Automatic sex estimation using deep convolutional neural network based on orthopantomogram images

Bu, Wen-qing; Guo, Yuxin; Zhang, Dong; Du, Shaoyi; Han, Mengqi; Wu, Zixuan; Tao, Yu; Chen, Teng; Guo, Yucheng; Meng, Hao-Tian

doi:10.1016/j.forsciint.2023.111704

Cited by 4 publications

(6 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In age estimation, Milošević et al [ 26 ] reported an MAE of 3.96 on the dataset with a non-uniform age distribution between the younger and older age groups, while the proposed ForensicNet achieved an MAE of 2.93 ± 2.61 on the dataset with uniform age distribution ranging from 15 to 80 years. Bu et al [ 27 ] obtained ACC and SEN values for sex estimation using 10,703 panoramic radiographs from samples aged 5–25 years. In contrast, our ForensicNet achieved values of 0.992 for ACC, 0.990 for SEN, and 0.993 for SPE, respectively.…”

Section: Discussionmentioning

confidence: 99%

“…The performance of the age estimation model resulted in a mean absolute error (MAE) value of 3.96 ± 2.95. Bu et al [ 27 ] investigated the potential use of a deep network in predicting sex based on panoramic radiographs of 10,703 patients (4,789 males and 5,914 females) aged 5–25 years. The accuracy of sex estimation using a convolutional neural network was higher for adults (90.97%) than for minors (82.64%).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Automatic and robust estimation of sex and chronological age from panoramic radiographs using a multi-task deep learning network: a study on a South Korean population

Park,

Yang,

Kim

et al. 2024

Int J Legal Med

View full text Add to dashboard Cite

Sex and chronological age estimation are crucial in forensic investigations and research on individual identification. Although manual methods for sex and age estimation have been proposed, these processes are labor-intensive, time-consuming, and error-prone. The purpose of this study was to estimate sex and chronological age from panoramic radiographs automatically and robustly using a multi-task deep learning network (ForensicNet). ForensicNet consists of a backbone and both sex and age attention branches to learn anatomical context features of sex and chronological age from panoramic radiographs and enables the multi-task estimation of sex and chronological age in an end-to-end manner. To mitigate bias in the data distribution, our dataset was built using 13,200 images with 100 images for each sex and age range of 15–80 years. The ForensicNet with EfficientNet-B3 exhibited superior estimation performance with mean absolute errors of 2.93 ± 2.61 years and a coefficient of determination of 0.957 for chronological age, and achieved accuracy, specificity, and sensitivity values of 0.992, 0.993, and 0.990, respectively, for sex prediction. The network demonstrated that the proposed sex and age attention branches with a convolutional block attention module significantly improved the estimation performance for both sex and chronological age from panoramic radiographs of elderly patients. Consequently, we expect that ForensicNet will contribute to the automatic and accurate estimation of both sex and chronological age from panoramic radiographs.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Automatic and robust estimation of sex and chronological age from panoramic radiographs using a multi-task deep learning network: a study on a South Korean population

Park,

Yang,

Kim

et al. 2024

Int J Legal Med

View full text Add to dashboard Cite

show abstract

“…This iterative testing on different subsets of the dataset and averaging the results provides a more comprehensive evaluation, thereby enhancing the credibility and generalizability of our results. Bu et al 19) explored the feasibility of using deep learning-driven AI models for sex determination in Northern Chinese individuals on the basis of orthopantomograms; they achieved 90.97% accuracy, 92.22% sensitivity (recall) and 93.79% precision among images of adults. While direct comparisons between these studies and our research may be challenging due to variations in modalities and experimental conditions, these findings indicate that sex can be precisely deduced from radiographic images of the craniomaxillofacial region using deep learning approaches.…”

Section: Discussionmentioning

confidence: 99%

“…The performances of deep learning models were determined in terms of accuracy, sensitivity (recall), precision, F1 score, receiver operating characteristic (ROC) curves, and areas under the ROC curve (AUCs) of the test datasets 19,20) . Performance metrics were evaluated as follows.…”

Section: Performance Metricsmentioning

confidence: 99%

Sex estimation from maxillofacial radiographs using a deep learning approach

HASE,

MINE,

OKAZAKI

et al. 2024

Dent. Mater. J.

View full text Add to dashboard Cite

The purpose of this study was to construct deep learning models for more efficient and reliable sex estimation. Two deep learning models, VGG16 and DenseNet-121, were used in this retrospective study. In total, 600 lateral cephalograms were analyzed. A saliency map was generated by gradient-weighted class activation mapping for each output. The two deep learning models achieved high values in each performance metric according to accuracy, sensitivity (recall), precision, F1 score, and areas under the receiver operating characteristic curve. Both models showed substantial differences in the positions indicated in saliency maps for male and female images. The positions in saliency maps also differed between VGG16 and DenseNet-121, regardless of sex. This analysis of our proposed system suggested that sex estimation from lateral cephalograms can be achieved with high accuracy using deep learning.

show abstract

“…Most of the research investigating the role of AI in forensic sciences has focused on areas such as sex and age estimation [9][10][11][12][13][14][15][16][17][18], physical attributes, and in forensic odontology and anthropology for human identification purposes [12,[19][20][21][22][23][24][25][26]. Furthermore, AI could be very helpful in the evaluation of DNA methylation-based age prediction.…”

Section: Introductionmentioning

confidence: 99%

Artificial Intelligence and Forensic Genetics: Current Applications and Future Perspectives

Sessa,

Esposito,

Cocimano

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

The term artificial intelligence (AI) was coined in the 1950s and it has successfully made its way into different fields of medicine. Forensic sciences and AI are increasingly intersecting fields that hold tremendous potential for solving complex criminal investigations. Considering the great evolution in the technologies applied to forensic genetics, this literature review aims to explore the existing body of research that investigates the application of AI in the field of forensic genetics. Scopus and Web of Science were searched: after an accurate evaluation, 12 articles were included in the present systematic review. The application of AI in the field of forensic genetics has predominantly focused on two aspects. Firstly, several studies have investigated the use of AI in haplogroup analysis to enhance and expedite the classification process of DNA samples. Secondly, other research groups have utilized AI to analyze short tandem repeat (STR) profiles, thereby minimizing the risk of misinterpretation. While AI has proven to be highly useful in forensic genetics, further improvements are needed before using these applications in real cases. The main challenge lies in the communication gap between forensic experts: as AI continues to advance, the collaboration between forensic sciences and AI presents immense potential for transforming investigative practices, enabling quicker and more precise case resolutions.

show abstract

Automatic sex estimation using deep convolutional neural network based on orthopantomogram images

Cited by 4 publications

References 35 publications

Automatic and robust estimation of sex and chronological age from panoramic radiographs using a multi-task deep learning network: a study on a South Korean population

Automatic and robust estimation of sex and chronological age from panoramic radiographs using a multi-task deep learning network: a study on a South Korean population

Sex estimation from maxillofacial radiographs using a deep learning approach

Artificial Intelligence and Forensic Genetics: Current Applications and Future Perspectives

Contact Info

Product

Resources

About