Byung-Yoon Roh
Byung-Yoon Roh has a total of 32 co-authors. Here are the top co-authors by number of shared publications:
- Yo-Seob Seo
Department of Oral and Maxillofacial Radiology, College of Dentistry, Chosun University, Gwangju, Korea
7 shared publications - Jong-Mo Ahn
Department of Oral Medicine, School of Dentistry, Chosun University, Gwangju 61452, Republic of Korea
6 shared publications - Ji-Won Ryu
Department of Oral Medicine, School of Dentistry, Chosun University, Gwangju 61452, Republic of Korea
5 shared publications - Ju-Heon Lee
Forensic Medicine Division, National Forensic Service Gwangju Institute, Jangseong, Korea
5 shared publications - In-Soo Seo
Forensic Medicine Division, National Forensic Service Gwangju Institute, Jangseong, Korea
4 shared publications - Sang-Seob Lee
Department of Anatomy, College of Medicine, The Catholic University of Korea, Seoul, Republic of Korea
4 shared publications
Latest Publications
- Open Access
- 30 June 2026
- Published by Journal of Oral Medicine and Pain in Journal of Oral Medicine and Pain
- Vol. 51 (2) , 49-55
Artificial Intelligence-Based Evaluation of Mandibular Condyle Maturation for Condylar Age Assessment in Adolescents and Young Adults
- 30 June 2026
- Published by Journal of Oral Medicine and Pain in Journal of Oral Medicine and Pain
- Vol. 51 (2) , 49-55
Open AccessArtificial Intelligence-Based Evaluation of Mandibular Condyle Maturation for Condylar Age Assessment in Adolescents and Young Adults
- 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.
- 30 December 2024
- Published by Journal of Oral Medicine and Pain in Journal of Oral Medicine and Pain
- Vol. 49 (4) , 118-123
Dental Age Estimation in Children Using Convolution Neural Network Algorithm: A Pilot Study
- 30 December 2024
- Published by Journal of Oral Medicine and Pain in Journal of Oral Medicine and Pain
- Vol. 49 (4) , 118-123
Dental Age Estimation in Children Using Convolution Neural Network Algorithm: A Pilot Study
- Open Access
- 28 February 2023
- Published by The Korean Society for Legal Medicine in Korean Journal of Legal Medicine
- Vol. 47 (1) , 1-7
Dental Age Estimation Using the Demirjian Method: Statistical Analysis Using Neural Networks
In children and adolescents, dental age estimation is performed with the development of the teeth. Various statistical analysis methods have been used to determine the relationship between age and dental maturity and develop an accurate method of age calculation. This study attempted to apply a neural network model for the statistical analysis of dental age estimation in children and evaluated its applicability. This study used 1196 panoramic radiographs of patients aged 3–16 years, and 996 and 200 were randomly classified into training and test sets, respectively. The dental maturity of the mandibular left teeth was evaluated using Demirjian's method, the neural network model using the backpropagation algorithm was derived using training sets, and the errors were evaluated using 100 radiographs of each male and female as test sets. In addition, multiple linear regression analysis was conducted on the same training set, and the error was calculated by applying it to the test set and comparing it with the error of the neural network model. In the neural network model, the mean absolute error (MAE) and root mean squared error (RMSE) were 0.589 and 0.783 in male subjects and 0.529 and 0.760 in female subjects, respectively. In the multiple linear regression model, the MAE and RMSE were 0.600 and 0.748 in male subjects and 0.566 and 0.789 in female subjects, respectively. When applying the neural network model to the statistical analysis of the dental developmental stage, the results were as accurate as those of conventional statistical analysis methods. This study’s approach is expected to be useful for estimating the ages of children.
- 28 February 2023
- Published by The Korean Society for Legal Medicine in Korean Journal of Legal Medicine
- Vol. 47 (1) , 1-7
Open AccessDental Age Estimation Using the Demirjian Method: Statistical Analysis Using Neural Networks
In children and adolescents, dental age estimation is performed with the development of the teeth. Various statistical analysis methods have been used to determine the relationship between age and dental maturity and develop an accurate method of age calculation. This study attempted to apply a neural network model for the statistical analysis of dental age estimation in children and evaluated its applicability. This study used 1196 panoramic radiographs of patients aged 3–16 years, and 996 and 200 were randomly classified into training and test sets, respectively. The dental maturity of the mandibular left teeth was evaluated using Demirjian's method, the neural network model using the backpropagation algorithm was derived using training sets, and the errors were evaluated using 100 radiographs of each male and female as test sets. In addition, multiple linear regression analysis was conducted on the same training set, and the error was calculated by applying it to the test set and comparing it with the error of the neural network model. In the neural network model, the mean absolute error (MAE) and root mean squared error (RMSE) were 0.589 and 0.783 in male subjects and 0.529 and 0.760 in female subjects, respectively. In the multiple linear regression model, the MAE and RMSE were 0.600 and 0.748 in male subjects and 0.566 and 0.789 in female subjects, respectively. When applying the neural network model to the statistical analysis of the dental developmental stage, the results were as accurate as those of conventional statistical analysis methods. This study’s approach is expected to be useful for estimating the ages of children.
