Sztuczna inteligencja w ocenie płci w medycynie sądowej: przegląd narracyjny na temat podejść uczenia maszynowego i głębokiego uczenia w różnych obszarach szkieletu
Wybierz format
RIS BIB ENDNOTEData publikacji: 15.09.2026
Problems of Forensic Sciences (Z Zagadnień Nauk Sądowych), 2026, 145, s. 25-44
https://doi.org/10.4467/12307483PFS.26.002.23947Autorzy
Artificial intelligence in forensic sex estimation: A narrative review of machine learning and deep learning approaches across skeletal regions
Introduction: With the development of artificial intelligence (AI ), especially machine learning (ML) and deep learning (DL) techniques, numerous studies have emerged that apply these methods to sex estimation based on metric and morphometric features of skeletal bones. This narrative review aims to summarise and evaluate machine learning and deep learning methods in sex estimation based on the measurements and morphometry of the pelvis, skull, long bones, and hyoid bone.
Methods: A detailed search of ML and DL techniques in sex estimation from the skeletal regions was conducted through PubMed and Scopus databases from January 2015. After the final selection, original articles, systematic reviews, and metaanalyses were analysed.
Results: ML models based on morphometric measurements of the pelvis achieved accuracy rates of 85–97.33% in various populations. DL methods, particularly Convolutional Neural Networks, eliminating the need for manual measurements, achieved accuracy rates of 99.8% for the pelvis, over 96% for the cranium, and 89% for long bones. For ML models using the hyoid bone, the accuracy rates were 69.2–95.4%, and for DL models, up to 89%. These systems provide automated sex identification with reproducible, objective, and rapid assessment. However, critical limitations persist, including data dependency and population bias, limited explainability, legal and ethical uncertainty, impracticality, and the absence of international validation standards.
Conclusions: The current state of knowledge and level of technological development indicate that AI should serve as a support tool rather than a standalone replacement for expert anthropological assessment. Its role is to enhance repeatability, minimise bias, and clarify confidence levels in skeletal sex estimation.
1. Mello-Gentil T, Souza-Mello V. Contributions of anatomy to forensic sex estimation: focus on head and neck bones. Forensic Sci Res. 2021 Jul 1;7(1):11–23. https://doi.org/10.1080/20961790.2021.1889136.
2. Ferraz AX, Schroder ÂGD, Gonçalves FM, Küchler EC , Santos RS, Zeigelboim BS, et al. Artificial intelligence model for predicting sexual dimorphism through the hyoid bone in adult patients. PLoS One. 2024;19:e0310811. https://doi.org/10.1371/journal.pone.0310811.
3. d’Oliveira Coelho J, Curate F. CA DOE S: An interactive machine-learning approach for sex estimation with the pelvis. Forensic Sci Int. 2019;302:109873. https://doi.org/10.1016/j.forsciint.2019.109873.
4. Epain M, Valette S, Zou K, Faisan S, Heitz F, Croisille P, et al. Sex estimation from coxal bones using deep learning in a population balanced by sex and age. Int J Legal Med. 2024;138:2617–23. https://doi.org/10.1007/s00414-024-03268-2.
5. Toy S, Secgin Y, Oner Z, Turan MK, Oner S, Senol D. A study on sex estimation by using machine learning algorithms with parameters obtained from computerized tomography images of the cranium. Sci Rep. 2022;12:4278. https://doi.org/10.1038/s41598-022-07415-w.
6. Imaizumi K, Usui S, Nagata T, Hayakawa H, Shiotani S. Sex-estimation method for three-dimensional shapes of the skull and skull parts using machine learning. Forensic Sci Int. 2025;373:112532. https://doi.org/10.1016/j.forsciint.2025.112532.
7. Baca K, Bridge B, Snow M. Three-dimensional geometric morphometric sex determination of the whole and modeled fragmentary human pubic bone. PLoS One. 2022;17:e0265754. https://doi.org/10.1371/journal.pone.0265754.
8. Toneva D, Nikolova S, Agre G, Zlatareva D, Hadjidekov V, Lazarov N. Machine learning approaches for sex estimation using cranial measurements. Int J Legal Med. 2021;135:951–66. https://doi.org/10.1007/s00414-020-02460-4.
9. Ferrell MJ, Schultz JJ, Adams DM. Combining morphological traits and measurements of the skull for osteological sex estimation using random forest modeling. J Forensic Sci. 2026;71:668–82. https://doi.org/10.1111/1556-4029.70241.
