Возможности использования нейросетей в судебной медицине

Введение. Современные вызовы, связанные с ростом объема данных в различных сферах человеческой деятельности, требуют внедрения инновационных методов анализа, среди которых особое место занимает искусственный интеллект (ИИ). В медицине технологии машинного обучения активно применяются для автоматизации диагностики, прогнозирования заболеваний и обработки медицинских изображений. Судебно-медицинская экспертиза также начинает использовать нейросетевые алгоритмы для повышения точности и скорости исследований.

Цель работы – изучить современные подходы к использованию ИИ в судебно-медицинской экспертизе и смежных областях на основании литературных данных за последние 10 лет.

Материалы и методы. Анализ и систематизация научных публикаций, размещенных в базах данных PubMed, Scopus, Web of Science, eLibrary.ru, «КиберЛенинка» за 2015–2024 гг. (имеется менее 5 % источников за 2008–2014 гг.) по поисковым словам artificial intelligence, forensic examination, machine learning. Обнаружено 98 источников, по критериям включения отобрано 62.

Результаты и обсуждение. Ключевые направления применения нейросетей в судебной медицине включают в себя идентификацию личности, в т. ч. по черепу, зубному статусу и ДНК, анализ повреждений, обработку биометрических данных, статистическую обработку медицинской информации для выявления скрытых закономерностей. Использование компьютерного зрения позволяет автоматизировать анализ фото- и видеоматериалов с мест преступлений, а прогнозные модели на основе ИИ помогают в установлении времени наступления смерти и определении факторов, влияющих на исход судебно-медицинских исследований. Однако внедрение нейросетей в экспертную практику требует решения ряда проблем, включая валидацию алгоритмов, обеспечение достоверности результатов, соблюдение этико-правовых норм.

Заключение. Таким образом, применение нейросетей в судебной медицине, хотя обладает потенциалом, сегодня ограничено необходимостью дорогостоящей инфраструктуры, риском алгоритмических предубеждений и отсутствием правовой базы. Внедрение ИИ возможно лишь как часть комплексного исследования при обязательном контроле со стороны эксперта-человека.

1. Vodanović M, Subašić M, Milošević DP, Galić I, Brkić H. Artificial intelligence in forensic medicine and forensic dentistry. The Journal of Forensic Odonto-Stomatology. 2023;41(2):30–41. PMID: https://pubmed.gov/37634174.

2. Kokin AV. Forensic expertise in the era of the fourth industrial revolution (Industry 4.0). Theory and Practice of Forensic Science. 2021;16(2):29–36. (In Russ.). DOI: https://doi.org/10.30764/1819-2785-2021-2-29-36.

3. Sunde N, Dror IE. A hierarchy of expert performance (HEP) applied to digital forensics: Reliability and biasability in digital forensics decision making. Forensic Science International: Digital Investigation. 2021;37:301175. DOI: https://doi.org/10.1016/j.fsidi.2021.301175.

4. Hmyz AI. Using the power of artificial intelligence in judicial expertise. Bulletin of Economic Security. 2022;(5):224–227. (In Russ.). DOI: https://doi.org/10.24412/2414-3995-2022-5-224-227.

5. Fang YT, Lan Q, Xie T, Liu YF, Mei SY, Zhu BF. New opportunities and challenges for forensic medicine in the era of artificial intelligence technology. Fa Yi Xue Za Zhi. 2020;36(1):77–85. (In Chinese). DOI: https://doi.org/10.12116/j.issn.1004-5619.2020.01.016.

6. Fedorenko VA, Sorokina KO, Giverts PV. Classification of firing pin marks images by weapon specimens using a fully-connected neural networks. Izvestiya of Saratov University. Economics. Management. Law. 2022; 22(2):184–190. (In Russ.). DOI: https://doi.org/10.18500/1994-2540-2022-22-2-184-190.

7. Sorokina KO, Fedorenko VA, Giverts PV. Identification of similar images of breech face impressions by the correlation cells method. Izvestiya of Saratov University. Economics. Management. Law. 2020;20(2):203–209. (In Russ.). DOI: https://doi.org/10.18500/1994-2540-2020-20-2-203-209.

8. Kamshad M. Artificial intelligence in forensic science. International Journal of Forensic Research. 2021; 4(1):172–173. DOI: https://doi.org/10.2139/ssrn.3910244.

9. Chen CY, Tseng PK. The boundary of artificial intelligence in forensic science. Dialogo. 2023;10(1):83–90. DOI: https://doi.org/10.51917/dialogo.2023.10.1.5.

