Sex estimation using skull silhouette images from postmortem computed tomography by deep learning.
Deep learning
Personal identification
Postmortem computed tomography
Sex estimation
Silhouette images
Journal
Scientific reports
ISSN: 2045-2322
Titre abrégé: Sci Rep
Pays: England
ID NLM: 101563288
Informations de publication
Date de publication:
30 Sep 2024
30 Sep 2024
Historique:
received:
08
06
2024
accepted:
27
09
2024
medline:
1
10
2024
pubmed:
1
10
2024
entrez:
30
9
2024
Statut:
epublish
Résumé
Prompt personal identification is required during disasters that can result in many casualties. To rapidly estimate sex based on skull structure, this study applied deep learning using two-dimensional silhouette images, obtained from head postmortem computed tomography (PMCT), to enhance the outline shape of the skull. We investigated the process of sex estimation using silhouette images viewed from different angles and majority votes. A total of 264 PMCT cases (132 cases for each sex) were used for transfer learning with two deep-learning models (AlexNet and VGG16). VGG16 exhibited the highest accuracy (89.8%) for lateral projections. The accuracy improved to 91.7% when implementing a majority vote based on the results of multiple projection angles. Moreover, silhouette images can be obtained from simple and popular X-ray imaging in addition to PMCT. Thus, this study demonstrated the feasibility of sex estimation by combining silhouette images with deep learning. The results implied that X-ray images can be used for personal identification.
Identifiants
pubmed: 39349950
doi: 10.1038/s41598-024-74703-y
pii: 10.1038/s41598-024-74703-y
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
22689Subventions
Organisme : Japan Society for the Promotion of Science
ID : 19K08122
Informations de copyright
© 2024. The Author(s).
Références
University of Hawai’i News. UH forensic anthropologist assists in identifying Maui fire victims. https://www.hawaii.edu/news/2023/08/26/forensic-anthropologist-maui-fire/ (2023).
Rutty, G. N., Robinson, C. E., BouHaidar, R., Jeffery, A. J. & Morgan, B. The role of mobile computed tomography in mass fatality incidents. J. Forensic Sci.52, 1343–1349. https://doi.org/10.1111/j.1556-4029.2007.00548.x (2007).
doi: 10.1111/j.1556-4029.2007.00548.x
Rutty, G. N. et al. Remote post-mortem radiology reporting in disaster victim identification: experience gained in the 2017 Grenfell Tower disaster. Int. J. Leg. Med.134, 637–643. https://doi.org/10.1007/s00414-019-02109-x (2020).
doi: 10.1007/s00414-019-02109-x
Brough, A. L., Morgan, B. & Rutty, G. N. Postmortem computed tomography (PMCT) and disaster victim identification. Radiol. Med.120, 866–873. https://doi.org/10.1007/s11547-015-0556-7 (2015).
doi: 10.1007/s11547-015-0556-7
Ministry of Health, Labour and Welfare of Japan. The Program on Promotion of Policy about Death Investigation. https://www.mhlw.go.jp/web/t_doc?dataId=80ab7031&dataType=0&pageNo=1. (2019).
Oura, K., Ikeda, N., Yoon, Y., Kato, T. & Morishita, J. Potential for personal identification using the volume of the mastoid air cells extracted from postmortem computed tomographic images. Leg. Med.58, 102060. https://doi.org/10.1016/j.legalmed.2022.102060 (2022).
doi: 10.1016/j.legalmed.2022.102060
Heo, J. H. et al. The significance of evaluating sphenoid sinus fluid by postmortem computed tomography in cases of drowning. J. Forensic Leg. Med.97, 102551. https://doi.org/10.1016/j.jflm.2023.102551 (2023).
doi: 10.1016/j.jflm.2023.102551
Yoon, Y. et al. Image Quality using conditional generative adversarial networks for applying post-mortem computed Tomography in Forensic Pathology: a Phantom Study. J. Radiological Sci. Technol.46 (4), 315–323. https://doi.org/10.17946/JRST.2023.46.4.315 (2023).
doi: 10.17946/JRST.2023.46.4.315
Wada, Y., Morishita, J., Yoon, Y., Okumura, M. & Ikeda, N. A simple method for the automatic classification of body parts and detection of implanted metal using postmortem computed tomography scout view. Radiol. Phys. Technol.13, 378–384. https://doi.org/10.1007/s12194-020-00581-4 (2020).
doi: 10.1007/s12194-020-00581-4
Sato, M., Kondo, Y., Okamoto, M. & Takahashi, N. Development of individual identification method using thoracic vertebral features as biometric fingerprints. Sci. Rep.12 (1). https://doi.org/10.1038/s41598-022-20748-w (2022).
