vermian cerebellar hemorrhage; type 5, cerebellar hemorrhage involving almost the entire cerebellar hemisphere. The distribution and US detection rates of cerebellar hemorrhage were compared according to the cerebellar hemorrhage type. Results: A total of 56 (33 male, 23 female) cases (7.32%) among 765 MRIs showed cerebellar hemorrhage (median gestational age, 27 + 1 weeks [IQR 5 + 2]; median birth weight, 955 g [IQR 882.5]). The most common pattern was type 1 (60.7%). Type 3 cerebellar hemorrhage was more commonly observed in the inferior and peripheral cerebellum compared to types 1 and 2 cerebellar hemorrhage (P=0.002). In retrospective review of images, type 3 was the most commonly missed type of cerebellar hemorrhage (initial US detection rate, 33.3%; retrospective US detection rate, 75%). Conclusion: This study underscores the importance of understanding cerebellar hemorrhage patterns and suggests that careful inspection of inferior and periphery of the cerebellum is important to avoid missed diagnosis of cerebellar hemorrhage. Graphical
- 4 January 2025
- Published by Springer Nature in Pediatric Radiology
- Vol. 55 (2) , 324-333
Open AccessCerebellar hemorrhage in neonates: pattern analysis by ultrasonography and magnetic resonance imaging
Background: Cerebellar hemorrhage in neonates is increasingly being identified but is still underdiagnosed. While magnetic resonance imaging (MRI) is the optimal imaging modality for cerebellar hemorrhage evaluation, ultrasonography (US) is commonly used for screening. Characterizing the patterns and distribution of cerebellar hemorrhage lesions can help facilitate its detection by aiding to focus on prevailing type of cerebellar hemorrhage. Objective: This study aimed to analyze the patterns of cerebellar hemorrhage in neonates, comparing US findings with MRI. Materials and methods: This was a retrospective study of 765 neonatal intensive care unit (NICU)-admitted neonates who underwent brain MRI due to various clinical and radiological requirements. Two pediatric radiologists reviewed brain MRI and US in consensus, and cerebellar hemorrhage patterns were classified based on MRI findings: type 1, punctate cerebellar hemorrhage without cerebellar volume loss; type 2, focal cerebellar hemorrhage with cerebellar volume loss; type 3, ovoid/crescent cerebellar hemorrhage in the periphery of the cerebellar hemisphere; type 4, isolated vermian cerebellar hemorrhage; type 5, cerebellar hemorrhage involving almost the entire cerebellar hemisphere. The distribution and US detection rates of cerebellar hemorrhage were compared according to the cerebellar hemorrhage type. Results: A total of 56 (33 male, 23 female) cases (7.32%) among 765 MRIs showed cerebellar hemorrhage (median gestational age, 27 + 1 weeks [IQR 5 + 2]; median birth weight, 955 g [IQR 882.5]). The most common pattern was type 1 (60.7%). Type 3 cerebellar hemorrhage was more commonly observed in the inferior and peripheral cerebellum compared to types 1 and 2 cerebellar hemorrhage (P=0.002). In retrospective review of images, type 3 was the most commonly missed type of cerebellar hemorrhage (initial US detection rate, 33.3%; retrospective US detection rate, 75%). Conclusion: This study underscores the importance of understanding cerebellar hemorrhage patterns and suggests that careful inspection of inferior and periphery of the cerebellum is important to avoid missed diagnosis of cerebellar hemorrhage. Graphical
- Open Access
- 1 January 2025
- Published by XMLink in Korean Journal of Radiology
- Vol. 26 (9) , 867-876
Development of a Deep-Learning Model for Estimating Newborn Gestational Age via Lumbar Vertebral Segmentation on Plain Radiography
Ham S, et al. Korean J Radiol. 2025 Sep;26(9):867-876. https://doi.org/10.3348/kjr.2025.0172
- 1 January 2025
- Published by XMLink in Korean Journal of Radiology
- Vol. 26 (9) , 867-876
Open AccessDevelopment of a Deep-Learning Model for Estimating Newborn Gestational Age via Lumbar Vertebral Segmentation on Plain Radiography
Ham S, et al. Korean J Radiol. 2025 Sep;26(9):867-876. https://doi.org/10.3348/kjr.2025.0172
- 27 April 2024
- Published by Springer Nature in European Radiology
- Vol. 34 (10) , 6396-6406
Olecranon bone age assessment in puberty using a lateral elbow radiograph and a deep-learning model