10. Ponkin IV, Redkina AI. Artificial intelligence from the point of view of law. RUDN Journal of Law. 2018; 22(1):91–109. (In Russ.). DOI: https://doi.org/10.22363/2313-2337-2018-22-1-91-109.

11. Poskryakov RS. The use of artificial intelligence in judicial work. Ogarev-Online. 2019;(16):2. (In Russ.). EDN: https://elibrary.ru/VGMMPE.

12. Smith RT, Clarke TJ, Mayer W, Cunningham A, Matthews B, Zucco JE. Mixed reality interaction and presentation techniques for medical visualisations. In: Rea PM (ed.). Biomedical visualisation. Advances in experimental medicine and biology, vol. 1320. Cham: Springer; 2020. P. 123–139. DOI: https://doi.org/10.1007/978-3-030-47483-6_7.

13. Remez AI, Mayer AO, Yasnov AO. Artificial intelligence approaches in histology. Laboratory Service. 2022; 11(2):56–58. (In Russ.). DOI: https://doi.org/10.17116/labs20221102156.

14. Latfullina DR. The human mind and artificial intelligence. In: Uchenye zapiski. Vol. XIV. Collection of articles by teachers of the Kazan Branch of the Russian State University of Justice. Kazan: Otechestvo; 2018. P. 512–516. (In Russ.). EDN: https://elibrary.ru/XZRRRR.

15. Tomakova RA, Filist SA, Gorbatenko SA, Shvetsova NA. Analysis of histological images using morphological operators synthesized on the basis of Fourier transform and neural network modeling. Biotechnosphere. 2010;(3):54–60. (In Russ.). EDN: https://elibrary.ru/SZBSLB.

16. Shortliffe E, Buchanan B. A model of inexact reasoning in medicine. Mathematical Biosciences. 1975;23(3–4): 351–379. DOI: https://doi.org/10.1016/0025-5564(75)90047-4.

17. Tournois L, Trousset V, Hatsch D, Delabarde T, Ludes B, Lefevre T. Artificial intelligence in the practice of forensic medicine: A scoping review. Internal Journal of Legal Medicine. 2024;138(3):1023–1037. DOI: https://doi.org/10.1007/s00414-023-03140-9.

18. Rossinskaya ER. Neural networks in forensic expertology and expert practice: Problems and prospects. Courier of Kutafin Moscow State Law University. 2024;(3):21–33. (In Russ.). https://doi.org/10.17803/2311-5998.2024.115.3.021-033.

19. Klevno VA, Maximov AV. The question of classification and terminology of expert errors. Russian Journal of Forensic Medicine. 2017;3(2):8–11. (In Russ.). DOI: https://doi.org/10.19048/2411-8729-2017-3-2-8-11.

20. Johnson J, Khoshgoftaar T. Survey on deep learning with class imbalance. Journal of Big Data. 2019;6:27. DOI: https://doi.org/10.1186/s40537-019-0192-5.

21. Lefevre T, Tournois L. Artificial intelligence and diagnostics in medicine and forensic science. Diagnostics. 2023;13(23):3554. DOI: https://doi.org/10.3390/diagnostics13233554.

22. Fernandes K, Cardoso JS, Astrup BS. A deep learning approach for the forensic evaluation of sexual assault. Pattern Analysis and Applications. 2018;21(3):629–640. DOI: https://doi.org/10.1007/s10044-018-0694-3.

23. El-Din EAA. Artificial intelligence in forensic science: Invasion or revolution? Egyptian Society of Clinical Toxicology Journal. 2022;10(2):20–32. DOI: https://doi.org/10.21608/esctj.2022.158178.1012.

24. Morkhat PM. On the issue of the legal understanding of artificial intelligence. Agrarian and Land Law. 2017;(11):89–95. (In Russ.). EDN: https://elibrary.ru/XQJVRB.

25. Wankhade TD, Ingale SW, Mohite PM, Bankar NJ. Artificial intelligence in forensic medicine and toxicology: The future of forensic medicine. Cureus. 2022;14(8):e28376. DOI: https://doi.org/10.7759/cureus.28376.

26. Thurzo A, Kosnáčová HS, Kurilová V, Kosmeľ S, Beňuš R, Moravanský N, et al. Use of advanced artificial intelligence in forensic medicine, forensic anthropology and clinical anatomy. Healthcare. 2021;9(11):1545. DOI: https://doi.org/10.3390/healthcare9111545.

27. Matsuda S, Yoshimura H. Personal identification with artificial intelligence under COVID‑19 crisis: A scoping review. Systematic Reviews. 2022;11:7. DOI: https://doi.org/10.1186/s13643-021-01879‑z.