- Open Access
- 31 August 2022
- Published by The Korean Society for Legal Medicine in Korean Journal of Legal Medicine
- Vol. 46 (3) , 71-78
Estimating Age Using Nationwide Survey Data on the Number of Residual Teeth
Given that tooth loss is a degenerative change, the number of residual teeth may be used to specify a particular age range as a marker for age estimation. This study examined changes in the number of teeth with age using a nationwide oral survey database and derived the age distribution of the Korean population according to the number of teeth. Data on the number of teeth and age were extracted from the oral examination data of the Korean National Health and Nutrition Examination Survey (KNHANES) from 2016 to 2018. Statistical analyses of a complex sample survey were performed using weighted values. The distribution range of the number of teeth by age was broad. The proportion of young people decreased progressively as the number of remaining teeth decreased. In contrast, the proportion of those from the older age group decreased slightly as the number of teeth increased. The number of teeth was subdivided into groups of four, age was categorized into 5-year intervals, and the distribution of age groups by the number of teeth was analyzed. We attempted to determine the age group threshold at approximately 95th percentile for age. In summary, we found that if there were ≤4, 5-12, and 13-20 residual teeth, the estimated age was ≥60, ≥55, and ≥50 years, respectively, with an approximately 95% probability. When many teeth are lost and it is difficult to apply conventional dental age estimation methods, our method may assist in narrowing the age range, although it is not an accurate age determination method.
- 31 August 2022
- Published by The Korean Society for Legal Medicine in Korean Journal of Legal Medicine
- Vol. 46 (3) , 71-78
Open AccessEstimating Age Using Nationwide Survey Data on the Number of Residual Teeth
Given that tooth loss is a degenerative change, the number of residual teeth may be used to specify a particular age range as a marker for age estimation. This study examined changes in the number of teeth with age using a nationwide oral survey database and derived the age distribution of the Korean population according to the number of teeth. Data on the number of teeth and age were extracted from the oral examination data of the Korean National Health and Nutrition Examination Survey (KNHANES) from 2016 to 2018. Statistical analyses of a complex sample survey were performed using weighted values. The distribution range of the number of teeth by age was broad. The proportion of young people decreased progressively as the number of remaining teeth decreased. In contrast, the proportion of those from the older age group decreased slightly as the number of teeth increased. The number of teeth was subdivided into groups of four, age was categorized into 5-year intervals, and the distribution of age groups by the number of teeth was analyzed. We attempted to determine the age group threshold at approximately 95th percentile for age. In summary, we found that if there were ≤4, 5-12, and 13-20 residual teeth, the estimated age was ≥60, ≥55, and ≥50 years, respectively, with an approximately 95% probability. When many teeth are lost and it is difficult to apply conventional dental age estimation methods, our method may assist in narrowing the age range, although it is not an accurate age determination method.
- Open Access
- 30 December 2021
- Published by Journal of Oral Medicine and Pain in Journal of Oral Medicine and Pain
- Vol. 46 (4) , 125-130
Age Estimation Based on Mandibular Premolar and Molar Development: A Pilot Study
Byung-Yoon Roh, Eui-Joo Kim, In-Soo Seo, Hyeong-Geon Kim, Hye-Won Ryu, Ju-Heon Lee, Yo-Seob Seo, Ji-Won Ryu, Jong-Mo Ahn. JOMP 2021;46:125-30. https://doi.org/10.14476/jomp.2021.46.4.125
- 30 December 2021
- Published by Journal of Oral Medicine and Pain in Journal of Oral Medicine and Pain
- Vol. 46 (4) , 125-130
Open AccessAge Estimation Based on Mandibular Premolar and Molar Development: A Pilot Study
Byung-Yoon Roh, Eui-Joo Kim, In-Soo Seo, Hyeong-Geon Kim, Hye-Won Ryu, Ju-Heon Lee, Yo-Seob Seo, Ji-Won Ryu, Jong-Mo Ahn. JOMP 2021;46:125-30. https://doi.org/10.14476/jomp.2021.46.4.125
- 31 December 2020
- Published by The Oral Biology Research Institute at Chosum University in Oral Biology Research
- Vol. 44 (4) , 127-132
Age estimation by pulp/tooth area ratio in a Korean sample on digital panoramic radiographs
Byung-Yoon Roh, Chang-Gyum Kim, Sang-Seob Lee, Won-Joon Lee, Yo-Seob Seo, Ji-Won Ryu, Jong-Mo Ahn, and Chang-Lyuk Yoon. Oral Biol Res 2020;44:127-32. https://doi.org/10.21851/obr.44.04.202012.127
- 31 December 2020
- Published by The Oral Biology Research Institute at Chosum University in Oral Biology Research
- Vol. 44 (4) , 127-132
Age estimation by pulp/tooth area ratio in a Korean sample on digital panoramic radiographs
