A potential method for sex estimation of human skeletons using deep learning and three-dimensional surface scanning

Cao, Yiqi; Ma, Yonggang; Vieira, Duarte Nuno; Guo, Yucheng; Wang, Yahui; Deng, Kaifei; Chen, Yijiu; Zhang, Jianhua; Qin, Zhiqiang; Chen, Feng; Huang, Ping; Ji, Zhang

doi:10.1007/s00414-021-02675-z

Cited by 14 publications

(11 citation statements)

References 55 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similar to other studies that used different types of medical images to determine sex, the utilization of CT-scanned pelvic images had accuracies between 94% and 98.5%, whereas the lumbar spine X-ray images achieved an accuracy of 98%, and hand radiograph was able to correctly determine sex with an accuracy of 98%. 25,35,36 In this study, the superior endplate of the lumbar vertebra had the highest performance of sex determination.…”

Section: Discussionmentioning

confidence: 63%

“…In forensic anthropology, DL methods have been successfully utilized in various cases, including Bewes et al which determined sex from CT scans of human skulls and achieved 95% accuracy as well as estimated sex from the dorsal pubic region with an accuracy of 98.5%. 24,25 Nonetheless, the accuracy for the DL method of lumbar vertebrae using dry bone photographs has not been investigated. This would promote precision and facilitate personal identification.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Deep learning and morphometric approach for Sex determination of the lumbar vertebrae in a Thai population

et al. 2022

View full text Add to dashboard Cite

Sex determination is a fundamental step in biological profile estimation from skeletal remains in forensic anthropology. This study proposes deep learning and morphometric technique to perform sex determination from lumbar vertebrae in a Thai population. A total of 1100 lumbar vertebrae (L1-L5) from 220 Thai individuals (110 males and 110 females) were obtained from the Forensic Osteology Research Center, Faculty of Medicine, Chiang Mai University, Thailand. In addition, two linear measurements of superior and inferior endplates from the digital caliper and image analysis were carried out for morphometric technique. Deep learning applied image classification to the superior and inferior endplates of the lumbar vertebral body. All lumbar vertebrae images are included in the dataset to increase the number of images per class. The accuracy determined the performance of each technique. The results showed the accuracies of 82.7%, 90.0%, and 92.5% for digital caliper, image analysis, and deep learning techniques, respectively. The lumbar vertebrae L1-L5 exhibit sexual dimorphism and can be used in sex estimation. Deep learning is more accurate in determining sex than the morphometric method. In addition, the subjectivity and errors in the measurement are decreased. Finally, this study presented an alternative approach to determining sex from lumbar vertebrae when the more traditionally used skeletal elements are incomplete or absent.

show abstract

Section: Discussionmentioning

confidence: 63%

Section: Introductionmentioning

confidence: 99%

Deep learning and morphometric approach for Sex determination of the lumbar vertebrae in a Thai population

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Any update or development of medical imaging technology may help to promote the development of imaging applications in forensics. With the maturity of deep learning technology [ 84 , 85 ] and artificial intelligence [ 86 ] technologies, they are promising for potential applications as a screening tool or in computer-aided diagnostics in forensic cases.…”

Section: Advantages Disadvantages and Prospectsmentioning

confidence: 99%

Forensic Imaging: A Powerful Tool in Modern Forensic Investigation

Zhang

2022

Forensic Sciences Research

View full text Add to dashboard Cite

Forensic imaging is a non-invasive examination process during the forensic investigation. It is mainly used in forensic pathology as an adjunct to the traditional autopsy. In the past two decades, forensic imaging has been vigorously developed by forensic experts from computed tomography (CT) to multiple augmented techniques through CT and magnetic resonance imaging (MRI). The application field of forensic imaging has also been broadened as its advantages are recognised by more forensic practitioners. In addition to the forensic pathology, this technique has been used in other forensic disciplines, including forensic anthropology, forensic odontology, forensic ballistics and wildlife forensics, etc. This article reviews the development of forensic imaging as the practice and research development in different forensic disciplines based on the relevant literature analysis.

show abstract

“…A CNN is a kind of feed-forward artificial neural network created to process and classify multidimensional data such as images. 13 14 …”

Section: Introductionmentioning

confidence: 99%

Sex determination from lateral cephalometric radiographs using an automated deep learning convolutional neural network

et al. 2022

View full text Add to dashboard Cite

Purpose Despite the proliferation of numerous morphometric and anthropometric methods for sex identification based on linear, angular, and regional measurements of various parts of the body, these methods are subject to error due to the observer’s knowledge and expertise. This study aimed to explore the possibility of automated sex determination using convolutional neural networks (CNNs) based on lateral cephalometric radiographs. Materials and Methods Lateral cephalometric radiographs of 1,476 Iranian subjects (794 women and 682 men) from 18 to 49 years of age were included. Lateral cephalometric radiographs were considered as a network input and output layer including 2 classes (male and female). Eighty percent of the data was used as a training set and the rest as a test set. Hyperparameter tuning of each network was done after preprocessing and data augmentation steps. The predictive performance of different architectures (DenseNet, ResNet, and VGG) was evaluated based on their accuracy in test sets. Results The CNN based on the DenseNet121 architecture, with an overall accuracy of 90%, had the best predictive power in sex determination. The prediction accuracy of this model was almost equal for men and women. Furthermore, with all architectures, the use of transfer learning improved predictive performance. Conclusion The results confirmed that a CNN could predict a person’s sex with high accuracy. This prediction was independent of human bias because feature extraction was done automatically. However, for more accurate sex determination on a wider scale, further studies with larger sample sizes are desirable.

show abstract

A potential method for sex estimation of human skeletons using deep learning and three-dimensional surface scanning

Cited by 14 publications

References 55 publications

Deep learning and morphometric approach for Sex determination of the lumbar vertebrae in a Thai population

Deep learning and morphometric approach for Sex determination of the lumbar vertebrae in a Thai population

Forensic Imaging: A Powerful Tool in Modern Forensic Investigation

Sex determination from lateral cephalometric radiographs using an automated deep learning convolutional neural network

Contact Info

Product

Resources

About