Seong Jae Hwang
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
Research Subjects
Seong Jae Hwang has a total of 79 co-authors. Here are the top co-authors by number of shared publications:
- Kyobin Choo
Yonsei University
6 shared publications - Chanyoung Kim
Yonsei University
5 shared publications - Jinyeong Kim
Yonsei University College of Medicine
4 shared publications - Woojung Han
Yonsei University
4 shared publications - Youngjun Jun
Yonsei University
4 shared publications - Dayun Ju
Yonsei University
3 shared publications
Latest Publications
- 3 October 2026
- Published by Springer Nature
- p. 425-443
Qwerty: Training-Free Motion Control via Query-Warped Video Diffusion Transformers
- 3 October 2026
- Published by Springer Nature
- p. 425-443
Qwerty: Training-Free Motion Control via Query-Warped Video Diffusion Transformers
- 26 September 2026
- Published by Springer Nature
- p. 98-108
Contrastive and Adaptive Multi-modal Masked Autoencoder for Spatial Transcriptomics
- 26 September 2026
- Published by Springer Nature
- p. 98-108
Contrastive and Adaptive Multi-modal Masked Autoencoder for Spatial Transcriptomics
- 25 September 2026
- Published by Springer Nature
- p. 14-23
Anatomically Consistent TMJ Disc Segmentation via Semantic Anchoring and Clinical Priors
- 25 September 2026
- Published by Springer Nature
- p. 14-23
Anatomically Consistent TMJ Disc Segmentation via Semantic Anchoring and Clinical Priors
- 17 September 2026
- Published by Springer Nature
- p. 240-257
Controlling Motion Transfer in Diffusion Transformers via Attention Heads
- 17 September 2026
- Published by Springer Nature
- p. 240-257
Controlling Motion Transfer in Diffusion Transformers via Attention Heads
- 11 September 2026
- Published by Springer Nature
- p. 582-599
Delaunay Canopy: Building Wireframe Reconstruction from Airborne LiDAR Point Clouds via Delaunay Graph
- 11 September 2026
- Published by Springer Nature
- p. 582-599
Delaunay Canopy: Building Wireframe Reconstruction from Airborne LiDAR Point Clouds via Delaunay Graph
- 21 September 2025
- Published by Springer Nature
- p. 523-533
PRETI: Patient-Aware Retinal Foundation Model via Metadata-Guided Representation Learning
- 21 September 2025
- Published by Springer Nature
- p. 523-533
PRETI: Patient-Aware Retinal Foundation Model via Metadata-Guided Representation Learning
- 20 September 2025
- Published by Springer Nature
- p. 397-407
Pathology-Aware Adaptive Watermarking for Text-Driven Medical Image Synthesis
- 20 September 2025
- Published by Springer Nature
- p. 397-407
Pathology-Aware Adaptive Watermarking for Text-Driven Medical Image Synthesis
- 20 September 2025
- Published by Springer Nature
- p. 433-443
Mono-Modalizing Extremely Heterogeneous Multi-modal Medical Image Registration
- 20 September 2025
- Published by Springer Nature
- p. 433-443
Mono-Modalizing Extremely Heterogeneous Multi-modal Medical Image Registration
- Open Access
PRETI: Patient-Aware Retinal Foundation Model via Metadata-Guided Representation Learning
Retinal foundation models have significantly advanced retinal image analysis by leveraging self-supervised learning to reduce dependence on labeled data while achieving strong generalization. Many recent approaches enhance retinal image understanding using report supervision, but obtaining clinical reports is often costly and challenging. In contrast, metadata (e.g., age, gender) is widely available and serves as a valuable resource for analyzing disease progression. To effectively incorporate patient-specific information, we propose PRETI, a retinal foundation model that integrates metadata-aware learning with robust self-supervised representation learning. We introduce Learnable Metadata Embedding (LME), which dynamically refines metadata representations. Additionally, we construct patient-level data pairs, associating images from the same individual to improve robustness against non-clinical variations. To further optimize retinal image representation, we propose Retina-Aware Adaptive Masking (RAAM), a strategy that selectively applies masking within the retinal region and dynamically adjusts the masking ratio during training. PRETI captures both global structures and fine-grained pathological details, resulting in superior diagnostic performance. Extensive experiments demonstrate that PRETI achieves state-of-the-art results across diverse diseases and biomarker predictions using in-house and public data, indicating the importance of metadata-guided foundation models in retinal disease analysis. Our code and pretrained model are available at https://github.com/MICV-yonsei/PRETI
Open AccessPRETI: Patient-Aware Retinal Foundation Model via Metadata-Guided Representation Learning
