JCJae Won Choi

Jae Won Choi

*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


Jae Won Choi has a total of 208 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Deep Learning–based Bone Mineral Density Prediction Using Pediatric Chest Radiographs: A Multicenter Feasibility Study

    by Jae Won Choi, Young Jin Ryu, Jung-Eun Cheon, Young Hun Choi, Jae-Yeon Hwang, Seunghyun Lee, Yeon Jin Cho, Seok Young Koh, Yun Jeong Lee, Young Ah Lee, et al.

    An artificial intelligence model using pediatric chest radiographs accurately detected low bone mineral density ( Z score ≤ −2.0) in internal and external test sets.

  • Open Access

    Advances in automated fetal brain MRI segmentation and biometry: Insights from the FeTA 2024 challenge

    by Vladyslav Zalevskyi, Thomas Sanchez, Misha Kaandorp, Margaux Roulet, Diego Fajardo-Rojas, Liu Li, Jana Hutter, Hongwei Bran Li, Matthew J. Barkovich, Hui Ji, et al.


  • Open Access

    Diffusion-Weighted Imaging With Deep Learning Reconstruction in the Pediatric Brain: Comparison With Multi-Shot Diffusion-Weighted Imaging

    by Ha Young Yang, Jae-Yeon Hwang, Jae Won Choi, Yeon Jin Cho, Seunghyun Lee, Jung-Eun Cheon, Young Hun Choi

    Yang HY, et al. Investig Magn Reson Imaging. 2026 Sep;30(3):194-203. https://doi.org/10.13104/imri.2026.0018

  • Open Access

    Deep learning-enhanced zero echo time silent brain magnetic resonance imaging in infants without sedation

    by Chanyoung Rhee, Jae-Yeon Hwang, Jae Won Choi, Yeon Jin Cho, Seunghyun Lee, Jung-Eun Cheon, Young Hun Choi

    Background: Reducing acoustic noise is essential in infant brain magnetic resonance imaging (MRI) to minimize the need for sedation. Deep learning (DL)–based MRI reconstruction may enhance the image quality of the zero echo time (ZTE) silent sequence. Objective: To evaluate the effect of DL-based reconstruction on the image quality of ZTE infant brain MRI using the feed-and-wrap technique, compared to conventional MRI with sedation. Materials and methods: This retrospective study included 78 infants (postmenstrual age ≤16 months) who underwent brain MRI between January 2022 and December 2024. The control group underwent sedated 3-dimensional T1-weighted magnetization-prepared rapid gradient-echo (MPRAGE) imaging. The experimental group underwent unsedated inversion recovery-prepared ZTE imaging with and without DL-based reconstruction (ZTE-DL and ZTE, respectively), using the feed-and-wrap technique. Three radiologists independently rated five image quality metrics using a 5-point Likert scale. Signal uniformity was assessed by the coefficient of variation across eight brain regions. Differences among sequences were analyzed using the Mann–Whitney U test with Bonferroni correction. Interrater agreement was assessed using Cohen’s kappa coefficient. Results: ZTE-DL had the highest scores for noisiness, gray-white matter differentiation, artifacts, and overall image quality. ZTE-DL showed no significant differences from MPRAGE except for reduced noisiness, while significantly outperforming ZTE across all metrics (all P 0.6) for most metrics. Signal uniformity was greatest in ZTE-DL for gray and white matter (all P P =0.721). Conclusion: DL-based MRI reconstruction improved ZTE image quality and provided comparable image quality to MPRAGE, potentially reducing the need for sedation in infant brain MRI. Graphical


  • Development and validation of a deep learning-based algorithm for quantifying bronchiolitis obliterans in paediatric computed tomography

    by Chanyoung Rhee, Jae-Yeon Hwang, Ji Young Ha, Jae Won Choi, Yeon Jin Cho, Seunghyun Lee, Jung-Eun Cheon, Dong In Suh, Young Hun Choi

