Planimetric wound assessment using neural network technology

In clinical practice, one of the key methods for monitoring the effectiveness of soft tissue wound treatment is the assessment of wound surface area. Neural network technologies represent a promising approach for calculating wound surface area, identifying signs of wound healing progression, and planning personalized treatment according to clinical dynamics.

Purpose of the study. To analyze the results of wound surface area measurements obtained using the WoundVision software.

Materials and methods. The study was conducted in three stages: bench testing using schematic wounds and wound models, experimental testing in laboratory animals, and clinical evaluation in patients with trophic ulcers. The accuracy of wound surface area assessment was compared using the L. N. Popova method, ImageJ, UniversalDesktopRuler, and WoundVision computer software, as well as the ImitoWound mobile application.

Results. The accuracy of wound area calculation was found to depend on contour shape and surface curvature. ImageJ and UniversalDesktopRuler systematically underestimated measurements, with an average accuracy of 80–88 %. The ImitoWound application demonstrated stable results with an average accuracy of 92 %, although its performance decreased on curved surfaces. Due to the implementation of neural network technologies and 3D scanning, the WoundVision software demonstrated the best results across all study groups. When using WoundVision, the mean accuracy of wound area measurements was 98.27 ± 0.65 % for schematic wounds, 99.19 ± 0.49 % for wound models, 98.52 ± 4.17 % for wounds in laboratory animals, and 98.52 ± 4.17 % for trophic ulcers in patients.

Conclusion. The developed WoundVision software demonstrated the highest accuracy among the evaluated methods. However, several limitations remain, including the need for a specialized camera. Nevertheless, the L. N. Popova method remains the most accurate currently available technique, although it is labor-intensive because of the time required for its implementation and its practical limitations.

1. Kaye KS, Petty LA, Shorr AF, Zilberberg MD. Current Epidemiology, Etiology, and Burden of Acute Skin Infections in the United States. Clin Infect Dis. 2019 Apr 8;68(Suppl 3):S193–S199. https://doi.org/10.1093/cid/ciz002

2. Wang W, Meng Q, Li Q, Liu J, Zhou M, Jin Z, Zhao K. Chitosan Derivatives and Their Application in Biomedicine. Int J Mol Sci. 2020 Jan 12;21(2):487. https://doi.org/10.3390/ijms21020487

3. International Wound Infection Institute (IWII) Wound Infection in Clinical Practice. Wounds International. 2022. Available at: https://woundsinternational.com/wp-content/uploads/2023/05/IWII-CD-2022-web.pdf Accessed: 06.05.2026.

4. Williams M. Wound infections: an overview. Br J Community Nurs. 2021 Jun 1;26(Sup6):S22–S25. https://doi.org/10.12968/bjcn.2021.26.sup6.s22

5. Grigoryan A.Yu. Application of factor analysis in studying the efficiency of local treatment of purulent wounds of the skin and soft tissues. Tver Medical Journal 2023;4:78–80. (In Russ.). EDN: OTOLMR

6. Ibraheem WI, Bhati AK, Hakami NA, Alshehri AD, Wadani MHM, Ageeli FME. Comparison of Digital Planimetry and Ruler Methods for the Measurement of Extraction Socket Wounds. Medicina (Kaunas). 2023 Jan 10;59(1):135. https://doi.org/10.3390/medicina59010135

7. Tabaldyev AT. Modern methods for the treatment of purulent wounds and their efficiency. Bulletin of Science and Practice. 2022;8(12):311–319. (In Russ.). https://doi.org/10.33619/2414-2948/85/36

8. Al-Kanani ES, Soloshenko AV, Nikolayev SB, Oleynik NV, Gerasimov IV, Ivashchuk OD, et al. Purulent complications after planned operations in a multidisciplinary hospital. Challenges in Modern Medicine 2024;47(1):99–118. (In Russ.). https://doi.org/10.52575/2687-0940-2024-47-1-99-118