28. Livingston M. Preventing racial bias in federal AI. Journal of Science Policy & Governance. 2020;16(2). DOI: https://doi.org/10.38126/JSPG160205.

29. Obermeyer Z, Powers B, Vogeli C, Mullainathan S. Dissecting racial bias in an algorithm used to manage the health of populations. Science. 2019;366(6464):447–453. DOI: https://doi.org/10.1126/science.aax2342.

30. Liew SS, Khalil-Hani M, Radzi F, Bakhteri R. Gender classification: A convolutional neural network approach. Turkish Journal of Electrical Engineering and Computer Sciences. 2016;24(3):1248–1264. DOI: https://doi.org/10.3906/elk‑1311-58.

31. Ortega RF, Irurita J, Campo EJE, Mesejo P. Analysis of the performance of machine learning and deep learning methods for sex estimation of infant individuals from the analysis of 2D images of the ilium. International Journal of Legal Medicine. 2021;135:2659–2666. DOI: https://doi.org/10.1007/s00414-021-02660-6.

32. Porto LF, Lima LNC, Franco A, Pianto D, Machado CEP, Vidal FB. Estimating sex and age from a face: A forensic approach using machine learning based on photo-anthropometric indexes of the Brazilian population. International Journal of Legal Medicine. 2020;134(6):2239–2259. DOI: https://doi.org/10.1007/s00414-020-02346-5.

33. Saini M, Anup KK. Biometrics in forensic identification: Applications and challenges. Journal of Forensic Medicine. 2016;1(2):1000108. Available from: https://clck.ru/3QRkCa (accessed 5 May 2025).

34. Zhu YZ, Zhang J, Cheng Q, Deng KF, Ma KJ, Zhang JH, et al. Research progress of automatic diatom test by artificial intelligence. Fa Yi Xue Za Zhi. 2022;38(1):14–19. (In Chinese). DOI: https://doi.org/10.12116/j.issn.1004-5619.2021.410404.

35. Lin HH, Chiang WC, Yang CT, Cheng CT, Zhang T, Lo LJ. On construction of transfer learning for facial symmetry assessment before and after orthognathic surgery. Computer Methods and Programs in Biomedicine. 2021;200:105928. DOI: https://doi.org/10.1016/j.cmpb.2021.105928.

36. Dalvit Carvalho da Silva R, Jenkyn TR, Carranza VA. Development of a convolutional neural network based skull segmentation in MRI using standard tesselation language models. Journal of Personalized Medicine. 2021;11(4):310. DOI: https://doi.org/10.3390/jpm11040310.

37. Lee SM, Kim HP, Jeon K, Lee SH, Seo JK. Automatic 3D cephalometric annotation system using shadowed 2D image-based machine learning. Physics in Medicine and Biology. 2019;64(5):055002. DOI: https://doi.org/10.1088/1361-6560/ab00c9.

38. Leonov SV, Kosukhina OI, Shakiryanova YP. Practical experience in training artificial neural networks for forensic medicine. In: Avdeev AI, Vlasyuk IV (eds.). Selected issues of forensic medical examination. Issue 21. Khabarovsk: Editorial and Publishing Center of Postgraduate Institute; 2022. P. 55–58. (In Russ.). EDN: https://elibrary.ru/DVZBYE.

39. Voyevodkin DV, Rustemova GR, Begaliyev YN, Igembayev KA, Ayupova ZN. Identifying fake conclusions of forensic medical examinations using an artificial intelligence technology based on the experience in the Republic of Kazakhstan: A review. Russian Journal of Forensic Medicine. 2023;9(3):287–298. (In Russ.). DOI: https://doi.org/10.17816/fm8270.

40. Kokin AV, Denisov YD. Artificial intelligence in criminalistics and forensic examination: Issues of legal personality and algorithmic bias. Theory and Practice of Forensic Examination. 2023;18(2):30–37. (In Russ.). DOI: https://doi.org/10.30764/1819-2785-2023-2-30-37.

41. Perepechina IO. Some new possibilities of DNA (RNA)-diagnostics. Bulletin of Economic Security. 2019;(2):214–219. (In Russ.). EDN: https://elibrary.ru/WLZPGC.

42. Kraeva YV, Rozhkova VR. DNA phenotyping: Problems and prospects. Issues of Russian Justice. 2021;(11):440–444. (In Russ.). EDN: https://elibrary.ru/UQTICA.

43. Popova AY, Gazhonova VE, Kartashov MV, Shevchenko SA, Belova OS. Radiomics in the radiation diagnosis of biological subtypes of breast cancer. Ural Medical Journal. 2024;23(4):41–56. (In Russ.). DOI: https://doi.org/10.52420/umj.23.4.41.