Packhäuser, K. et al. Deep learning-based patient reidentification is able to exploit the biometric nature of medical chest X-ray data. Sci. Rep.12 (1), 14851. https://doi.org/10.1038/s41598-022-19045-3 (2022).
doi: 10.1038/s41598-022-19045-3
pmcid: 9434540
Saukko, P. & Knight, B. Knight’s Forensic Pathology 4th editionCRC press,. (2015).
Walker, P. L. Sexing skulls using discriminant function analysis of visually assessed traits. Am. J. Phys. Anthropol.136 (1), 39–50. https://doi.org/10.1002/ajpa.20776 (2008).
doi: 10.1002/ajpa.20776
Garcovich, D., Gasco, A., Lorenzo, L. A. & Aiuto, A. Adobes Martin, M. Sex estimation through geometric morphometric analysis of the frontal bone: an assessment in pre-pubertal and post-pubertal modern Spanish population. Int. J. Legal Med.136 (1), 319–328. https://doi.org/10.1007/s00414-021-02712-x (2022).
doi: 10.1007/s00414-021-02712-x
Thurzo, A. et al. Use of advanced artificial intelligence in forensic medicine, forensic anthropology and clinical anatomy. Healthcare. 9 (11), 1545. https://doi.org/10.3390/healthcare9111545 (2021).
doi: 10.3390/healthcare9111545
pmcid: 8619074
Oner, Z., Turan, M. K., Oner, S., Secgin, Y. & Sahin, B. Sex estimation using sternum part lenghts by means of artificial neural networks. Forensic Sci. Int.301, 6–11. https://doi.org/10.1016/j.forsciint.2019.05.011 (2019).
doi: 10.1016/j.forsciint.2019.05.011
Li, Y. et al. Forensic age estimation for pelvic X-ray images using deep learning. Eur. Radiol.29 (5), 2322–2329. https://doi.org/10.1007/s00330-018-5791-6 (2019).
doi: 10.1007/s00330-018-5791-6
Pham, C. V. et al. Age estimation based on 3D post-mortem computed tomography images of mandible and femur using convolutional neural networks. PLoS One. 16 (5), e0251388. https://doi.org/10.1371/journal.pone.0251388 (2021).
doi: 10.1371/journal.pone.0251388
pmcid: 8115850
Kim, M. J. et al. Automatic cephalometric landmark identification system based on the multi-stage convolutional neural networks with CBCT combination images. Sensors. 21 (2), 505. https://doi.org/10.3390/s21020505 (2021).
doi: 10.3390/s21020505
pmcid: 7828192
Dalvit, C., da Silva, R., Jenkyn, T. R. & Carranza, V. A. Development of a convolutional neural network based skull segmentation in MRI using standard tesselation language models. J. Pers. Med.11 (4), 310. https://doi.org/10.3390/jpm11040310 (2021).
doi: 10.3390/jpm11040310
Cao, Y. et al. Use of deep learning in forensic sex estimation of virtual pelvic models from the Han population. Forensic Sci. Res.7 (3), 540–549. https://doi.org/10.1080/20961790.2021.2024369 (2022).
doi: 10.1080/20961790.2021.2024369
pmcid: 9639534
Bewes, J., Low, A., Morphett, A., Pate, F. D. & Henneberg, M. Artificial intelligence for sex determination of skeletal remains: application of a deep learning artificial neural network to human skulls. J. Forensic Leg. Med.62, 40–43. https://doi.org/10.1016/j.jflm.2019.01.004 (2019).
