In Kyu Lee
In Kyu Lee has a total of 31 co-authors. Here are the top co-authors by number of shared publications:
- Hyun-Woo Kim
Medipixel Inc Seoul Republic of Korea
4 shared publications - Jaesik Min
Medipixel, Inc
3 shared publications - Jonghoe Ku
Medipixel Inc Seoul Republic of Korea
3 shared publications - Sumin Seo
Medipixel, Inc
3 shared publications Bejal Kikani
2 shared publicationsChristopher E. Jensen
2 shared publications
Latest Publications
- Open Access
- 21 October 2026
- Published by Springer Nature in Communications Medicine
Disruption of marrow microenvironments in chronic lymphocytic leukemia by high-resolution synchrotron micro-computed tomography
Background: Chronic lymphocytic leukemia (CLL) is associated with increased fracture risk unexplained by standard bone density scans, suggesting underlying microstructural alterations. Whether leukemic infiltration disrupts the bone marrow microenvironment at the structural level remains poorly understood. Methods: We used high-resolution synchrotron micro-computed tomography (SR μ CT) on bone marrow biopsies from 17 CLL patients, stratified into low and high infiltration groups using objective, data-driven k-means clustering. Osteocyte lacunar density and intertrabecular marrow surface area-to-volume ratio (SA:V) were quantified using image processing and deep learning segmentation. Sensitivity analyses adjusting for prior therapy were performed using linear regression. Results: Here we show that high CLL marrow infiltration is associated with a 40.3% reduction in lacunar density and a 101% increase in normalized intertrabecular marrow SA:V, a metric reflecting greater structural fragmentation of the marrow compartment. Both changes correlate with leukemic infiltration percentage and show partial reversal after therapy in a longitudinal case. Conclusions: We identify a marrow remodeling phenotype in CLL characterized by osteocyte depletion and intertrabecular marrow disruption. These changes likely contribute to skeletal fragility and represent potential microstructural biomarkers for assessing marrow health more accurately than conventional imaging.
- 21 October 2026
- Published by Springer Nature in Communications Medicine
Open AccessDisruption of marrow microenvironments in chronic lymphocytic leukemia by high-resolution synchrotron micro-computed tomography
Background: Chronic lymphocytic leukemia (CLL) is associated with increased fracture risk unexplained by standard bone density scans, suggesting underlying microstructural alterations. Whether leukemic infiltration disrupts the bone marrow microenvironment at the structural level remains poorly understood. Methods: We used high-resolution synchrotron micro-computed tomography (SR μ CT) on bone marrow biopsies from 17 CLL patients, stratified into low and high infiltration groups using objective, data-driven k-means clustering. Osteocyte lacunar density and intertrabecular marrow surface area-to-volume ratio (SA:V) were quantified using image processing and deep learning segmentation. Sensitivity analyses adjusting for prior therapy were performed using linear regression. Results: Here we show that high CLL marrow infiltration is associated with a 40.3% reduction in lacunar density and a 101% increase in normalized intertrabecular marrow SA:V, a metric reflecting greater structural fragmentation of the marrow compartment. Both changes correlate with leukemic infiltration percentage and show partial reversal after therapy in a longitudinal case. Conclusions: We identify a marrow remodeling phenotype in CLL characterized by osteocyte depletion and intertrabecular marrow disruption. These changes likely contribute to skeletal fragility and represent potential microstructural biomarkers for assessing marrow health more accurately than conventional imaging.
- 25 September 2026
- Published by Springer Nature
- p. 3-12
Anatomy-Grounded Synthetic Coronary Angiography for Geometry-Informed Multi-view Matching
- 25 September 2026
- Published by Springer Nature
- p. 3-12
Anatomy-Grounded Synthetic Coronary Angiography for Geometry-Informed Multi-view Matching
- Open Access
Disruption of Marrow Microenvironments in Chronic Lymphocytic Leukemia by High-Resolution Synchrotron Micro-Computed Tomography
Chronic lymphocytic leukemia (CLL) is associated with increased fracture risk unexplained by standard bone density scans, suggesting underlying microstructural alterations. To investigate this, we used high-resolution synchrotron micro-computed tomography (SRµCT) on bone marrow biopsies from 17 CLL patients, who were stratified into low and high infiltration groups using objective, data-driven clustering. To our knowledge, this is the first report to quantify these changes. High CLL marrow infiltration was associated with a 40.3% reduction in lacuna density and a 101% increase in the normalized adipose surface area-to-volume ratio, a metric indicating greater structural fragmentation. Both changes correlated with leukemic infiltration percentage and showed partial reversal after therapy in a longitudinal case. Furthermore, high CLL burden significantly altered the morphological distributions of the remaining lacunar osteocyte (p < 0.001). We identify a novel marrow remodeling phenotype in CLL characterized by osteocyte depletion and adipose disruption. These changes likely contribute to skeletal fragility and represent potential microstructural biomarkers for assessing marrow health more accurately than conventional imaging.
