SBSun-Young Baek

Sun-Young Baek

*This is an algorithmically generated author record based on publicly available information.

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


Sun-Young Baek has a total of 86 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Comparison of Diagnostic Performance Between Standard Susceptibility Map‐Weighted Imaging and Susceptibility Map‐Weighted Imaging Reconstructed From Clinical SWI and Neuromelanin MRI in Early Parkinson's Disease

    by Seon Lee, Yongsik Sim, Jinyoung Youn, Eung Yeop Kim, Seung Hwan Moon, Sun‐Young Baek, Beomseok Sohn

    Background: Susceptibility map‐weighted imaging (SMwI) provides high accuracy for early Parkinson's disease (ePD) by enhancing nigral hyperintensity. However, standard SMwI requires dedicated acquisition; reconstruction from routinely acquired sequences may offer a practical alternative. Purpose: To compare the diagnostic performance of standard SMwI with SWI‐ and neuromelanin (NM)‐driven SMwI for differentiating ePD from disease controls (DC). Study Type: Retrospective. Subjects: One hundred and eighty‐seven drug‐naïve ePD (age: 67.5 ± 9.4 years, 102 male) and 43 DC (age: 67.1 ± 9.2 years, 12 male). Field Strength/Sequence: 3 T, multi‐echo gradient‐echo (GRE) for standard SMwI; GRE‐based NM imaging: multi‐echo GRE for SWI. Assessment: Nigral hyperintensity was assessed by three neuroradiologists (4‐, 2‐, and 1‐year experience). Diagnostic performance was evaluated using clinical diagnosis for all subjects and PET for 106 subjects (98 ePD, 8 DC). PET‐based assessment included side‐based analyses accounting for PET laterality and patient‐based analyses regardless of direction. Statistical Tests: Sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), accuracy and area under the curve (AUC) were assessed using clinical diagnosis as reference; sensitivity, specificity, and accuracy using PET. Significance was set at p < 0.05. Results: Using clinical diagnosis as reference, standard SMwI showed highest diagnostic performance (sensitivity 0.856; specificity 1.000; PPV 1.000; AUC 0.928). SWI‐driven SMwI maintained similar sensitivity ( p = 0.355) but showed significantly reduced specificity, PPV, accuracy, AUC. In the PET subgroup, side‐ and patient‐based analyses showed no differences in sensitivity ( p = 0.261, p = 0.670), specificity ( p = 1.000, p = 1.000) and accuracy ( p = 0.268, p = 0.695) between standard and SWI‐driven SMwI. Data Conclusion: SWI‐driven SMwI approached the diagnostic performance of standard SMwI with PET reference but showed inferior performance with clinical diagnosis, suggesting a fallback option when dedicated SMwI is unavailable. Evidence Level: 3. Technical Efficacy: Stage 1.


  • Open Access

    Association of Breast Tissue Composition on Preoperative Automated Breast Ultrasound With Accuracy of Cancer Multiplicity Evaluation and Recurrence-Free Survival in Patients With Early-Stage Breast Cancer

    by Myoung Kyoung Kim, Haejung Kim, Sun-Young Baek, Eun Young Ko, Boo-Kyung Han, Eun Sook Ko, Jeongmin Lee, Nami Choi, Jin Chung, Ji Soo Choi

    To investigate whether breast tissue composition on preoperative automated breast ultrasound (ABUS) is associated with the accuracy of cancer multiplicity evaluation and postoperative recurrence-free survival (RFS) in patients with early-stage breast cancer. This retrospective analysis included women with early-stage breast cancer (clinical Tis, T1–2/N0) who underwent ABUS and digital mammography (DM) between October 2019 and April 2021. Tissue composition on ABUS was assessed using the Breast Imaging Reporting and Data System background echotexture (BE) (homogeneous-fat, homogeneous-fibroglandular, or heterogeneous). In a subgroup of patients with mammographically dense breasts, the glandular tissue component (GTC) on ABUS were further stratified into high (moderate or marked) or low (minimal or mild). Multivariable logistic and Cox regression analyses were used to identify factors associated with accurate cancer multiplicity categorization (unifocal, multifocal/multicentric, or bilateral) using ABUS + DM, and with RFS, respectively. Among 409 women (mean age ± standard deviation, 50.2 ± 8.7 years), ABUS combined with DM yielded accurate cancer multiplicity categorization in 368 patients (90.0%). Neither BE nor GTC on ABUS affected the accuracy of categorization when ABUS was combined with DM. Over a median postoperative follow-up of 3.5 years, 11 recurrences occurred. Heterogeneous BE on ABUS (hazard ratio [HR] 11.24 [95% confidence interval [CI]: 2.82–44.92]; P = 0.001), BRCA mutation (HR 15.94 [2.47–102.97]; P = 0.004), and pathologic index cancer size (HR per 1-cm increase 1.91 [1.13–3.23]; P = 0.02) was independently associated with RFS. In patients with dense breasts, heterogeneous BE (HR 14.17 [95% CI: 2.69–74.60]; P = 0.002) and high GTC (HR 10.32 [2.35–45.28]; P = 0.002) on ABUS, BRCA mutation (HR 24.34 [2.75–215.06]; P = 0.004), and pathologic cancer size (HR per 1-cm increase 2.62 [1.50–4.59]; P = 0.001) was independently associated with RFS. In patients with early-stage breast cancer, heterogeneous BE and high GTC on preoperative ABUS, along with larger cancer size and BRCA mutation, was associated with worse RFS. However, BE and GTC did not affect cancer multiplicity evaluation when ABUS was used in combination with DM.


