Preview

Proceedings of the Institute for System Programming of the RAS (Proceedings of ISP RAS)

Advanced search

Use of Genetic Algorithms and Neural Networks in the Analysis of Foot Deformities

https://doi.org/10.15514/ISPRAS-2024-36(3)-17

Abstract

The work is devoted to the current problem of diagnosing foot deformities, which are characterized by a high incidence among all age groups. Among the objective quantitative methods for diagnosing flatfoot, plantography, based on the assessment of prints of the plantar surface of the foot, has become widespread in clinical practice. The purpose of the study was to evaluate and analyze the effectiveness of methods for automatic assessment of footprints using “computer vision”. The study examines methods for automatic recognition and marking of photoplantograms of the foot using genetic algorithms and neural networks to construct control points of the foot using the example of calculating the indices of the longitudinal and transverse arches of the foot. A comparison was made of the results of calculating flatfoot indices and photoplantograms using manual and automatic markings. It was found that the accuracy of automatic methods for analyzing photoplantograms using genetic algorithms and neural networks is 92–97% in relation to manual marking. At the same time, the time spent on manual marking exceeded the duration of automatic image analysis by 2 - 2.5 times. The results obtained confirmed the possibility of optimizing the diagnostic process when conducting mass (screening) examinations of the condition of the arches of the feet.

About the Authors

Sergey Ivanovich KIREEV
Saratov National Research State University named after N.G. Chernyshevsky
Russian Federation

Dr. Sci. (Medicine), Associate Professor. Area of scientific interests: methods of treating foot deformities, joint pathologies, spinal pathologies, limitation of joint mobility due to the consequences of injuries and diseases of the nervous system.



Inna Aleksandrovna BATRAEVA
Saratov National Research State University named after N.G. Chernyshevsky
Russian Federation

Cand. Sci. (Phys.-Math.), Associate Professor, Head of the Department of Programming Technologies, Faculty of Computer Science and Information Technologies, SSU. Areas of scientific and practical interests: compiler theory, information systems and data analysis in applied linguistics, computer vision and data analysis in medicine.



Dmitry Sergeevich PANTELEEV
Saratov National Research State University named after N.G. Chernyshevsky
Russian Federation

Master student in software and administration of information networks, Faculty of Computer Science and Information Technology, SSU. Areas of scientific and practical interests: database management systems, graph models and graph analysis algorithms in finance, computer vision and data analysis in medicine.



Maxim Vladislavovitch ZABOEV
Saratov National Research State University named after N.G. Chernyshevsky
Russian Federation

Bachelor in fundamental computer science and information technology, Faculty of Computer Science and Information Technology, SSU. Areas of scientific and practical interests: database management systems, graph models and graph analysis algorithms in finance, computer vision and data analysis in medicine.



References

1. Babovi´c, S.S.; Vujovi´c, M.; Stilinovi´c, N.P.; Jefti´c, O.; Novakovi´c, A.D. Labeling of Baropodometric Analysis Data Using Computer Vision Techniques in Classification of Foot Deformities. Medicina 2023, 59, 840. https://doi.org/10.3390/ medicina59050840

2. Chae J, Kang YJ, Noh Y. A Deep-Learning Approach for Foot-Type Classification Using Heterogeneous Pressure Data. Sensors (Basel). 2020 Aug 11;20(16):4481. doi: 10.3390/s20164481. PMID: 32796568; PMCID: PMC7472491.

3. Oliveira FP, Sousa A, Santos R, Tavares JM. Towards an efficient and robust foot classification from pedobarographic images. Comput Methods Biomech Biomed Engin. 2012;15(11):1181-8. doi: 10.1080/10255842.2011.581239. Epub 2011 Jun 8. PMID: 21660782.

4. Maestre-Rendon JR, Rivera-Roman TA, Sierra-Hernandez JM, Cruz-Aceves I, Contreras-Medina LM, Duarte-Galvan C, Fernandez-Jaramillo AA. Low Computational-Cost Footprint Deformities Diagnosis Sensor through Angles, Dimensions Analysis and Image Processing Techniques. Sensors (Basel). 2017 Nov 22;17(11):2700. doi: 10.3390/s17112700. PMID: 29165397; PMCID: PMC5713009.

5. Гилязев Р. А., Турдаков Д. Ю. Активное обучение и краудсорсинг: обзор методов оптимизации разметки данных. Труды ИСП РАН, том 30, вып. 2, 2018 г., стр. 215–250. DOI: 10.15514/ISPRAS-2018-30(2)-11. / Gilyazev R.A., Turdakov D.Y. Active learning and crowdsourcing: a survey of annotation optimization methods. Trudy ISP RAN/Proc. ISP RAS, 2018, vol. 30, issue 2, pp. 215-250. (in Russian). DOI:10.15514/ISPRAS-2018-30(2)-11.

6. Береснев А. П., Зоев И. В., Марков Н. Г. Исследование свёрточных нейронных сетей класса yolo для мобильных систем детектирования объектов на изображениях. 28-я Международная конференция по компьютерной графике и машинному зрению. Труды конференции. 2018, стр. 196-199. / Beresnev A. P., Zoev I. V., Markov N. G. Study of convolutional neural networks of the yolo class for mobile systems for detecting objects in images. 28th International Conference on Computer Graphics and Computer Vision. Proceedings of the conference. 2018, pp. 196-199. (in Russian). Доступно по ссылке: https://www.graphicon.ru/html/2018/papers/proceedings.pdf. 14.04.2024.