Retinal foundation models have significantly advanced retinal image analysis by leveraging self-supervised learning to reduce dependence on labeled data while achieving strong generalization. Many recent approaches enhance retinal image understanding using report supervision, but obtaining clinical reports is often costly and challenging. In contrast, metadata (e.g., age, gender) is widely available and serves as a valuable resource for analyzing disease progression. To effectively incorporate patient-specific information, we propose PRETI, a retinal foundation model that integrates metadata-aware learning with robust self-supervised representation learning. We introduce Learnable Metadata Embedding (LME), which dynamically refines metadata representations. Additionally, we construct patient-level data pairs, associating images from the same individual to improve robustness against non-clinical variations. To further optimize retinal image representation, we propose Retina-Aware Adaptive Masking (RAAM), a strategy that selectively applies masking within the retinal region and dynamically adjusts the masking ratio during training. PRETI captures both global structures and fine-grained pathological details, resulting in superior diagnostic performance. Extensive experiments demonstrate that PRETI achieves state-of-the-art results across diverse diseases and biomarker predictions using in-house and public data, indicating the importance of metadata-guided foundation models in retinal disease analysis. Our code and pretrained model are available at https://github.com/MICV-yonsei/PRETI
- Open Access
- 15 April 2025
- Published by Springer Nature in Scientific Reports
- Vol. 15  (1) , 13039
A prediction model of pediatric bone density from plain spine radiographs using deep learning
Osteoporosis, a bone disease characterized by decreased bone mineral density (BMD) resulting in decreased mechanical strength and an increased fracture risk, remains poorly understood in children. Herein, we developed/validated a deep learning-based model to predict pediatric BMD using plain spine radiographs. Using a two-stage model, Yolov8 was applied for vertebral body detection to predict BMD values using a regression model based on ResNet-18, from which a low-BMD group was classified based on Z-scores of predicted BMD. Patients aged 10-20-years who underwent dual-energy X-ray absorptiometry and radiography within 6 months at our hospital were enrolled. Ultimately, 601 patients (mean age, 14 years 4 months [SD 2 years]; 276 males) were included. The model achieved robust performance in detecting vertebral bodies (average precision [AP] 50 = 0.97, AP [50:95] = 0.68) and predicting BMD, with significant correlation (r = 0.72), showing consistency across different vertebral segments and agreement (intraclass correlation coefficient: 0.64). Moreover, it successfully classified low-BMD groups (area under the receiver operating characteristic curve = 0.85) with high sensitivity (0.76) and specificity (0.87). This deep-learning approach shows promise for BMD prediction and classification, with potential to enhance early detection and streamline bone health management in high-risk pediatric populations.
- 15 April 2025
- Published by Springer Nature in Scientific Reports
- Vol. 15  (1) , 13039
Open AccessA prediction model of pediatric bone density from plain spine radiographs using deep learning
Osteoporosis, a bone disease characterized by decreased bone mineral density (BMD) resulting in decreased mechanical strength and an increased fracture risk, remains poorly understood in children. Herein, we developed/validated a deep learning-based model to predict pediatric BMD using plain spine radiographs. Using a two-stage model, Yolov8 was applied for vertebral body detection to predict BMD values using a regression model based on ResNet-18, from which a low-BMD group was classified based on Z-scores of predicted BMD. Patients aged 10-20-years who underwent dual-energy X-ray absorptiometry and radiography within 6 months at our hospital were enrolled. Ultimately, 601 patients (mean age, 14 years 4 months [SD 2 years]; 276 males) were included. The model achieved robust performance in detecting vertebral bodies (average precision [AP] 50 = 0.97, AP [50:95] = 0.68) and predicting BMD, with significant correlation (r = 0.72), showing consistency across different vertebral segments and agreement (intraclass correlation coefficient: 0.64). Moreover, it successfully classified low-BMD groups (area under the receiver operating characteristic curve = 0.85) with high sensitivity (0.76) and specificity (0.87). This deep-learning approach shows promise for BMD prediction and classification, with potential to enhance early detection and streamline bone health management in high-risk pediatric populations.