10. Piraianu A-I, Fulga A, Musat CL, Ciobotaru O-R, Poalelungi DG, Stamate E, et al. Enhancing the evidence with algorithms: How artificial intelligence is transforming forensic medicine. Diagnostics (Basel). 2023;13:2992. https://doi.org/10.3390/diagnostics13182992.
11. Knecht S, Krüger G, Liebenberg L, Ardagna Y, Perrin M, Ouladsine M, et al. Case-specific accuracy in sex estimation from long bones in forensic anthropology: An “accuracy x-factors” approach. Forensic Sci Int. 2026;380:112820. https://doi.org/10.1016/j.forsciint.2026.112820.
12. Nikita E, Nikitas P. Sex estimation: a comparison of techniques based on binary logistic, probit and cumulative probit regression, linear and quadratic discriminant analysis, neural networks, and naïve Bayes classification using ordinal variables. Int J Legal Med. 2020;134:1213–25. https://doi.org/10.1007/s00414-019-02148-4.
13. Kenyhercz MW, Klales AR , Stull KE, McCormick KA, Cole SJ. Worldwide population variation in pelvic sexual dimorphism: A validation and recalibration of the Klales et al. method. Forensic Sci Int. 2017;277:259.e1-259.e8. https://doi.org/10.1016/j.forsciint.2017.05.001.
14. Etli Y, Asirdizer M, Hekimoglu Y, Keskin S, Yavuz A. Sex estimation from sacrum and coccyx with discriminant analyses and neural networks in an equally distributed population by age and sex. Forensic Sci Int. 2019;303:109955. https://doi.org/10.1016/j.forsciint.2019.109955.
15. Torimitsu S, Makino Y, Saitoh H, Sakuma A, Ishii N, Yajima D, et al. Morphometric analysis of sex differences in contemporary Japanese pelves using multidetector computed tomography. Forensic Sci Int. 2015;257:530.e1-530.e7. https://doi.org/10.1016/j.forsciint.2015.10.018.
16. Cao Y, Ma Y, Vieira DN, Guo Y, Wang Y, Deng K, et al. A potential method for sex estimation of human skeletons using deep learning and three-dimensional surface scanning. Int J Legal Med. 2021;135:2409–21. https://doi.org/10.1007/s00414-021-02675-z.
17. Jerković I, Bašić Ž, Krešić E, Jerković N, Dolić K, Čavka M, et al. Developing a fully applicable machine learning (ML) based sex classification model using linear cranial dimensions. Sci Rep. 2024;14:30969. https://doi.org/10.1038/s41598-024-82073-8.
18. Ferrell MJ, Schultz JJ, Adams DM. Decision trees for estimating osteological sex from the skull using an expanded suite of morphological traits. J Forensic Sci. 2025;70:835–53. https://doi.org/10.1111/1556-4029.70017.
19. Çiftçi R, Dönmez E, Kurtoğlu A, Eken Ö, Samee NA, Alkanhel RI . Human gender estimation from CT images of skull using deep feature selection and feature fusion. Sci Rep. 2024;14:16879. https://doi.org/10.1038/s41598-024-65521-3.
20. Seo T, Yoon Y, Kim Y, Usumoto Y, Eto N, Sadamatsu Y, et al. Sex estimation using skull silhouette images from postmortem computed tomography by deep learning. Sci Rep. 2024;14:22689. https://doi.org/10.1038/s41598-024-74703-y.
21. Kondou H, Morohashi R, Kimura S, Idota N, Matsunari R, Ichioka H, et al. Artificial intelligence-based forensic sex determination of East Asian cadavers from skull morphology. Sci Rep. 2023;13:21026. https://doi.org/10.1038/s41598-023-48363-3.
22. Bu W, Guo Y, Zhang D, Du S, Han M, Wu Z, et al. Automatic sex estimation using deep convolutional neural network based on orthopantomogram images. Forensic Sci Int. 2023;348:111704. https://doi.org/10.1016/j.forsciint.2023.111704.
23. Sevinc O, Mehrubeoglu M, Yılmaz AA , Derrick S. Forensic identification using siamese, transfer learning and custom deep learning models. Sci Rep. 2025;16:890. https://doi.org/10.1038/s41598-025-30703-0.
