Nak-Won Lee
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Nak-Won Lee has a total of 25 co-authors. Here are the top co-authors by number of shared publications:
- Hyelim Yi
Forensic Medicine Division National Forensic Service Daejeon Institute Daejeon Korea
3 shared publications - Jeong Hwan Kim
Forensic Medicine Division National Forensic Service Daejeon Institute Daejeon Korea
3 shared publications - Ji Hye Park
Forensic Medicine Division National Forensic Service Daejeon Institute Daejeon Korea
3 shared publications - Min Jee Park
Forensic Medicine Division National Forensic Service Daejeon Institute Daejeon Korea
3 shared publications - Minjung Kim
Department of Forensic Medicine National Forensic Service Seoul Institute Seoul Korea
3 shared publications - Bon Young Koo
Division of Forensic Medicine, National Forensic Service Daegu Institute, Chilgok, Korea
2 shared publications
Latest Publications
- Open Access
- 28 February 2026
- Published by The Korean Society for Legal Medicine in Korean Journal of Legal Medicine
- Vol. 50 (1) , 1-8
Age Estimation Using Convolutional Neural Networks with Lumbar and Thoracic Spine Images from Postmortem Computed Tomography: A Pilot Study
In forensic medicine, age estimation commonly involves assessing age-related changes in teeth and skeletal structures. Vertebral morphological alterations, such as osteophyte formation, serve as age indicators. Recent studies using deep-learning techniques, such as neural networks, for age estimation from radiographic images have been conducted, reporting significantly higher accuracy than previous studies. This study aimed to estimate age using neural network-based deep-learning techniques applied to computed tomography (CT) cross-sectional images of the spine and evaluate its feasibility. Postmortem CT scans of 214 cadavers with varying decomposition levels were used. Coronal and sagittal cross-sectional images penetrating the center of each vertebral body were extracted for the 11th and 12th thoracic vertebrae and the first to fifth lumbar vertebrae. Using these images, along with the chronological ages of deceased individuals, an age estimation model was developed through regression analysis in PyTorch, employing a convolutional neural networks architecture with five-fold cross-validation. The model achieved a mean absolute error of 5.385 years, root mean squared error of 7.029 years, and coefficient of determination of 0.793. Although the sample size was relatively small, the results suggested the potential applicability of vertebral imagingbased age estimation in the Korean population. Further research using a larger dataset may improve the accuracy and reliability of the model.
- 28 February 2026
- Published by The Korean Society for Legal Medicine in Korean Journal of Legal Medicine
- Vol. 50 (1) , 1-8
Open AccessAge Estimation Using Convolutional Neural Networks with Lumbar and Thoracic Spine Images from Postmortem Computed Tomography: A Pilot Study
In forensic medicine, age estimation commonly involves assessing age-related changes in teeth and skeletal structures. Vertebral morphological alterations, such as osteophyte formation, serve as age indicators. Recent studies using deep-learning techniques, such as neural networks, for age estimation from radiographic images have been conducted, reporting significantly higher accuracy than previous studies. This study aimed to estimate age using neural network-based deep-learning techniques applied to computed tomography (CT) cross-sectional images of the spine and evaluate its feasibility. Postmortem CT scans of 214 cadavers with varying decomposition levels were used. Coronal and sagittal cross-sectional images penetrating the center of each vertebral body were extracted for the 11th and 12th thoracic vertebrae and the first to fifth lumbar vertebrae. Using these images, along with the chronological ages of deceased individuals, an age estimation model was developed through regression analysis in PyTorch, employing a convolutional neural networks architecture with five-fold cross-validation. The model achieved a mean absolute error of 5.385 years, root mean squared error of 7.029 years, and coefficient of determination of 0.793. Although the sample size was relatively small, the results suggested the potential applicability of vertebral imagingbased age estimation in the Korean population. Further research using a larger dataset may improve the accuracy and reliability of the model.
- Open Access
- 30 November 2024
- Published by The Korean Society for Legal Medicine in Korean Journal of Legal Medicine
- Vol. 48 (4) , 153-164
A Statistical Analysis of Forensic Autopsies Performed in the Jungbu Province of Korea in 2022
We analyzed the manner and cause of death in 1,193 forensic autopsies from the Jungbu province (central part of South Korea) conducted by the National Forensic Service Daejeon Institute in 2022. Analysis of the manner of deaths revealed that 43.1% (514/1,193 cases) were natural deaths; 42.8% (511/1,193 cases) were unnatural deaths; and 14.1% (168/1,193 cases) were unknown. Among the unnatural deaths, the major manner of death was 44.6% (228/511 cases) by accidents, 34.1% (174/511 cases) by suicide, 13.5% (69/511 cases) undetermined, and 7.8% (40/511 cases) by homicide. Among the unnatural deaths, the major causes of death was 38.4% (196/511 cases) by trauma, 20.4% (104/511 cases) by poisoning, and 17.6% (90/511 cases) by asphyxia. Falling was the major cause of death by trauma (58.7%, 115/196 cases), and strangulation was the major cause of death by asphyxia (75.6%, 68/90 cases). Among the natural deaths, heart disease was the major cause (46.7%, 240/514 cases), followed by endocrine, nutritional and metabolic diseases (14.0%, 72/514 cases). A time-series statistical analysis and comparison of the manner and cause of deaths in this province may facilitate more advanced interpretations relating to both public safety and healthcare in the future.