Objectives To improve pubertal bone age (BA) evaluation by developing a precise and practical elbow BA classification using the olecranon, and a deep-learning AI model. Materials and methods Lateral elbow radiographs taken for BA evaluation in children under 18 years were collected from January 2020 to June 2022, retrospectively. A novel classification and the olecranon BA were established based on the morphological changes in the olecranon ossification process during puberty. The olecranon BA was compared with other elbow and hand BA methods, using intraclass correlation coefficients (ICCs), and a deep-learning AI model was developed. Results A total of 3508 lateral elbow radiographs (mean age 9.8 ± 1.8 years) were collected. The olecranon BA showed the highest applicability (100%) and interobserver agreement (ICC 0.993) among elbow BA methods. It showed excellent reliability with Sauvegrain (0.967 in girls, 0.969 in boys) and Dimeglio (0.978 in girls, 0.978 in boys) elbow BA methods, as well as Korean standard (KS) hand BA in boys (0.917), and good reliability with KS in girls (0.896) and Greulich–Pyle (GP)/Tanner–Whitehouse (TW)3 (0.835 in girls, 0.895 in boys) hand BA methods. The AI model for olecranon BA showed an accuracy of 0.96 and a specificity of 0.98 with EfficientDet-b4. External validation showed an accuracy of 0.86 and a specificity of 0.91. Conclusion The olecranon BA evaluation for puberty, requiring only a lateral elbow radiograph, showed the highest applicability and interobserver agreement, and excellent reliability with other BA evaluation methods, along with a high performance of the AI model. Clinical relevance statement This AI model uses a single lateral elbow radiograph to determine bone age for puberty from the olecranon ossification center and can improve pubertal bone age assessment with the highest applicability and excellent reliability compared to previous methods. Key Points Elbow bone age is valuable for pubertal bone age assessment, but conventional methods have limitations. Olecranon bone age and its AI model showed high performances for pubertal bone age assessment. Olecranon bone age system is practical and accurate while requiring only a single lateral elbow radiograph.
- 27 April 2024
- Published by Springer Nature in European Radiology
- Vol. 34 (10) , 6396-6406
Olecranon bone age assessment in puberty using a lateral elbow radiograph and a deep-learning model
Objectives To improve pubertal bone age (BA) evaluation by developing a precise and practical elbow BA classification using the olecranon, and a deep-learning AI model. Materials and methods Lateral elbow radiographs taken for BA evaluation in children under 18 years were collected from January 2020 to June 2022, retrospectively. A novel classification and the olecranon BA were established based on the morphological changes in the olecranon ossification process during puberty. The olecranon BA was compared with other elbow and hand BA methods, using intraclass correlation coefficients (ICCs), and a deep-learning AI model was developed. Results A total of 3508 lateral elbow radiographs (mean age 9.8 ± 1.8 years) were collected. The olecranon BA showed the highest applicability (100%) and interobserver agreement (ICC 0.993) among elbow BA methods. It showed excellent reliability with Sauvegrain (0.967 in girls, 0.969 in boys) and Dimeglio (0.978 in girls, 0.978 in boys) elbow BA methods, as well as Korean standard (KS) hand BA in boys (0.917), and good reliability with KS in girls (0.896) and Greulich–Pyle (GP)/Tanner–Whitehouse (TW)3 (0.835 in girls, 0.895 in boys) hand BA methods. The AI model for olecranon BA showed an accuracy of 0.96 and a specificity of 0.98 with EfficientDet-b4. External validation showed an accuracy of 0.86 and a specificity of 0.91. Conclusion The olecranon BA evaluation for puberty, requiring only a lateral elbow radiograph, showed the highest applicability and interobserver agreement, and excellent reliability with other BA evaluation methods, along with a high performance of the AI model. Clinical relevance statement This AI model uses a single lateral elbow radiograph to determine bone age for puberty from the olecranon ossification center and can improve pubertal bone age assessment with the highest applicability and excellent reliability compared to previous methods. Key Points Elbow bone age is valuable for pubertal bone age assessment, but conventional methods have limitations. Olecranon bone age and its AI model showed high performances for pubertal bone age assessment. Olecranon bone age system is practical and accurate while requiring only a single lateral elbow radiograph.
