Gaeun Lee
Research Subjects
Gaeun Lee has a total of 27 co-authors. Here are the top co-authors by number of shared publications:
- June-Goo Lee
Department of Biomedical Engineering, Asan Medical Center, University of Ulsan College of Medicine, Seoul 05505, Republic of Korea
3 shared publications - Bumsoo Park
Department of Neurosurgery, Bon Hospital, Daejeon 34188, Republic of Korea
1 shared publication - Deok Kim
Department of Neurosurgery, Ajou University College of Medicine, Suwon 16499, Republic of Korea
1 shared publication - Dong Hyun Yang
Department of Radiology and Research Institute of Radiology, University of Ulsan College of Medicine, Asan Medical Center, Seoul, Republic of Korea
1 shared publication - Gyu-Jun Jeong
Department of Biomedical Engineering, AMIST, Asan Medical Center, University of Ulsan College of Medicine, Seoul, South Korea
1 shared publication - Hyun Jung Koo
Department of Radiology and Research Institute of Radiology, University of Ulsan College of Medicine, Asan Medical Center, Seoul, Korea
1 shared publication
Latest Publications
- Open Access
- 11 May 2024
- Published by MDPI AG in Bioengineering
- Vol. 11 (5) , 481
Deep Learning Method for Precise Landmark Identification and Structural Assessment of Whole-Spine Radiographs
This study measured parameters automatically by marking the point for measuring each parameter on whole-spine radiographs. Between January 2020 and December 2021, 1017 sequential lateral whole-spine radiographs were retrospectively obtained. Of these, 819 and 198 were used for training and testing the performance of the landmark detection model, respectively. To objectively evaluate the program’s performance, 690 whole-spine radiographs from four other institutions were used for external validation. The combined dataset comprised radiographs from 857 female and 850 male patients (average age 42.2 ± 27.3 years; range 20–85 years). The landmark localizer showed the highest accuracy in identifying cervical landmarks (median error 1.5–2.4 mm), followed by lumbosacral landmarks (median error 2.1–3.0 mm). However, thoracic landmarks displayed larger localization errors (median 2.4–4.3 mm), indicating slightly reduced precision compared with the cervical and lumbosacral regions. The agreement between the deep learning model and two experts was good to excellent, with intraclass correlation coefficient values >0.88. The deep learning model also performed well on the external validation set. There were no statistical differences between datasets in all parameters, suggesting that the performance of the artificial intelligence model created was excellent. The proposed automatic alignment analysis system identified anatomical landmarks and positions of the spine with high precision and generated various radiograph imaging parameters that had a good correlation with manual measurements.
- 11 May 2024
- Published by MDPI AG in Bioengineering
- Vol. 11 (5) , 481
Open AccessDeep Learning Method for Precise Landmark Identification and Structural Assessment of Whole-Spine Radiographs
This study measured parameters automatically by marking the point for measuring each parameter on whole-spine radiographs. Between January 2020 and December 2021, 1017 sequential lateral whole-spine radiographs were retrospectively obtained. Of these, 819 and 198 were used for training and testing the performance of the landmark detection model, respectively. To objectively evaluate the program’s performance, 690 whole-spine radiographs from four other institutions were used for external validation. The combined dataset comprised radiographs from 857 female and 850 male patients (average age 42.2 ± 27.3 years; range 20–85 years). The landmark localizer showed the highest accuracy in identifying cervical landmarks (median error 1.5–2.4 mm), followed by lumbosacral landmarks (median error 2.1–3.0 mm). However, thoracic landmarks displayed larger localization errors (median 2.4–4.3 mm), indicating slightly reduced precision compared with the cervical and lumbosacral regions. The agreement between the deep learning model and two experts was good to excellent, with intraclass correlation coefficient values >0.88. The deep learning model also performed well on the external validation set. There were no statistical differences between datasets in all parameters, suggesting that the performance of the artificial intelligence model created was excellent. The proposed automatic alignment analysis system identified anatomical landmarks and positions of the spine with high precision and generated various radiograph imaging parameters that had a good correlation with manual measurements.
- Open Access
- 1 January 2024
- Published by XMLink in Korean Circulation Journal
- Vol. 54 (1) , 30-39
Deep Learning-Based Lumen and Vessel Segmentation of Intravascular Ultrasound Images in Coronary Artery Disease
Jeong GJ, et al. Korean Circ J. 2024 Jan;54(1):30-39. https://doi.org/10.4070/kcj.2023.0166
- 1 January 2024
- Published by XMLink in Korean Circulation Journal
- Vol. 54 (1) , 30-39
Open AccessDeep Learning-Based Lumen and Vessel Segmentation of Intravascular Ultrasound Images in Coronary Artery Disease
Jeong GJ, et al. Korean Circ J. 2024 Jan;54(1):30-39. https://doi.org/10.4070/kcj.2023.0166
- Open Access
- 1 January 2020
- Published by XMLink in Korean Journal of Radiology
- Vol. 21 (6) , 660-669
Automated Segmentation of Left Ventricular Myocardium on Cardiac Computed Tomography Using Deep Learning
Koo HJ, et al. Korean J Radiol. 2020 Feb;21:e64. https://doi.org/10.3348/kjr.2019.0378
- 1 January 2020
- Published by XMLink in Korean Journal of Radiology
- Vol. 21 (6) , 660-669
Open AccessAutomated Segmentation of Left Ventricular Myocardium on Cardiac Computed Tomography Using Deep Learning
Koo HJ, et al. Korean J Radiol. 2020 Feb;21:e64. https://doi.org/10.3348/kjr.2019.0378
- Top Cited Papers
- 1 August 2019
- Published by Radiological Society of North America (RSNA) in Radiology
- Vol. 292 (2) , 365-373
Deep Learning–based Image Conversion of CT Reconstruction Kernels Improves Radiomics Reproducibility for Pulmonary Nodules or Masses
CT image conversion using a convolutional neural network can reduce the effect of different reconstruction kernels on radiomic parameters. This will facilitate comparison of image features derived ... Background Intratumor heterogeneity in lung cancer may influence outcomes. CT radiomics seeks to assess tumor features to provide detailed imaging features. However, CT radiomic features vary accor...
- 1 August 2019
- Published by Radiological Society of North America (RSNA) in Radiology
- Vol. 292 (2) , 365-373
Top Cited PapersDeep Learning–based Image Conversion of CT Reconstruction Kernels Improves Radiomics Reproducibility for Pulmonary Nodules or Masses
CT image conversion using a convolutional neural network can reduce the effect of different reconstruction kernels on radiomic parameters. This will facilitate comparison of image features derived ... Background Intratumor heterogeneity in lung cancer may influence outcomes. CT radiomics seeks to assess tumor features to provide detailed imaging features. However, CT radiomic features vary accor...