    Objectives: To develop and validate a deep learning-based algorithm for quantifying bronchiolitis obliterans (BO) on paediatric chest CT. Methods: This retrospective study included 86 children (39 males; median age, 10 years) diagnosed with BO who underwent both inspiratory and expiratory CT between January 2018 and November 2021. The deep learning-based BO quantification model was trained on 26 CT scans using a 3D nnU-Net, with radiologist-segmented low attenuation regions (LARs) serving as ground truth. Model performance was evaluated through internal test with 4 CT scans and external test with 6 CT scans. Intra-vendor robustness was assessed using 22 CT scans with varying reconstruction methods, kernel types, and slice thicknesses. Comparison with semiquantitative radiologist grading was performed using 28 CT scans. Dice similarity coefficient (DSC), sensitivity, and precision were used to evaluate model performance. Results: The model achieved a DSC of 85.41 ± 3.28%, sensitivity of 85.14 ± 7.66%, and precision of 86.21 ± 3.92% in the internal test, and 82.53 ± 4.34%, 82.17 ± 6.15%, and 84.15 ± 3.16% in the external test, respectively. For intra-vendor robustness, no significant differences in BO quantification were observed across different reconstruction methods, kernel types, and slice thicknesses (all P > .05). Compared to radiologists’ grading, the model demonstrated strong to very strong correlations across all lung lobes (all P < .001). Conclusion: The model demonstrated accurate quantification of BO on paediatric CT, with good agreement with the radiologist-segmented ground truth. Advances in knowledge: This study presents a 3D nnU-Net-based deep learning algorithm for robust quantification of BO on paediatric CT, providing reproducible measurements of LARs.

  • Accelerated brain magnetic resonance imaging with deep learning reconstruction: a comparative study on image quality in pediatric neuroimaging

    by Jae Won Choi, Yeon Jin Cho, Seul Bi Lee, Seunghyun Lee, Jae-Yeon Hwang, Young Hun Choi, Jung-Eun Cheon, Joonsung Lee

    Background Magnetic resonance imaging (MRI) is crucial in pediatric radiology; however, the prolonged scan time is a major drawback that often requires sedation. Deep learning reconstruction (DLR) is a promising method for accelerating MRI acquisition. Objective To evaluate the clinical feasibility of accelerated brain MRI with DLR in pediatric neuroimaging, focusing on image quality compared to conventional MRI. Materials and methods In this retrospective study, 116 pediatric participants (mean age 7.9 ± 5.4 years) underwent routine brain MRI with three reconstruction methods: conventional MRI without DLR (C-MRI), conventional MRI with DLR (DLC-MRI), and accelerated MRI with DLR (DLA-MRI). Two pediatric radiologists independently assessed the overall image quality, sharpness, artifacts, noise, and lesion conspicuity. Quantitative image analysis included the measurement of image noise and coefficient of variation (CoV). Results DLA-MRI reduced the scan time by 43% compared with C-MRI. Compared with C-MRI, DLA-MRI demonstrated higher scores for overall image quality, noise, and artifacts, as well as similar or higher scores for lesion conspicuity, but similar or lower scores for sharpness. DLC-MRI demonstrated the highest scores for all the parameters. Despite variations in image quality and lesion conspicuity, the lesion detection rates were 100% across all three reconstructions. Quantitative analysis revealed lower noise and CoV for DLA-MRI than those for C-MRI. Interobserver agreement was substantial to almost perfect (weighted Cohen’s kappa = 0.72–0.97). Conclusion DLR enabled faster MRI with improved image quality compared with conventional MRI, highlighting its potential to address prolonged MRI scan times in pediatric neuroimaging and optimize clinical workflows. Graphical Abstract


  • Open Access

    Advances in Automated Fetal Brain MRI Segmentation and Biometry: Insights from the FeTA 2024 Challenge

    by Vladyslav Zalevskyi, Thomas Sanchez, Misha Kaandorp, Margaux Roulet, Diego Fajardo-Rojas, Liu Li, Jana Hutter, Hongwei Bran Li, Matthew Barkovich, Hui Ji, et al.

    Accurate fetal brain tissue segmentation and biometric analysis are essential for studying brain development in utero. The FeTA Challenge 2024 advanced automated fetal brain MRI analysis by introducing biometry prediction as a new task alongside tissue segmentation. For the first time, our diverse multi-centric test set included data from a new low-field (0.55T) MRI dataset. Evaluation metrics were also expanded to include the topology-specific Euler characteristic difference (ED). Sixteen teams submitted segmentation methods, most of which performed consistently across both high- and low-field scans. However, longitudinal trends indicate that segmentation accuracy may be reaching a plateau, with results now approaching inter-rater variability. The ED metric uncovered topological differences that were missed by conventional metrics, while the low-field dataset achieved the highest segmentation scores, highlighting the potential of affordable imaging systems when paired with high-quality reconstruction. Seven teams participated in the biometry task, but most methods failed to outperform a simple baseline that predicted measurements based solely on gestational age, underscoring the challenge of extracting reliable biometric estimates from image data alone. Domain shift analysis identified image quality as the most significant factor affecting model generalization, with super-resolution pipelines also playing a substantial role. Other factors, such as gestational age, pathology, and acquisition site, had smaller, though still measurable, effects. Overall, FeTA 2024 offers a comprehensive benchmark for multi-class segmentation and biometry estimation in fetal brain MRI, underscoring the need for data-centric approaches, improved topological evaluation, and greater dataset diversity to enable clinically robust and generalizable AI tools.