doi: 10.1016/j.jflm.2019.01.004
Morishita, J. & Ueda, Y. New solutions for automated image recognition and identification: challenges to radiologic technology and forensic pathology. Radiol. Phys. Technol.14 (2), 123–133. https://doi.org/10.1007/s12194-021-00611-9 (2021).
doi: 10.1007/s12194-021-00611-9
Nikita, E. & Michopoulou, E. A quantitative approach for sex estimation based on cranial morphology. Am. J. Phys. Anthropol.165 (3), 507–517. https://doi.org/10.1002/ajpa.23376 (2018).
doi: 10.1002/ajpa.23376
Nikita, E. Quantitative sex estimation based on cranial traits using R functions. J. Forensic Sci.64 (1), 175–180. https://doi.org/10.1111/1556-4029.13833 (2019).
doi: 10.1111/1556-4029.13833
Yang, W. et al. Sex Determination of Three-Dimensional Skull Based on Improved Backpropagation Neural Network. Computational and mathematical methods in medicine, 9163547 (2019). (2019)(1).
Kawazoe, Y. et al. A simple method for semi-automatic readjustment for positioning in post-mortem head computed tomography imaging. J. Forensic Radiol. Imaging. 16, 57–64. https://doi.org/10.1016/j.jofri.2019.01.004 (2019).
doi: 10.1016/j.jofri.2019.01.004
Deng, J. et al. ImageNet: a large-scale hierarchical image database. IEEE conf. Comput. Vis. Pattern Recognit. 248–255 (2009).
Krizhevsky, A., Sutskever, I. & Hinton, G. E. ImageNet classification with deep convolutional neural networks. Adv. Neural Inf. Process. Syst.25, 1097–1105 (2012).
Simonyan, K. & Zisserman, A. Very deep convolutional networks for large-scale image recognition. Preprint at. https://doi.org/10.48550/arXiv.1409.1556 (2014).
doi: 10.48550/arXiv.1409.1556
Selvaraju, R. R. et al. Grad-Cam: Visual explanations from deep networks via gradient-based localization. In Proceedings of the IEEE International Conference on Computer Vision (ICCV), 618–626 (2017).
González-Colmenares, G., Sanabria Medina, C., Rojas-Sánchez, M. P., León, K. & Malpud, A. Sex estimation from skull base radiographs in a contemporary Colombian population. J. Forensic Leg. Med.62, 77–81. https://doi.org/10.1016/j.jflm.2019.01.006 (2019).
doi: 10.1016/j.jflm.2019.01.006
Giles, E. & Elliot, O. Sex determination by discriminant function analysis of crania. Am. J. Phys. Anthropol.21 (1), 53–68. https://doi.org/10.1002/ajpa.1330210108 (1963).
doi: 10.1002/ajpa.1330210108
Ogawa, Y., Imaizumi, K., Miyasaka, S. & Yoshino, M. Discriminant functions for sex estimation of modern Japanese skulls. J. Forensic Leg. Med.20 (4), 234–238. https://doi.org/10.1016/j.jflm.2012.09.023 (2013).
doi: 10.1016/j.jflm.2012.09.023
Patil, K. R. & Mody, R. N. Determination of sex by discriminant function analysis and stature by regression analysis: a lateral cephalometric study. Forensic Sci. Int. 147(2–3), 175–180 (2005). https://doi.org/10.1016/j.forsciint.2004.09.071 Terrie, S. Skull Comparison. Sketchfab https://skfb.ly/oGrLE (2020). Licensed under CC BY 4.0. (permits sharing and adaptation with attribution).
Terrie, S. Skull Comparison. Sketchfab. Licensed under CC BY 4.0. https://skfb.ly/oGrLE (2020).
Matsunobu, Y., Morishita, J., Usumoto, Y., Okumura, M. & Ikeda, N. Bone comparison identification method based on chest computed tomography imaging. Leg. Med.29, 1–5. https://doi.org/10.1016/j.legalmed.2017.08.002 (2017).
doi: 10.1016/j.legalmed.2017.08.002
Dosovitskiy, A. et al. An image is worth 16 × 16 words: transformers for image recognition at scale. Preprint https://doi.org/10.48550/arXiv.2010.11929 (2020).
doi: 10.48550/arXiv.2010.11929