9. Ivanusa SY, Risman BV, Shayakhmetov RE, Yanishevskiy AV, Babenko MV, Shipilov PA. Computer planimetry as an objective control method for wound healing in diabetic foot syndrome. Bulletin of the Russian Military Medical Academy 2023;25(2):239–248. (In Russ.). https://doi.org/10.17816/brmma321607

10. Mikhailov NO, Bokov DA, Andreev AA, Glukhov AA. Comparative analysis of modern methods of planimetry in the study of soft tissue wounds. Russian Journal of Preventive Medicine and Public Health. 2022;25(5-2):46. (In Russ.). EDN: FANAZR

11. Derii EK, Zinovev EV, Krainyukov PE, Kostyakov DV, Kokorin VV, Khruskina EV, Boyarinov BO. Approaches to determining the area of the wound surface. Military Medical Journal. 2022;343(3):61–65. (In Russ.). https://doi.org/10.52424/00269050_2022_343_3_61

12. Sánchez-Jiménez D, Buchón-Moragues FF, Escutia-Muñoz B, Botella-Estrada R. SfM-3DULC: Reliability of a new 3D wound measurement procedure and its accuracy in projected area. Int Wound J. 2022 Jan;19(1):44–51. https://doi.org/10.1111/iwj.13595

13. Foltynski P, Ladyzynski P. Digital Planimetry with a New Adaptive Calibration Procedure Results in Accurate and Precise Wound Area Measurement at Curved Surfaces. J Diabetes Sci Technol. 2022 Jan;16(1):128–136. https://doi.org/10.1177/1932296820959346

14. Lucas Y, Niri R, Treuillet S, Douzi H, Castaneda B. Wound Size Imaging: Ready for Smart Assessment and Monitoring. Adv Wound Care (New Rochelle). 2021 Nov;10(11):641–661. https://doi.org/10.1089/wound.2018.0937

15. Robinson CJ, Dickie B, Lindner C, Herrera J, Dingle L, Reid AJ, et al. Complex wound analysis using AI. Comput Biol Med. 2025 May;190:109945. https://doi.org/10.1016/j.compbiomed.2025.109945

16. Liu H, Sun W, Cai W, Luo K, Lu C, Jin A, et al. Current status, challenges, and prospects of artificial intelligence applications in wound repair theranostics. Theranostics. 2025 Jan 2;15(5):1662–1688. https://doi.org/10.7150/thno.105109

17. Nazarenko AG, Kleimenova EB, Molodchenkov AI, Ponomarchuk AS, Gerasimova NP, Yurchenkova ES, Yashina LP. Application of machine learning methods to image analysis of chronic wounds. Artificial Intelligence and Decision Making 2025;1:103–114. (In Russ.). https://doi.org/10.14357/20718594250109

18. Certificate of state registration of the computer program No. 2025667847 Russian Federation. Neural network model training system for segmentation of soft tissue wounds: application 11.06.2025: published 09.07.2025. Mikhailov N.O., Maksimov A.V., Andreev A.A., Glukhov A.A.; applicant Voronezh State Medical University named after N. N. Burdenko Ministry of Health of the Russian Federation. (In Russ.). EDN: BGKAQX

19. Certificate of state registration of the computer program No. 2025680231 Russian Federation. Automated wound area recognition and measurement system: application 11.06.2025: published 04.08.2025. Mikhailov N.O., Maksimov A.V., Andreev A. A., Glukhov A.A.; applicant Voronezh State Medical University named after N.N. Burdenko Ministry of Health of the Russian Federation. (In Russ.). EDN: LQYJSE

20. Mikhailov NO, Glukhov AA, Andreev AA, Laptieva AYu, Sudakov OV, Ivashkov VYu, Denisenko AS. Comparative analysis of accuracy and time of calculation of wound surface area using mobile applications. Science and Innovations in Medicine. 2025;10(2):161–168. (In Russ.). https://doi.org/10.35693/sim643331

21. Bokov DA, Mikhailov NO. Comparative analysis of modern methods of measuring the area of the wound surface. Molodezhnyi innovatsionnyi vestnik. 2022;11(2):27–31. (In Russ.). EDN: HXOLEK