Open AccessDisruption of Marrow Microenvironments in Chronic Lymphocytic Leukemia by High-Resolution Synchrotron Micro-Computed Tomography
Chronic lymphocytic leukemia (CLL) is associated with increased fracture risk unexplained by standard bone density scans, suggesting underlying microstructural alterations. To investigate this, we used high-resolution synchrotron micro-computed tomography (SRµCT) on bone marrow biopsies from 17 CLL patients, who were stratified into low and high infiltration groups using objective, data-driven clustering. To our knowledge, this is the first report to quantify these changes. High CLL marrow infiltration was associated with a 40.3% reduction in lacuna density and a 101% increase in the normalized adipose surface area-to-volume ratio, a metric indicating greater structural fragmentation. Both changes correlated with leukemic infiltration percentage and showed partial reversal after therapy in a longitudinal case. Furthermore, high CLL burden significantly altered the morphological distributions of the remaining lacunar osteocyte (p < 0.001). We identify a novel marrow remodeling phenotype in CLL characterized by osteocyte depletion and adipose disruption. These changes likely contribute to skeletal fragility and represent potential microstructural biomarkers for assessing marrow health more accurately than conventional imaging.
- 20 September 2025
- Published by Springer Nature
- p. 149-159
Diffusion-Based User-Guided Data Augmentation for Coronary Stenosis Detection
- 20 September 2025
- Published by Springer Nature
- p. 149-159
Diffusion-Based User-Guided Data Augmentation for Coronary Stenosis Detection
- Open Access
Diffusion-Based User-Guided Data Augmentation for Coronary Stenosis Detection
Coronary stenosis is a major risk factor for ischemic heart events leading to increased mortality, and medical treatments for this condition require meticulous, labor-intensive analysis. Coronary angiography provides critical visual cues for assessing stenosis, supporting clinicians in making informed decisions for diagnosis and treatment. Recent advances in deep learning have shown great potential for automated localization and severity measurement of stenosis. In real-world scenarios, however, the success of these competent approaches is often hindered by challenges such as limited labeled data and class imbalance. In this study, we propose a novel data augmentation approach that uses an inpainting method based on a diffusion model to generate realistic lesions, allowing user-guided control of severity. Extensive evaluation on lesion detection and severity classification across various synthetic dataset sizes shows superior performance of our method on both a large-scale in-house dataset and a public coronary angiography dataset. Furthermore, our approach maintains high detection and classification performance even when trained with limited data, highlighting its clinical importance in improving the assessment of severity of stenosis and optimizing data utilization for more reliable decision support.
Open AccessDiffusion-Based User-Guided Data Augmentation for Coronary Stenosis Detection
Coronary stenosis is a major risk factor for ischemic heart events leading to increased mortality, and medical treatments for this condition require meticulous, labor-intensive analysis. Coronary angiography provides critical visual cues for assessing stenosis, supporting clinicians in making informed decisions for diagnosis and treatment. Recent advances in deep learning have shown great potential for automated localization and severity measurement of stenosis. In real-world scenarios, however, the success of these competent approaches is often hindered by challenges such as limited labeled data and class imbalance. In this study, we propose a novel data augmentation approach that uses an inpainting method based on a diffusion model to generate realistic lesions, allowing user-guided control of severity. Extensive evaluation on lesion detection and severity classification across various synthetic dataset sizes shows superior performance of our method on both a large-scale in-house dataset and a public coronary angiography dataset. Furthermore, our approach maintains high detection and classification performance even when trained with limited data, highlighting its clinical importance in improving the assessment of severity of stenosis and optimizing data utilization for more reliable decision support.