  • Open Access

    Retrospective Clinical Trial to Evaluate the Effectiveness of a New Tanner–Whitehouse-Based Bone Age Assessment Algorithm Trained with a Deep Neural Network System

    by Meesun Lee, Young-Hun Choi, Seul-Bi Lee, Jae-Won Choi, Seunghyun Lee, Jae-Yeon Hwang, Jung-Eun Cheon, SungHyuk Hong, Jeonghoon Kim, Yeon-Jin Cho

    Background/Objectives: To develop an automated deep learning-based bone age prediction model using the Tanner–Whitehouse (TW3) method and evaluate its feasibility by comparing its performance with that of pediatric radiologists. Methods: The hand and wrist radiographs of 560 Korean children and adolescents (280 female, 280 male, mean age 9.43 ± 2.92 years) were evaluated using the TW3-based model and three pediatric radiologists. Images with bony destruction, congenital anomalies, or non-diagnostic quality were excluded. A commercialized AI solution built upon the Rotated Single Shot MultiBox Detector (SSD) and EfficientNet-B0 was used. Bone age measurements from the model and radiologists were compared using the paired t-tests. Linear regression analysis was performed and the coefficient of determination (r²), mean absolute error (MAE), and root mean square error (RMSE) were measured. A Bland–Altman analysis was conducted and the proportion of bone age predictions within 0.6 years of the radiologists’ assessments was calculated. Results: The TW3-based model demonstrated no significant differences between bone age measurements and radiologists, except for participants 13 years old (overall, p = 0.874; 6–8 years, p = 0.737; 8–9 years, p = 0.093; 9–10 years, p = 0.301; 10–11 years, p = 0.584; 11–13 years, p = 0.976; 13 years, p < 0.001). There was a strong linear correlation between the model prediction and radiologist assessments (r2 = 0.977). The RMSE and MAE values of the model were 0.529 (95% CI, 0.482–0.575) and 0.388 (95% CI, 0.361–0.417) years. Overall, 82.3% of bone age model predictions were within 0.6 years of the radiologists’ interpretation. Conclusions: Automated deep learning-based bone age assessment has the potential to reduce radiologists’ workload and provide standardized measurements for clinical decision making.


  • Open Access

    Ultrafast MRI for Pediatric Brain Assessment in Routine Clinical Practice

    by Hee Eun Moon, Ji Young Ha, Jae Won Choi, Seung Hyun Lee, Jae-Yeon Hwang, Young Hun Choi, Jung-Eun Cheon, Yeon Jin Cho

    Moon HE, et al. Korean J Radiol. 2025 Jan;26(1):75-87. https://doi.org/10.3348/kjr.2024.0725


  • Open Access

    Enhancing Radiomics Reproducibility: Deep Learning-Based Harmonization of Abdominal Computed Tomography (CT) Images

    by Seul Bi Lee, Youngtaek Hong, Yeon Jin Cho, Dawun Jeong, Jina Lee, Jae Won Choi, Jae Yeon Hwang, Seunghyun Lee, Young Hun Choi, Jung-Eun Cheon

    We assessed the feasibility of using deep learning-based image harmonization to improve the reproducibility of radiomics features in abdominal CT scans. In CT imaging, harmonization adjusts images from different institutions to ensure consistency despite variations in scanners and acquisition protocols. This process is essential because such differences can lead to variability in radiomics features, affecting reproducibility and accuracy. Harmonizing images minimizes these inconsistencies, supporting more reliable and clinically applicable results across diverse settings. A pre-trained harmonization algorithm was applied to 63 dual-energy abdominal CT images, which were reconstructed into four different types, and 10 regions of interest (ROIs) were analyzed. From the original 455 radiomics features per ROI, 387 were used after excluding redundant features. Reproducibility was measured using the intraclass correlation coefficient (ICC), with a threshold of ICC ≥ 0.85 indicating acceptable reproducibility. The region-based analysis revealed significant improvements in reproducibility post-harmonization, especially in vessel features, which increased from 14% to 69%. Other regions, including the spleen, kidney, muscle, and liver parenchyma, also saw notable improvements, although air reproducibility slightly decreased from 95% to 94%, impacting only a few features. In patient-based analysis, reproducible features increased from 18% to 65%, with an average of 179 additional reproducible features per patient after harmonization. These results demonstrate that deep learning-based harmonization can significantly enhance the reproducibility of radiomics features in abdominal CT, offering promising potential for advancing radiomics development and its clinical applications.