24. Blanc M, Knecht S, Nguyen K, Poulain C, Quatrehomme G, Alunni V, et al. Sexual dimorphism of the humerus bones in a French sample: comparison of several statistical models including machine learning models. Int J Legal Med. 2025;139:1395–408. https://doi.org/10.1007/s00414-025-03417-1.
25. Çayabatmaz B, Oner Z, Oner S, Secgin Y. Traditional sex estimation with parameters obtained from the distal end of the humerus: an example of using machine learning algorithms in morphometric studies. Egypt J Forensic Sci. 2026;16:5. https://doi.org/10.1186/s41935-025-00504-7.
26. Bertsatos A, Flouri D, Papadomanolakis A, Kranioti E, Aguilera M, Valakos E, et al. An automated sex estimation method for lower and upper limbs from European populations. Open Research Europe. 2025;5:188. https://doi.org/10.12688/openreseurope.20513.1.
27. Knecht S, Morandini P, Biehler-Gomez L, Ouladsine M, Roman C, Cattaneo C, et al. Population-specific validation of long bone linear discriminant analysis against morphoscopic pelvic methods for sex estimation in contemporary Italian skeletal remains. J Forensic Sci. 2026 Feb;71(3):1388–1397. https://doi.org/10.1111/1556-4029.70293.
28. Venema J, Peula D, Irurita J, Mesejo P. Employing deep learning for sex estimation of adult individuals using 2D images of the humerus. Neural Comput Appl. 2022;35:1–12. https://doi.org/10.1007/s00521-022-07981-0.
29. Li Y, Niu C, Wang J, Xu Y, Dai H, Xiong T, et al. A fully automated sex estimation for proximal femur X-ray images through deep learning detection and classification. Leg Med. 2022;57:102056. https://doi.org/10.1016/j.legalmed.2022.102056.
30. Demet Mutlu G, Asirdizer M, Kartal E, Keskin S, Mutlu İ, Goya C. Sex estimation from the hyoid bone measurements in an adult Eastern Turkish population using 3D CT images, discriminant function analysis, support vector machines, and artificial neural networks☆. Leg Med (Tokyo). 2024;67:102383. https://doi.org/10.1016/j.legalmed.2023.102383.
31. Abdelkader A, Ali SA, Abdeen A, Taher ES, Hussein AYA , Eldesoqui M, et al. Hyoid bone-based sex discrimination among Egyptians using a multidetector computed tomography: discriminant function analysis, meta-analysis, and artificial intelligence-assisted study. Sci Rep. 2025;15:2680. https://doi.org/10.1038/s41598-025-85518-w.
32. Tyagi A, Tiwari P, Bhardwaj P, Chawla H. Prognosis of sexual dimorphism with unfused hyoid bone: Artificial intelligence informed decision making with discriminant analysis. Sci Justice. 2021;61:789–96. https://doi.org/10.1016/j.scijus.2021.10.002.
33. Beltran-Aroca CM, Checa-Poza A, De-La-Barrera-Aranda E, Girela-Lopez E, Trujillo-Mederos A, Romero-Saldaña M. Is there sufficient evidence that the hyoid bone can be used for sexual dimorphism? a systematic review and meta-analysis. Int J Leg Med. 2026. https://doi.org/10.1007/s00414-026-03722-3.
34. Jerković I, Bašić Ž, Kružić I. Deep learning-based sex estimation of 3D hyoid bone models in a C roatian population using adapted PointNet++ network. Sci Rep. 2025;15:22728. https://doi.org/10.1038/s41598-025-07608-z.
35. Bakici RS, Cakmak M, Oner Z, Oner S. Sex prediction of hyoid bone from computed tomography images using the DenseNet121 deep learning model. Int J Morphol. 2024;42:826–32. https://doi.org/10.4067/s0717-95022024000300826.
Informacje: Problems of Forensic Sciences (Z Zagadnień Nauk Sądowych), 2026, 145, s. 25-44
Typ artykułu: Oryginalny artykuł naukowy
Tytuły:
Publikacja: 15.09.2026
Otrzymano: 27.04.2026
Zaakceptowano: 18.07.2026
Status artykułu: Otwarte
Licencja: CC BY-NC-ND 4.0
Udział procentowy autorów:
Korekty artykułu:
-Języki publikacji:
Angielski, PolskiLiczba wyświetleń: 107
Liczba pobrań: 79