  • Open Access

    Effect of Deep Learning-Based Artificial Intelligence on Radiologists’ Performance in Identifying Nigrosome 1 Abnormalities on Susceptibility Map-Weighted Imaging

    by Jiyeon Park, Chae Young Lim, So Yeon Won, Han Kyu Na, Phil Hyu Lee, Sun-Young Baek, Yun Hwa Roh, Minjung Seong, Yongsik Sim, Eung Yeop Kim, et al.

    Park J, et al. Korean J Radiol. 2025 Aug;26(8):771-781. https://doi.org/10.3348/kjr.2025.0208


  • Open Access

    Posterior subependymal germinal matrix hemorrhage as a mild form of hemorrhage in extremely preterm infants: neurodevelopmental outcomes at corrected ages of 18-24 months

    by Jae Mo Koo, So-Young Yoo, Ji Hye Kim, Ji Eun Park, Sun-Young Baek, Tae Yeon Jeon

    Purpose: This study aimed to explore the effects of both the presence and size of posterior subependymal germinal matrix hemorrhage (PS-GMH), considered a mild form of hemorrhage, on the neurodevelopmental outcomes of extremely preterm infants.Methods: A retrospective analysis was conducted on 221 extremely preterm infants, assessing their initial and term-equivalent age (TEA) cranial ultrasound (cUS) examinations from 2016 to 2021. Infants were classified based on the presence and size (small/large) of PS-GMH. Neurodevelopmental outcomes at corrected ages of 18-24 months were analyzed in 135 infants.Results: PS-GMH was identified in 86.9% (192/221) of the infants, with 13.5% (26/192) exhibiting large PS-GMH. Among the 135 infants who were followed up, those with PS-GMH were found to have younger gestational ages (P<0.001) and a higher incidence of maternal chorioamnionitis (P=0.016) than those without PS-GMH. Significant differences were observed in the incidence of grade II intraventricular hemorrhage (IVH) on initial cUS (P=0.003) and ventriculomegaly at TEA cUS (P=0.026) across the groups with no PS-GMH, small PS-GMH, and large PS-GMH. The large PS-GMH group exhibited a higher occurrence of grade II IVH than the small PS-GMH group (P=0.006). However, ventriculomegaly incidence did not significantly vary with PS-GMH status. Neurodevelopmental outcomes were also not significantly different across PS-GMH statuses. The adjusted odds ratios for any neurodevelopmental impairment, compared to the no PS-GMH group, were 1.70 (95% confidence interval [CI], 0.40 to 7.26; P=0.471) for all PS-GMH, 1.61 (95% CI, 0.37 to 6.93; P=0.526) for small PS-GMH, and 3.84 (95% CI, 0.62 to 24.00; P=0.150) for large PS-GMH.Conclusion: PS-GMH was frequently observed in extremely preterm infants; however, it did not independently predict adverse neurodevelopmental outcomes.


  • Real-world application of a 3D deep learning model for detecting and localizing cerebral microbleeds

    by So Yeon Won, Jun-Ho Kim, Changsoo Woo, Dong-Hyun Kim, Keun Young Park, Eung Yeop Kim, Sun-Young Baek, Hyun Jin Han, Beomseok Sohn