Byung-Yoon Roh, Chang-Gyum Kim, Sang-Seob Lee, Won-Joon Lee, Yo-Seob Seo, Ji-Won Ryu, Jong-Mo Ahn, and Chang-Lyuk Yoon. Oral Biol Res 2020;44:127-32. https://doi.org/10.21851/obr.44.04.202012.127
- 27 February 2018
- Published by Elsevier in Legal Medicine
- Vol. 32, 37-42
Analysis of forensic odontological examinations at the National Forensic Service of Korea from 2011 to 2015
- 27 February 2018
- Published by Elsevier in Legal Medicine
- Vol. 32, 37-42
Analysis of forensic odontological examinations at the National Forensic Service of Korea from 2011 to 2015
- Open Access
- 1 January 2018
- Published by The Korean Society for Legal Medicine in Korean Journal of Legal Medicine
- Vol. 42 (4) , 141-145
The Application of Paewinsky et al.'s Age Estimation Method to Periapical Radiographs
Roh BY, et al. Korean J Leg Med. 2018 Nov;42(4):141-145. https://doi.org/10.7580/kjlm.2018.42.4.141
- 1 January 2018
- Published by The Korean Society for Legal Medicine in Korean Journal of Legal Medicine
- Vol. 42 (4) , 141-145
Open AccessThe Application of Paewinsky et al.'s Age Estimation Method to Periapical Radiographs
Roh BY, et al. Korean J Leg Med. 2018 Nov;42(4):141-145. https://doi.org/10.7580/kjlm.2018.42.4.141
- 19 December 2017
- Published by Springer Nature in International journal of legal medicine
- Vol. 132 (4) , 1161-1166
The application of the Kvaal method to estimate the age of live Korean subjects using digital panoramic radiographs
Dental age estimation of the living is limited because observing the histological structure of teeth is difficult. Therefore, several methods have been proposed to estimate age by observing changes on dental radiographs of pulpal size caused by secondary dentin deposition. This study aims to evaluate the validity of the Kvaal method to estimate the ages of Korean subjects using digital panoramic radiographs and formulate regression equations for use in Korean subjects. We included 266 Korean subjects (age 21–69 years) visiting Chosun University Dental Hospital (Gwangju, South Korea). The pulpal size and width of six tooth types (maxillary central incisor, lateral incisor, second premolar, mandibular lateral incisor, canine, and first premolar) were measured on digital panoramic radiographs according to the Kvaal method. Statistical interobserver/intraobserver reliabilities were calculated to evaluate the reproducibility of the measured values, and correlations between actual ages and measured values were identified. The differences between the predicted ages and the actual age were analyzed. Paewinsky method was also applied and its validity was evaluated. In addition, a series of new regression equations for the age estimation of Korean subjects was produced. When both methods were applied directly to the teeth of the subjects, significant differences were observed between the estimated and chronological ages. The length-related parameters of the teeth of subjects calculated by the original Kvaal method showed no significant correlation. A regression equation derived from the width parameters without the length ratios is proposed for use in Korean subjects.
- 19 December 2017
- Published by Springer Nature in International journal of legal medicine
- Vol. 132 (4) , 1161-1166
The application of the Kvaal method to estimate the age of live Korean subjects using digital panoramic radiographs
Dental age estimation of the living is limited because observing the histological structure of teeth is difficult. Therefore, several methods have been proposed to estimate age by observing changes on dental radiographs of pulpal size caused by secondary dentin deposition. This study aims to evaluate the validity of the Kvaal method to estimate the ages of Korean subjects using digital panoramic radiographs and formulate regression equations for use in Korean subjects. We included 266 Korean subjects (age 21–69 years) visiting Chosun University Dental Hospital (Gwangju, South Korea). The pulpal size and width of six tooth types (maxillary central incisor, lateral incisor, second premolar, mandibular lateral incisor, canine, and first premolar) were measured on digital panoramic radiographs according to the Kvaal method. Statistical interobserver/intraobserver reliabilities were calculated to evaluate the reproducibility of the measured values, and correlations between actual ages and measured values were identified. The differences between the predicted ages and the actual age were analyzed. Paewinsky method was also applied and its validity was evaluated. In addition, a series of new regression equations for the age estimation of Korean subjects was produced. When both methods were applied directly to the teeth of the subjects, significant differences were observed between the estimated and chronological ages. The length-related parameters of the teeth of subjects calculated by the original Kvaal method showed no significant correlation. A regression equation derived from the width parameters without the length ratios is proposed for use in Korean subjects.