44. Remez AI, Zhuravlev AS, Fattakhov AO, Pavlova VA. Digital pathology in Russia: Experience and prospects. Russian Medical Journal. Medical Review. 2018;2(6):19–21. (In Russ.). EDN: https://elibrary.ru/XZRSMP.

45. Esmaeilyfard R, Paknahad M, Dokohaki S. Sex classification of first molar teeth in cone beam computed tomography images using data mining. Forensic Science International. 2021;318:110633. DOI: https://doi.org/10.1016/j.forsciint.2020.110633.

46. Borbat AM. Neural networks for morphological diagnostics. Clinical and Experimental Morphology. 2020; 9(2):11–15. DOI: https://doi.org/10.31088/CEM2020.9.2.11-15.

47. Sharma H, Zerbe N, Klempert I, Hellwich O, Hufnagl P. Deep convolutional neural networks for automatic classification of gastric carcinoma using whole slide images in digital histopathology. Computerized Medical Imaging and Graphics. 2017;61:2–13. DOI: https://doi.org/10.1016/j.compmedimag.2017.06.001.

48. Feng Y, Zhang L, Yi Z. Breast cancer cell nuclei classification in histopathology images using deep neural networks. International Journal of Computer Assisted Radiology and Surgery. 2018;13(2):179–191. DOI: https://doi.org/10.1007/s11548-017-1663-9.

49. Ker J, Bai Y, Lee HY, Rao J, Wang L. Automated brain histology classification using machine learning. Journal of Clinical Neuroscince. 2019;66:239–245. DOI: https://doi.org/10.1016/j.jocn.2019.05.019.

50. Alom MZ, Yakopcic C, Nasrin MS, Taha TM, Asari VK. Breast cancer classification from histopathological images with inception recurrent residual convolutional neural network. Journal of Digital Imaging. 2019;32:605–617. DOI: https://doi.org/10.1007/s10278-019-00182-7.

51. Yan R, Ren F, Wang Z, Wang L, Zhang T, Liu Y, et al. Breast cancer histopathological image classification using a hybrid deep neural network. Methods. 2019;173:52–60. DOI: https://doi.org/10.1016/j.ymeth.2019.06.014.

52. Hekler A, Utikal JS, Enk AH, Solass W, Schmitt A, Klode J, et al. Deep learning outperformed 11 pathologists in the classification of histopathological melanoma images. European Journal of Cancer. 2019;118: 91–96. DOI: https://doi.org/10.1016/j.ejca.2019.06.012.

53. Ehteshami BB, Veta M, Johannes van Diest P, van Ginneken B, Karssemeijer N, Litjens G, et al. Diagnostic assessment of deep learning algorithms for detection of lymph node metastases in women with breast cancer. JAMA. 2017;318(22):2199–2210. DOI: https://doi.org/10.1001/jama.2017.14585.

54. Liu Y, Kohlberger T, Norouzi M, Dahl GE, Smith JL, Mohtashamian A, et al. Artificial intelligence-based breast cancer nodal metastasis detection. Archives of Pathology & Laboratory Medicine. 2019;143(7): 859–868. DOI: https://doi.org/10.5858/arpa.2018-0147‑OA.

55. Polyakov VV. On using the concept of “artificial intelligence” in forensic science. Legal Linguistics. 2022;(25):21–28. (In Russ.). DOI: https://doi.org/10.14258/leglinleglin(2022)2504.

56. Malcev VA, Murzhina AS, Suchkova TE. Using artificial intelligence capabilities in forensic activities. Problems of Contemporary Science and Practice. 2023;(2):21–26. (In Russ.). EDN: https://elibrary.ru/IQNRDF.

57. Galante N, Cotroneo R, Furci D, Lodetti G, Casali MB. Applications of artificial intelligence in forensic sciences: Current potential benefits, limitations and perspectives. International Journal of Legal Medicine. 2023;137(2):445–458. DOI: https://doi.org/10.1007/s00414-022-02928-5.

58. Zubova YV. The use of artificial intelligence as a tool to counter crime. In: Avdeev AI, Rozenko SV (eds.). Strategic directions for countering crime at national and transnational levels. Iss. 6. Khanty-Mansiysk; 2023. P. 307–310. (In Russ.). EDN: https://elibrary.ru/YNLUPO.

59. Mazurov VA, Starodubtseva MA. Artificial intelligence as a means for forecasting and countering crime. Russian-Asian Law Journal. 2019;(3):46–50. (In Russ.). EDN: https://elibrary.ru/ZSGNNB.