Sung Hyun Kim
Sung Hyun Kim has a total of 23 co-authors. Here are the top co-authors by number of shared publications:
- Eun Kyoung Kang
Department of Rehabilitation Medicine, Kangwon National University Hospital, Kangwon National University School of Medicine, Chuncheon, Korea
2 shared publications - Hee-Won Park
Department of Rehabilitation Medicine, Kangwon National University Hospital, Kangwon National University School of Medicine, Chuncheon, Korea
2 shared publications - Sora Baek
Department of Rehabilitation Medicine, Kangwon National University Hospital, Kangwon National University College of Medicine, Chuncheon, Korea
2 shared publications Amal Muhammad Saleem
Center for Artificial Intelligence in Medicine and Imaging HealthHub Co. Ltd 06524 Seoul South Korea
1 shared publication- Azka Rehman
Department of Biomedical Sciences, Seoul National University Graduate School, Seoul, South Korea
1 shared publication Byoung Dai Lee
Division of AI and Computer Engineering Kyonggi University Suwon Republic of South Korea
1 shared publication
Latest Publications
- Open Access
- 1 January 2024
- Published by XMLink in Journal of the Korean Society of Radiology
- Vol. 85 (6) , 1035-1043
Standardization for Promoting Interoperability of Healthcare Data: The Progression of the Korean Society of Radiology
강준원, et al. J Korean Soc Radiol. 2024 Nov;85(6):1035-1043. https://doi.org/10.3348/jksr.2024.0124
- 1 January 2024
- Published by XMLink in Journal of the Korean Society of Radiology
- Vol. 85 (6) , 1035-1043
Open AccessStandardization for Promoting Interoperability of Healthcare Data: The Progression of the Korean Society of Radiology
강준원, et al. J Korean Soc Radiol. 2024 Nov;85(6):1035-1043. https://doi.org/10.3348/jksr.2024.0124
- Open Access
Dual-Stage Deeply Supervised Attention-based Convolutional Neural Networks for Mandibular Canal Segmentation in CBCT Scans
Accurate segmentation of mandibular canals in lower jaws is important in dental implantology. Medical experts determine the implant position and dimensions manually from 3D CT images to avoid damaging the mandibular nerve inside the canal. In this paper, we propose a novel dual-stage deep learning-based scheme for the automatic segmentation of the mandibular canal. Particularly, we first enhance the CBCT scans by employing the novel histogram-based dynamic windowing scheme, which improves the visibility of mandibular canals. After enhancement, we design 3D deeply supervised attention U-Net architecture for localizing the volumes of interest (VOIs), which contain the mandibular canals (i.e., left and right canals). Finally, we employed the multi-scale input residual U-Net architecture (MS-R-UNet) to segment the mandibular canals using VOIs accurately. The proposed method has been rigorously evaluated on 500 scans. The results demonstrate that our technique outperforms the current state-of-the-art segmentation performance and robustness methods.
Open AccessDual-Stage Deeply Supervised Attention-based Convolutional Neural Networks for Mandibular Canal Segmentation in CBCT Scans
Accurate segmentation of mandibular canals in lower jaws is important in dental implantology. Medical experts determine the implant position and dimensions manually from 3D CT images to avoid damaging the mandibular nerve inside the canal. In this paper, we propose a novel dual-stage deep learning-based scheme for the automatic segmentation of the mandibular canal. Particularly, we first enhance the CBCT scans by employing the novel histogram-based dynamic windowing scheme, which improves the visibility of mandibular canals. After enhancement, we design 3D deeply supervised attention U-Net architecture for localizing the volumes of interest (VOIs), which contain the mandibular canals (i.e., left and right canals). Finally, we employed the multi-scale input residual U-Net architecture (MS-R-UNet) to segment the mandibular canals using VOIs accurately. The proposed method has been rigorously evaluated on 500 scans. The results demonstrate that our technique outperforms the current state-of-the-art segmentation performance and robustness methods.