- 30 November 2024
- Published by The Korean Society for Legal Medicine in Korean Journal of Legal Medicine
- Vol. 48 (4) , 153-164
Open AccessA Statistical Analysis of Forensic Autopsies Performed in the Jungbu Province of Korea in 2022
We analyzed the manner and cause of death in 1,193 forensic autopsies from the Jungbu province (central part of South Korea) conducted by the National Forensic Service Daejeon Institute in 2022. Analysis of the manner of deaths revealed that 43.1% (514/1,193 cases) were natural deaths; 42.8% (511/1,193 cases) were unnatural deaths; and 14.1% (168/1,193 cases) were unknown. Among the unnatural deaths, the major manner of death was 44.6% (228/511 cases) by accidents, 34.1% (174/511 cases) by suicide, 13.5% (69/511 cases) undetermined, and 7.8% (40/511 cases) by homicide. Among the unnatural deaths, the major causes of death was 38.4% (196/511 cases) by trauma, 20.4% (104/511 cases) by poisoning, and 17.6% (90/511 cases) by asphyxia. Falling was the major cause of death by trauma (58.7%, 115/196 cases), and strangulation was the major cause of death by asphyxia (75.6%, 68/90 cases). Among the natural deaths, heart disease was the major cause (46.7%, 240/514 cases), followed by endocrine, nutritional and metabolic diseases (14.0%, 72/514 cases). A time-series statistical analysis and comparison of the manner and cause of deaths in this province may facilitate more advanced interpretations relating to both public safety and healthcare in the future.
- Open Access
- 30 November 2023
- Published by The Korean Society for Legal Medicine in Korean Journal of Legal Medicine
- Vol. 47 (4) , 110-121
A Statistical Analysis of Forensic Autopsies Performed in the Jungbu Province of Korea in 2021
We analyzed 1,079 forensic autopsies conducted in 2021 by the National Forensic Service Daejeon Institute from the Jungbu province in the central part of South Korea, for their manner and cause of death. Among the manner of death (n=1,079), 45.3% (n=489) were categorised as unnatural, 39.5% (n=426) as natural, and 15.2% (n=164) were unknown. Among the unnatural deaths (n=489), 40.7% (n=199) were accidents, 36.8% (n=180) were suicides, 14.1% (n=69) were undetermined, and 8.4% (n=41) were homicides. The major causes of unnatural deaths (n=489) were by trauma, causing 34.4% (n=168), poisoning causing 26.8% (n=131), and asphyxia causing 17.2% (n=84). The major cause of death by trauma (n=168) was falling at 46.4% (n=78), and by asphyxia (n=84) was strangulation at 76.2% (n=64). Among natural deaths (n=426), heart disease was the major cause at 49.8% (n=212) followed by vascular disease at 16.7% (n=71). In future, a time-series statistical analysis on the manner and causes of death in Jungbu province may provide insight and allow for more advanced interpretations about both healthcare and public safety.
- 30 November 2023
- Published by The Korean Society for Legal Medicine in Korean Journal of Legal Medicine
- Vol. 47 (4) , 110-121
Open AccessA Statistical Analysis of Forensic Autopsies Performed in the Jungbu Province of Korea in 2021
We analyzed 1,079 forensic autopsies conducted in 2021 by the National Forensic Service Daejeon Institute from the Jungbu province in the central part of South Korea, for their manner and cause of death. Among the manner of death (n=1,079), 45.3% (n=489) were categorised as unnatural, 39.5% (n=426) as natural, and 15.2% (n=164) were unknown. Among the unnatural deaths (n=489), 40.7% (n=199) were accidents, 36.8% (n=180) were suicides, 14.1% (n=69) were undetermined, and 8.4% (n=41) were homicides. The major causes of unnatural deaths (n=489) were by trauma, causing 34.4% (n=168), poisoning causing 26.8% (n=131), and asphyxia causing 17.2% (n=84). The major cause of death by trauma (n=168) was falling at 46.4% (n=78), and by asphyxia (n=84) was strangulation at 76.2% (n=64). Among natural deaths (n=426), heart disease was the major cause at 49.8% (n=212) followed by vascular disease at 16.7% (n=71). In future, a time-series statistical analysis on the manner and causes of death in Jungbu province may provide insight and allow for more advanced interpretations about both healthcare and public safety.