7. Polaka I., Sudars K., Namatevs I. Automatic data labeling by neural networks for the counting of objects in videos. Procedia Computer Science, 2019, issue 149, pp. 151–158. DOI: 10.1016/j.procs.2019.01.118. Доступно по ссылке: https://www.researchgate.net/publication/331694901_Automatic_data_labeling_by_neural_networks_for_the_counting_of_objects_in_videos, 14.04.2024.

8. Батраева И.А., Беликов А.В., Ионкина И.А., Забоев М.В., Миронов С.В., Пантелеев Д.С., Шапкин Ю.Г. Проблемы подготовки данных для анализа медицинских снимков. Методы компьютерной диагностики в биологии и медицине - 2023. Сборник статей Всероссийской школы-семинара. Саратов, 2023. стр. 192-194. / Batraeva I.A., Belikov A.V., Ionkina I.A., Zaboev M.V., Mironov S.V., Panteleev D.S., Shapkin Yu.G. Problems of preparing data for analyzing medical images. Methods of computer diagnostics in biology and medicine - 2023. Collection of articles of the All-Russian school-seminar. Saratov, 2023. pp. 192-194. (in Russian). Доступно по ссылке: https://www.elibrary.ru/item.asp?id=55822502/.

9. Пантелеев Д.С., Киреев С.И., Фалькович А.С., Батраева И.А., Забоев М.В., Чабукиани П.М. Программа для анализа и оценки плантографических критериев состояния (деформации) стопы "Подовизир". Свидетельство о регистрации программы для ЭВМ RU 2023682484, 25.10.2023. / Panteleev D.S., Kireev S.I., Falkovich A.S., Batraeva I.A., Zaboev M.V., Chabukiani P.M. A program for analyzing and assessing plantographic criteria for the condition (deformation) of the foot "Podovisir". Certificate of registration of the computer program RU 2023682484, 10/25/2023. (in Russian). Доступно по ссылке: https://www.elibrary.ru/item.asp?id=56001622/.

10. Смирнова Л. М., Аржанникова Е. Е., Карапетян С. В., Гаевская О. Э. Методика использования комплексов серии «Скан» при диагностике состояния стопы и назначении ортопедических стелек. СПб: ООО «ЦИАЦАН», 2015, 75 с. / Methodology for using the Scan series complexes in diagnosing foot conditions and prescribing orthopedic insoles: method. manual / Smirnova L. M., Arzhannikova E. E., Karapetyan S. V., Gaevskaya O. E. St. Petersburg: LLC “CIATSAN”, 2015, 75 p. (in Russian)

11. Akambase Jonas, Kokoreva Tatyana, Gurova Olga, Akambase Joseph. The effect of body positions on foot types: Considering body weight. Translational Research in Anatomy, 2019, vol. 16, pp. 1048-1053. DOI:10.1016/j.tria.2019.100048. (in Russian). Доступно по ссылке: https://www.sciencedirect.com/science/article/pii/S2214854X19300470/.

12. Вирсански Эйял. Генетические алгоритмы на Python. М.: ДМК-Пресс, 2020, стр. 286. / Virsanski Eyal. Genetic algorithms in Python. M.: DMK-Press, 2020, p. 286. (in Russian).

13. Веденяпин Д.А., Лосев А.Г. Применение искусственных нейронных сетей в диагностике венозных заболеваний. Вестник новых медицинских технологий, том XIX, вып 2, 2012, стр. 241. / Vedenyapin D.A., Losev A.G. Application of artificial neural networks in the diagnosis of venous diseases. Bulletin of new medical technologies, volume XIX, issue 2, 2012, p. 241. (in Russian). Доступно по ссылке: https://cyberleninka.ru/article/n/primenenie-iskusstvennyh-neyronnyh-setey-v-diagnostike-venoznyh-zabolevaniy

14. Провоторов В.М., Шалагина И.В., Демъяшкин В.А. Использование нейросетевых методов для решения вопросов дифференциальной диагностики при затяжных пневмониях. Пульмонология, 2003, вып.4, стр. 36-40 / Provotorov V.M., Shalagina I.V., Demyashkin V.A. The use of neural network methods to solve issues of differential diagnosis in prolonged pneumonia. Pulmonology, 2003, issue 4, pp. 36-40. (in Russian). Доступно по ссылке: https://journal.pulmonology.ru/pulm/article/view/2639

15. Ионкина И.А., Беликов А.В., Шапкин Ю.Г., Пантелеев Д.С., Батраева И.А., Миронов С.В., Тышкевич С.В. Применение ИТ-технологий в анализе эндоизображений при диагностике рецидивов желудочно-кишечных кровотечений. Материалы Международной конференции молодых ученых «Фундаментальная и прикладная медицина». Саратов, 2023, стр. 109-111. (in Russian). / Ionkina I.A., Belikov A.V., Shapkin Yu.G., Panteleev D.S., Batraeva I.A., Mironov S.V., Tyshkevich S.V. Application of IT technologies in the analysis of endoimages in the diagnosis of recurrent gastrointestinal bleeding. Proceedings of the International Conference of Young Scientists “Fundamental and Applied Medicine”. Saratov, 2023, pp. 109-111. (in Russian). Доступно по ссылке: https://elibrary.ru/item.asp?id=60363677


Review

For citations:


KIREEV S.I., BATRAEVA I.A., PANTELEEV D.S., ZABOEV M.V. Use of Genetic Algorithms and Neural Networks in the Analysis of Foot Deformities. Proceedings of the Institute for System Programming of the RAS (Proceedings of ISP RAS). 2024;36(3):241-258. (In Russ.) https://doi.org/10.15514/ISPRAS-2024-36(3)-17



Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.


ISSN 2079-8156 (Print)
ISSN 2220-6426 (Online)