Choul Woo Shin
Choul Woo Shin has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Ilwoong Choi
DRTECH Corp., Research & Development Center, Seongnam, Republic of Korea
2 shared publications - Chang Min Park
Department of Radiology, Seoul National University Hospital, Seoul, Korea
1 shared publication - Jihang Kim
Department of Radiology, Seoul National University Bundang Hospital, Seongnam, Republic of Korea
1 shared publication - Jong-Hyuk Lee
Department of Radiology, Seoul National University Hospital, Seoul National University College of Medicine, Seoul 03080, Republic of Korea
1 shared publication - Junghoon Kim
Department of Radiology, Seoul National University Bundang Hospital, Seongnam-si 13620, Republic of Korea
1 shared publication - Seoyoung Lee
KAIST
1 shared publication
Latest Publications
- 12 June 2025
- Published by SPIE-Intl Soc Optical Eng in Journal of Medical Imaging
- Vol. 12 (S2) , 1-18
Asymmetric scatter kernel estimation neural network for digital breast tomosynthesis
PurposeVarious deep learning (DL) approaches have been developed for estimating scatter radiation in digital breast tomosynthesis (DBT). Existing DL methods generally employ an end-to-end training approach, overlooking the underlying physics of scatter formation. We propose a deep learning approach inspired by asymmetric scatter kernel superposition to estimate scatter in DBT.ApproachWe use the network to generate the scatter amplitude distribution as well as the scatter kernel width and asymmetric factor map. To account for variations in local breast thickness and shape in DBT projection data, we integrated the Euclidean distance map and projection angle information into the network design for estimating the asymmetric factor.ResultsSystematic experiments on numerical phantom data and physical experimental data demonstrated the outperformance of the proposed approach to UNet-based end-to-end scatter estimation and symmetric kernel-based approaches in terms of signal-to-noise ratio and structure similarity index measure of the resulting scatter corrected images.ConclusionsThe proposed method is believed to have achieved significant advancement in scatter estimation of DBT projections, allowing a robust and reliable physics-informed scatter correction.
- 12 June 2025
- Published by SPIE-Intl Soc Optical Eng in Journal of Medical Imaging
- Vol. 12 (S2) , 1-18
Asymmetric scatter kernel estimation neural network for digital breast tomosynthesis
PurposeVarious deep learning (DL) approaches have been developed for estimating scatter radiation in digital breast tomosynthesis (DBT). Existing DL methods generally employ an end-to-end training approach, overlooking the underlying physics of scatter formation. We propose a deep learning approach inspired by asymmetric scatter kernel superposition to estimate scatter in DBT.ApproachWe use the network to generate the scatter amplitude distribution as well as the scatter kernel width and asymmetric factor map. To account for variations in local breast thickness and shape in DBT projection data, we integrated the Euclidean distance map and projection angle information into the network design for estimating the asymmetric factor.ResultsSystematic experiments on numerical phantom data and physical experimental data demonstrated the outperformance of the proposed approach to UNet-based end-to-end scatter estimation and symmetric kernel-based approaches in terms of signal-to-noise ratio and structure similarity index measure of the resulting scatter corrected images.ConclusionsThe proposed method is believed to have achieved significant advancement in scatter estimation of DBT projections, allowing a robust and reliable physics-informed scatter correction.
- Open Access
- 19 March 2025
- Published by MDPI AG in Journal of Clinical Medicine
- Vol. 14 (6) , 2091
Improving Image Quality of Chest Radiography with Artificial Intelligence-Supported Dual-Energy X-Ray Imaging System: An Observer Preference Study in Healthy Volunteers
Background/Objectives: To compare the image quality of chest radiography with a dual-energy X-ray imaging system using AI technology (DE-AI) to that of conventional chest radiography with a standard protocol. Methods: In this prospective study, 52 healthy volunteers underwent dual-energy chest radiography. Images were obtained using two exposures at 60 kVp and 120 kVp, separated by a 150 ms interval. Four images were generated for each participant: a conventional image, an enhanced standard image, a soft-tissue-selective image, and a bone-selective image. A machine learning model optimized the cancellation parameters for generating soft-tissue and bone-selective images. To enhance image quality, motion artifacts were minimized using Laplacian pyramid diffeomorphic registration, while a wavelet directional cycle-consistent adversarial network (WavCycleGAN) reduced image noise. Four radiologists independently evaluated the visibility of thirteen anatomical regions (eight soft-tissue regions and five bone regions) and the overall image with a five-point scale of preference. Pooled mean values were calculated for each anatomic region through meta-analysis using a random-effects model. Results: Radiologists preferred DE-AI images to conventional chest radiographs in various anatomic regions. The enhanced standard image showed superior quality in 9 of 13 anatomic regions. Preference for the soft-tissue-selective image was statistically significant for three of eight anatomic regions. Preference for the bone-selective image was statistically significant for four of five anatomic regions. Conclusions: Images produced by DE-AI provide better visualization of thoracic structures.
- 19 March 2025
- Published by MDPI AG in Journal of Clinical Medicine
- Vol. 14 (6) , 2091
Open AccessImproving Image Quality of Chest Radiography with Artificial Intelligence-Supported Dual-Energy X-Ray Imaging System: An Observer Preference Study in Healthy Volunteers
Background/Objectives: To compare the image quality of chest radiography with a dual-energy X-ray imaging system using AI technology (DE-AI) to that of conventional chest radiography with a standard protocol. Methods: In this prospective study, 52 healthy volunteers underwent dual-energy chest radiography. Images were obtained using two exposures at 60 kVp and 120 kVp, separated by a 150 ms interval. Four images were generated for each participant: a conventional image, an enhanced standard image, a soft-tissue-selective image, and a bone-selective image. A machine learning model optimized the cancellation parameters for generating soft-tissue and bone-selective images. To enhance image quality, motion artifacts were minimized using Laplacian pyramid diffeomorphic registration, while a wavelet directional cycle-consistent adversarial network (WavCycleGAN) reduced image noise. Four radiologists independently evaluated the visibility of thirteen anatomical regions (eight soft-tissue regions and five bone regions) and the overall image with a five-point scale of preference. Pooled mean values were calculated for each anatomic region through meta-analysis using a random-effects model. Results: Radiologists preferred DE-AI images to conventional chest radiographs in various anatomic regions. The enhanced standard image showed superior quality in 9 of 13 anatomic regions. Preference for the soft-tissue-selective image was statistically significant for three of eight anatomic regions. Preference for the bone-selective image was statistically significant for four of five anatomic regions. Conclusions: Images produced by DE-AI provide better visualization of thoracic structures.