- Open Access
- 1 May 2023
- Published by Korean Neurosurgical Society in Journal of Korean Neurosurgical Society
- Vol. 66 (3) , 316-323
Morbidity and Mortality Trends in Preterm Infants of <32 Weeks Gestational Age with Severe Intraventricular Hemorrhage : A 14-Year Single-Center Retrospective Study
Objective : Owing to advances in critical care treatment, the overall survival rate of preterm infants born at a gestational age (GA) <32 weeks has consistently improved. However, the incidence of severe intraventricular hemorrhage (IVH) has persisted, and there are few reports on in-hospital morbidity and mortality. Therefore, the aim of the present study was to investigate trends surrounding in-hospital morbidity and mortality of preterm infants with severe IVH over a 14-year period.Methods : This single-center retrospective study included 620 infants born at a GA 7 days after birth) for infants with severe IVH significantly improved over time, decreasing from 39.1% in phase I to 14.3% in phase II (p=0.043). A history of hypotension treated with vasoactive medication within 1 week after birth (adjusted odds ratio, 7.39; p=0.025) was found to be an independent risk factor for mortality. When comparing major morbidities of surviving infants, those in phase II were significantly more likely to have undergone surgery for necrotizing enterocolitis (NEC) (29.2% vs. 0.0%; p=0.027). Additionally, rates of late-onset sepsis (45.8% vs. 14.3%; p=0.049) and central nervous system infection (25.0% vs. 0.0%; p=0.049) were significantly higher in phase II survivors than in phase I survivors.Conclusion : In-hospital mortality in preterm infants with severe IVH decreased over the last decade, whereas major neonatal morbidities increased, particularly surgical NEC and sepsis. This study suggests the importance of multidisciplinary specialized medical and surgical neonatal intensive care in preterm infants with severe IVH.
- 1 May 2023
- Published by Korean Neurosurgical Society in Journal of Korean Neurosurgical Society
- Vol. 66 (3) , 316-323
Open AccessMorbidity and Mortality Trends in Preterm Infants of <32 Weeks Gestational Age with Severe Intraventricular Hemorrhage : A 14-Year Single-Center Retrospective Study
Objective : Owing to advances in critical care treatment, the overall survival rate of preterm infants born at a gestational age (GA) <32 weeks has consistently improved. However, the incidence of severe intraventricular hemorrhage (IVH) has persisted, and there are few reports on in-hospital morbidity and mortality. Therefore, the aim of the present study was to investigate trends surrounding in-hospital morbidity and mortality of preterm infants with severe IVH over a 14-year period.Methods : This single-center retrospective study included 620 infants born at a GA 7 days after birth) for infants with severe IVH significantly improved over time, decreasing from 39.1% in phase I to 14.3% in phase II (p=0.043). A history of hypotension treated with vasoactive medication within 1 week after birth (adjusted odds ratio, 7.39; p=0.025) was found to be an independent risk factor for mortality. When comparing major morbidities of surviving infants, those in phase II were significantly more likely to have undergone surgery for necrotizing enterocolitis (NEC) (29.2% vs. 0.0%; p=0.027). Additionally, rates of late-onset sepsis (45.8% vs. 14.3%; p=0.049) and central nervous system infection (25.0% vs. 0.0%; p=0.049) were significantly higher in phase II survivors than in phase I survivors.Conclusion : In-hospital mortality in preterm infants with severe IVH decreased over the last decade, whereas major neonatal morbidities increased, particularly surgical NEC and sepsis. This study suggests the importance of multidisciplinary specialized medical and surgical neonatal intensive care in preterm infants with severe IVH.
- Open Access
- 24 February 2022
- Published by The Korean Society of Radiology in Journal of the Korean Society of Radiology
- Vol. 83 (2) , 304-316
The Effect of COVID–19 on Pediatric Intussusception: A Retrospective Study of a Single Center in South Korea with 10–Year Experience
유여진, et al. J Korean Soc Radiol. 2022 Feb;83:e29. https://doi.org/10.3348/jksr.2021.0089
- 24 February 2022
- Published by The Korean Society of Radiology in Journal of the Korean Society of Radiology
- Vol. 83 (2) , 304-316
Open AccessThe Effect of COVID–19 on Pediatric Intussusception: A Retrospective Study of a Single Center in South Korea with 10–Year Experience
유여진, et al. J Korean Soc Radiol. 2022 Feb;83:e29. https://doi.org/10.3348/jksr.2021.0089