- 19 February 2025
- Published by Springer Nature
- p. 232-245
Gray’s Anatomy for Segment Anything Model: Optimizing Grayscale Medical Images for Fast and Lightweight Segmentation
- 19 February 2025
- Published by Springer Nature
- p. 232-245
Gray’s Anatomy for Segment Anything Model: Optimizing Grayscale Medical Images for Fast and Lightweight Segmentation
- Open Access
MPSeg : Multi-Phase strategy for coronary artery Segmentation
Accurate segmentation of coronary arteries is a pivotal process in assessing cardiovascular diseases. However, the intricate structure of the cardiovascular system presents significant challenges for automatic segmentation, especially when utilizing methodologies like the SYNTAX Score, which relies extensively on detailed structural information for precise risk stratification. To address these difficulties and cater to this need, we present MPSeg, an innovative multi-phase strategy designed for coronary artery segmentation. Our approach specifically accommodates these structural complexities and adheres to the principles of the SYNTAX Score. Initially, our method segregates vessels into two categories based on their unique morphological characteristics: Left Coronary Artery (LCA) and Right Coronary Artery (RCA). Specialized ensemble models are then deployed for each category to execute the challenging segmentation task. Due to LCA's higher complexity over RCA, a refinement model is utilized to scrutinize and correct initial class predictions on segmented areas. Notably, our approach demonstrated exceptional effectiveness when evaluated in the Automatic Region-based Coronary Artery Disease diagnostics using x-ray angiography imagEs (ARCADE) Segmentation Detection Algorithm challenge at MICCAI 2023.
Open AccessMPSeg : Multi-Phase strategy for coronary artery Segmentation
Accurate segmentation of coronary arteries is a pivotal process in assessing cardiovascular diseases. However, the intricate structure of the cardiovascular system presents significant challenges for automatic segmentation, especially when utilizing methodologies like the SYNTAX Score, which relies extensively on detailed structural information for precise risk stratification. To address these difficulties and cater to this need, we present MPSeg, an innovative multi-phase strategy designed for coronary artery segmentation. Our approach specifically accommodates these structural complexities and adheres to the principles of the SYNTAX Score. Initially, our method segregates vessels into two categories based on their unique morphological characteristics: Left Coronary Artery (LCA) and Right Coronary Artery (RCA). Specialized ensemble models are then deployed for each category to execute the challenging segmentation task. Due to LCA's higher complexity over RCA, a refinement model is utilized to scrutinize and correct initial class predictions on segmented areas. Notably, our approach demonstrated exceptional effectiveness when evaluated in the Automatic Region-based Coronary Artery Disease diagnostics using x-ray angiography imagEs (ARCADE) Segmentation Detection Algorithm challenge at MICCAI 2023.
- Open Access
SSASS: Semi-Supervised Approach for Stenosis Segmentation
Coronary artery stenosis is a critical health risk, and its precise identification in Coronary Angiography (CAG) can significantly aid medical practitioners in accurately evaluating the severity of a patient's condition. The complexity of coronary artery structures combined with the inherent noise in X-ray images poses a considerable challenge to this task. To tackle these obstacles, we introduce a semi-supervised approach for cardiovascular stenosis segmentation. Our strategy begins with data augmentation, specifically tailored to replicate the structural characteristics of coronary arteries. We then apply a pseudo-label-based semi-supervised learning technique that leverages the data generated through our augmentation process. Impressively, our approach demonstrated an exceptional performance in the Automatic Region-based Coronary Artery Disease diagnostics using x-ray angiography imagEs (ARCADE) Stenosis Detection Algorithm challenge by utilizing a single model instead of relying on an ensemble of multiple models. This success emphasizes our method's capability and efficiency in providing an automated solution for accurately assessing stenosis severity from medical imaging data.
Open AccessSSASS: Semi-Supervised Approach for Stenosis Segmentation
Coronary artery stenosis is a critical health risk, and its precise identification in Coronary Angiography (CAG) can significantly aid medical practitioners in accurately evaluating the severity of a patient's condition. The complexity of coronary artery structures combined with the inherent noise in X-ray images poses a considerable challenge to this task. To tackle these obstacles, we introduce a semi-supervised approach for cardiovascular stenosis segmentation. Our strategy begins with data augmentation, specifically tailored to replicate the structural characteristics of coronary arteries. We then apply a pseudo-label-based semi-supervised learning technique that leverages the data generated through our augmentation process. Impressively, our approach demonstrated an exceptional performance in the Automatic Region-based Coronary Artery Disease diagnostics using x-ray angiography imagEs (ARCADE) Stenosis Detection Algorithm challenge by utilizing a single model instead of relying on an ensemble of multiple models. This success emphasizes our method's capability and efficiency in providing an automated solution for accurately assessing stenosis severity from medical imaging data.
- Open Access
- 30 March 2018
- Published by The Society of Korean Medicine in Journal of Korean Medicine
- Vol. 39 (1) , 75-85
Case Report on Long Term Survival of Glioblastoma Patient Treated with Integrative Medicine
- 30 March 2018
- Published by The Society of Korean Medicine in Journal of Korean Medicine
- Vol. 39 (1) , 75-85
Open AccessCase Report on Long Term Survival of Glioblastoma Patient Treated with Integrative Medicine