- Open Access
- 30 November 2021
- Published by The Korean Society for Legal Medicine in Korean Journal of Legal Medicine
- Vol. 45 (4) , 111-121
A Statistical Analysis of Forensic Autopsies Performed in the Jungbu Province of Korea in 2020
We analyzed the manner and cause of death in 945 forensic autopsies from the Jungbu province (Central part of South Korea) conducted by the National Forensic Service Daejeon institute in 2020. Analysis of the manner of death revealed that 43.6% (412/945 cases) were natural deaths, 41.6% (393/945 cases) were unnatural deaths, and 14.8% (140/945 cases) deaths were unknown. Among the unnatural deaths, the major manner of death (40.7%, 160/393 cases) were by accidents, 29.5% (116/393 cases) were by suicide, 21.6% (85/393 cases) were undetermined, and 8.1% (32/393 cases) were by homicide. Among the unnatural deaths, the major cause of death (42.7%, 168/393 cases) were by trauma, 19.3% (76/393 cases) were by poisoning, and 16.5% (65/393 cases) were by asphyxia. Falling was the major cause of death by trauma (42.9%, 72/168 cases) and strangulation was the major cause of death by asphyxia (72.3%, 47/65 cases). Among natural deaths, heart disease was the major cause (43.7%, 180/412 cases), followed by vascular disease (18.9%, 78/412 cases). This study is the first statistical analysis of the manner and cause of deaths in the Jungbu province. A time-series statistical analysis of the manner and cause of deaths in this province might allow more advanced interpretations about both public safety and healthcare in the future.
- 30 November 2021
- Published by The Korean Society for Legal Medicine in Korean Journal of Legal Medicine
- Vol. 45 (4) , 111-121
Open AccessA Statistical Analysis of Forensic Autopsies Performed in the Jungbu Province of Korea in 2020
We analyzed the manner and cause of death in 945 forensic autopsies from the Jungbu province (Central part of South Korea) conducted by the National Forensic Service Daejeon institute in 2020. Analysis of the manner of death revealed that 43.6% (412/945 cases) were natural deaths, 41.6% (393/945 cases) were unnatural deaths, and 14.8% (140/945 cases) deaths were unknown. Among the unnatural deaths, the major manner of death (40.7%, 160/393 cases) were by accidents, 29.5% (116/393 cases) were by suicide, 21.6% (85/393 cases) were undetermined, and 8.1% (32/393 cases) were by homicide. Among the unnatural deaths, the major cause of death (42.7%, 168/393 cases) were by trauma, 19.3% (76/393 cases) were by poisoning, and 16.5% (65/393 cases) were by asphyxia. Falling was the major cause of death by trauma (42.9%, 72/168 cases) and strangulation was the major cause of death by asphyxia (72.3%, 47/65 cases). Among natural deaths, heart disease was the major cause (43.7%, 180/412 cases), followed by vascular disease (18.9%, 78/412 cases). This study is the first statistical analysis of the manner and cause of deaths in the Jungbu province. A time-series statistical analysis of the manner and cause of deaths in this province might allow more advanced interpretations about both public safety and healthcare in the future.
- Open Access
- 31 May 2020
- Published by The Korean Society for Legal Medicine in Korean Journal of Legal Medicine
- Vol. 44 (2) , 76-83
Postmortem Diagnosis of Anaphylactic Shock by Histopathological Examination of Mast Cell
- 31 May 2020
- Published by The Korean Society for Legal Medicine in Korean Journal of Legal Medicine
- Vol. 44 (2) , 76-83
Open AccessPostmortem Diagnosis of Anaphylactic Shock by Histopathological Examination of Mast Cell
- Open Access
- 1 January 2020
- Published by The Korean Society for Legal Medicine in Korean Journal of Legal Medicine
- Vol. 44 (1) , 17-23
Usefulness of Mast Cell Tryptase Analysis for Postmortem Diagnosis of Anaphylactic Shock
Park JP, et al. Korean J Leg Med. 2020 Feb;44(1):17-23. https://doi.org/10.7580/kjlm.2020.44.1.17
- 1 January 2020
- Published by The Korean Society for Legal Medicine in Korean Journal of Legal Medicine
- Vol. 44 (1) , 17-23
Open AccessUsefulness of Mast Cell Tryptase Analysis for Postmortem Diagnosis of Anaphylactic Shock
Park JP, et al. Korean J Leg Med. 2020 Feb;44(1):17-23. https://doi.org/10.7580/kjlm.2020.44.1.17