    Background Detection and localization of cerebral microbleeds (CMBs) is crucial for disease diagnosis and treatment planning. However, CMB detection is labor-intensive, time-consuming, and challenging owing to its visual similarity to mimics. This study aimed to validate the performance of a three-dimensional (3D) deep learning model that not only detects CMBs but also identifies their anatomic location in real-world settings. Methods A total of 21 patients with 116 CMBs and 12 without CMBs were visited in the neurosurgery outpatient department between January 2023 and October 2023. Three readers, including a board-certified neuroradiologist (reader 1), a resident in radiology (reader 2), and a neurosurgeon (reader 3) independently reviewed SWIs of 33 patients to detect CMBs and categorized their locations into lobar, deep, and infratentorial regions without any AI assistance. After a one-month washout period, the same datasets were redistributed randomly, and readers reviewed them again with the assistance of the 3D deep learning model. A comparison of the diagnostic performance between readers with and without AI assistance was performed. Results All readers with an AI assistant (reader 1:0.991 [0.930–0.999], reader 2:0.922 [0.881–0.905], and reader 3:0.966 [0.928–0.984]) tended to have higher sensitivity per lesion than readers only (reader 1:0.905 [0.849–0.942], reader 2:0.621 [0.541–0.694], and reader 3:0.871 [0.759–0.935], p = 0.132, 0.017, and 0.227, respectively). In particular, radiology residents (reader 2) showed a statistically significant increase in sensitivity per lesion when using AI. There was no statistically significant difference in the number of FPs per patient for all readers with AI assistant (reader 1: 0.394 [0.152–1.021], reader 2: 0.727 [0.334–1.582], reader 3: 0.182 [0.077–0.429]) and reader only (reader 1: 0.364 [0.159–0.831], reader 2: 0.576 [0.240–1.382], reader 3: 0.121 [0.038–0.383], p = 0.853, 0.251, and 0.157, respectively). Our model accurately categorized the anatomical location of all CMBs. Conclusions Our model demonstrated promising potential for the detection and anatomical localization of CMBs, although further research with a larger and more diverse population is necessary to establish clinical utility in real-world settings.


  • Open Access

    The Impact of an Antimicrobial Stewardship Program on Days of Therapy in the Pediatric Center: An Interrupted Time-Series Analysis of a 19-Year Study

    by Kyung-Ran Kim, Hyo Jung Park, Sun-Young Baek, Soo-Han Choi, Byung-Kee Lee, SooJin Kim, Jong Min Kim, Ji-Man Kang, Sun-Ja Kim, Sae Rom Choi, et al.

    Kim KR, et al. J Korean Med Sci. 2024 May;39:e172. https://doi.org/10.3346/jkms.2024.39.e172


  • Open Access

    Dietary Diversity during Early Infancy Increases Microbial Diversity and Prevents Egg Allergy in High-Risk Infants

    by Bo Ra Lee, Hye-In Jung, Su Kyung Kim, Mijeong Kwon, Hyunmi Kim, Minyoung Jung, Yechan Kyung, Byung Eui Kim, Suk-Joo Choi, Soo-Young Oh, et al.

    Lee BR, et al. Immune Netw. 2021 Nov;22(2):e17. https://doi.org/10.4110/in.2022.22.e17


  • Open Access

    Seasonal and monthly variation in peak expiratory flow rate in children with asthma

    by Minji Kim, Young-Min Kim, Ji Young Lee, Hea-Kyoung Yang, Hyunmi Kim, Soohyun Ahn, Sun-Young Baek, Jihyun Kim, Kangmo Ahn

    Kim M, et al. Asia Pac Allergy. 2021 Apr;11(2):e19. https://doi.org/10.5415/apallergy.2021.11.e19


  • Open Access

    Adjustment of azathioprine dose should be based on a lower 6‐TGN target level to avoid leucopenia in NUDT15 intermediate metabolisers

    by Ben Kang, Tae Jun Kim, Jaeyoung Choi, Sun‐Young Baek, Soohyun Ahn, Rihwa Choi, Soo‐Youn Lee, Yon Ho Choe

    Summary: Background: The association between NUDT15 polymorphisms and thiopurine‐induced leucopenia is well known.Aim: To investigate the association between NUDT15 polymorphisms and time‐to‐leucopenia in paediatric patients with inflammatory bowel disease (IBD) receiving azathioprine and to determine the relationship between NUDT15 polymorphisms and 6‐thioguanine nucleotide (6‐TGN) levels.Methods: This retrospective observational study included Korean paediatric patients with IBD who were treated with azathioprine and underwent NUDT15 and TPMT genotyping. Azathioprine doses were adjusted by regular thiopurine metabolite monitoring. Factors associated with time‐to‐leucopenia and the relationship between NUDT15 polymorphisms and 6‐TGN levels were analysed.Results: Among the 167 patients included, leucopenia was observed in 16% (19/119), 44% (20/45) and 100% (3/3) of the NUDT15 normal, intermediate and poor metabolisers respectively (P < 0.001). NUDT15 polymorphism was significantly associated with time‐to‐leucopenia (HR = 5.26, 95% CI = 2.74‐10.09, P < 0.001). There was a positive association between 6‐TGN levels and leucopenia among the NUDT15 intermediate/TPMT normal metabolisers (median 361.3 vs 263.8 pmol/8 × 108 RBC, P = 0.013). The most accurate 6‐TGN cut‐off level associated with leucopenia was 308.2 pmol/8 × 108 RBC (AUC = 0.742, 95% CI = 0.569‐0.915, sensitivity 80.0%, specificity 72.7%, P < 0.001) in this subgroup. When the specificity was set to 8 RBC (sensitivity 93.3%, specificity 13.6%).Conclusions: NUDT15 polymorphisms were associated with time‐to‐leucopenia during azathioprine treatment in Korean paediatric patients with IBD. In order to reduce the development of thiopurine‐induced leucopenia (8 RBC).