- Open Access
- 31 August 2021
- Published by Korean Academy of Rehabilitation Medicine in Annals of Rehabilitation Medicine
- Vol. 45 (4) , 294-303
The Association Between Sagittal Plane Alignment and Disc Space Narrowing of Lumbar Spine in Farmers
Objective To investigate whether lumbar lordosis (LL) and lumbar segmental lordosis (LSL) are related to sex, age, low back pain (LBP), and lumbar disc space narrowing (DSN).Methods A total of 569 farmers were recruited. In lateral spine radiograph, LL (L1–L5) and LSL (L1, L2, L3, L4, and L5) were measured using Cobb’s method. The differences in LSL values (ΔLSL) according to the presence or absence of a DSN were calculated as LSLDSN – LSLnoDSN for each DSN level.Results In male, the lateral spine radiograph showed significantly greater L4-LSL and L5-LSL and smaller L1-LSL and L2-LSL compared to female. LLs in the 50–59 and ≥60 years age groups were significantly smaller compared to those in the <50 years age group. In subjects with LBP, LL and L4-LSL were significantly smaller than in those without. The ΔLSLs at the disc level with DSN showed the greatest decrease: L1-ΔLSL (Δ-3.99°), L2-ΔLSL (Δ-3.31°), L3-ΔLSL (Δ-2.87°), L4-ΔLSL (Δ-3.31°), and L5-ΔLSL (Δ-4.44°) in L1/2, L2/3, L3/4, L4/5, and L5/S1 DSN, respectively. Conversely, distant ΔLSLs were inversely increased: L1-LSL (Δ0.75°) with L4/5 DSN and L2-LSL (Δ0.94°) with L5/S1 DSN.Conclusion Sagittal plane alignment was significantly associated with sex, age, LBP, and DSN. LSLs around the levels of DSN were decreased, and there was compensational increase of LSL distant to the DSN to maintain the overall LL.
- 31 August 2021
- Published by Korean Academy of Rehabilitation Medicine in Annals of Rehabilitation Medicine
- Vol. 45 (4) , 294-303
Open AccessThe Association Between Sagittal Plane Alignment and Disc Space Narrowing of Lumbar Spine in Farmers
Objective To investigate whether lumbar lordosis (LL) and lumbar segmental lordosis (LSL) are related to sex, age, low back pain (LBP), and lumbar disc space narrowing (DSN).Methods A total of 569 farmers were recruited. In lateral spine radiograph, LL (L1–L5) and LSL (L1, L2, L3, L4, and L5) were measured using Cobb’s method. The differences in LSL values (ΔLSL) according to the presence or absence of a DSN were calculated as LSLDSN – LSLnoDSN for each DSN level.Results In male, the lateral spine radiograph showed significantly greater L4-LSL and L5-LSL and smaller L1-LSL and L2-LSL compared to female. LLs in the 50–59 and ≥60 years age groups were significantly smaller compared to those in the <50 years age group. In subjects with LBP, LL and L4-LSL were significantly smaller than in those without. The ΔLSLs at the disc level with DSN showed the greatest decrease: L1-ΔLSL (Δ-3.99°), L2-ΔLSL (Δ-3.31°), L3-ΔLSL (Δ-2.87°), L4-ΔLSL (Δ-3.31°), and L5-ΔLSL (Δ-4.44°) in L1/2, L2/3, L3/4, L4/5, and L5/S1 DSN, respectively. Conversely, distant ΔLSLs were inversely increased: L1-LSL (Δ0.75°) with L4/5 DSN and L2-LSL (Δ0.94°) with L5/S1 DSN.Conclusion Sagittal plane alignment was significantly associated with sex, age, LBP, and DSN. LSLs around the levels of DSN were decreased, and there was compensational increase of LSL distant to the DSN to maintain the overall LL.
- Open Access
- 1 January 2020
- Published by XMLink in Imaging Science in Dentistry
- Vol. 50 (3) , 237-243
Evaluation of the clinical efficacy of a TW3-based fully automated bone age assessment system using deep neural networks
Shin NY, et al. Imaging Sci Dent. 2020 Sep;50(3):237-243. https://doi.org/10.5624/isd.2020.50.3.237
- 1 January 2020
- Published by XMLink in Imaging Science in Dentistry
- Vol. 50 (3) , 237-243
Open AccessEvaluation of the clinical efficacy of a TW3-based fully automated bone age assessment system using deep neural networks
Shin NY, et al. Imaging Sci Dent. 2020 Sep;50(3):237-243. https://doi.org/10.5624/isd.2020.50.3.237
- Open Access
- 1 January 2017
- Published by Korean Academy of Rehabilitation Medicine in Annals of Rehabilitation Medicine
- Vol. 41 (5) , 808-815
Clinical Usefulness of X-Ray Findings for Non-specific Low Back Pain in Korean Farmers: FARM Study
Kang EK, et al. Ann Rehabil Med. 2017 Oct;41(5):808-815. https://doi.org/10.5535/arm.2017.41.5.808
- 1 January 2017
- Published by Korean Academy of Rehabilitation Medicine in Annals of Rehabilitation Medicine
- Vol. 41 (5) , 808-815
Open AccessClinical Usefulness of X-Ray Findings for Non-specific Low Back Pain in Korean Farmers: FARM Study
Kang EK, et al. Ann Rehabil Med. 2017 Oct;41(5):808-815. https://doi.org/10.5535/arm.2017.41.5.808