Computer-Assisted Semen Analysis (CASA) systems are currently widely used to evaluate human spermatozoa as an alternative method to traditional manual semen examination, which has several limitations. The introduction of digital microscopy with subsequent automatic artificial intelligence-based object recognition is considered as a promising direction in optimizing semen analysis. During this research study, 100 semen samples were examined with a consistent evaluation of sperm motility and morphology, DNA fragmentation, and the presence of leukocytes in each sample. Each sample was examined sequentially: first using the Vision Assist automatic scanning system and Vision Sperm software, then by manual microscopy. As a result of the study, data was obtained that using the Vision system allows for a faster and more standardized semen analysis: the average time spent on automated evaluation of semen was two times less compared to manual microscopy of semen. Thus, the use of Vision systems reduces the time for conducting semen analyses, standardizes them, increasing the efficiency of laboratories.
Dmitriy Yu. Sosnin – MD, PhD, DSc,Professor at the Department of Faculty Therapy No. 2, Occupational Pathology and Clinical Laboratory Diagnostics of the Wagner State Medical University, E. A. Vagner Perm State Medical University, Ministry of Health of Russian Federation, Perm, Russia.
Anton N. Belkin – senior lecturer of the Department of Pathological Anatomy with a sectional course of the Perm State Medical University named after E. A. Wagner, Ministry of Health of Russian Federation, Perm, Russia.
Oleg G. Kubarev – clinical laboratory scientist, scientific consultant of the Design and Development department, ‘Medica Product’ LLC, Perm, Russia.
Gleb A. Kataev – technical writer of ‘Medica Product’ LLC, Perm, Russia.
Anna S. Churilova – head of the Artificial Intelligence Development Group of the Design and Development Department of ‘Medica Product’ LLC, Perm, Russia.
Boris F. Falkov – director of the Design and Development Department, ‘Medica Product’ LLC, Perm, Russia.
Vladislav A. Sapozhkov – Engineer of the Analytical Systems Group of the Service Center LLC ‘Medica Product’, Moscow, Russia.
1. Bragina EE. Interpretaciya spermogrammy. Struktura i funkciya spermatozoidov v norme i pri narushenii fertil'nosti. Moscow: Prakticheskaya medicina; 2024. (In Russ).
2. Issledovanie kachestva spermy bazovoe. Trebovaniya i metody issledovaniya (GOST ISO 23162–2023). Moscow: Rossijskij institut standartizacii; 2023. (In Russ).
3. Shatohina IS, Kuznecova VS. Issledovanie eyakulyata. Moscow: MONIKI im. M.F. Vladimirskogo; 2014. (In Russ).
4. Surmacz P, Niwinska A, Kautz E, et al. Comparison of two staining techniques on the manual and automated canine sperm morphology analysis. Reprod Domest Anim. 2022;57(6):678-684. DOI: 10.1111/rda.14100
5. Tang SS, Lu JC, Xu YH, et al. Analysis of selected sperm samples by a computer-assisted system with high frame rate: a prospective study. Health Sci Rep. 2023;6(5):e1217. DOI: 10.1002/hsr2.1217
6. Cheon WH, Park HJ, Park MJ, et al. Validation of a smartphone-based, computer-assisted sperm analysis system compared with laboratory-based manual microscopic semen analysis and computer-assisted semen analysis. Investig Clin Urol. 2019;60(5):380-7. DOI: 10.4111/icu.2019.60.5.380
7. Dearing C, Jayasena C, Lindsay K. Can the Sperm Class Analyser (SCA) CASA-Mot system for human sperm motility analysis reduce imprecision and operator subjectivity and improve semen analysis? Hum Fertil. 2021;24(3):208-18. DOI: 10.1080/14647273.2019.1610581
8. Leung ETY, Mei X, Lee BKM, et al. Automatic identification of human spermatozoa with zona pellucida-binding capability using deep learning. Hum Reprod Open. 2025;10(3):hoaf024. DOI: 10.1093/hropen/hoaf024
9. Macleod IC, Irvine DS. The predictive value of computer-assisted semen analysis in the context of a donor insemination programme. Hum Reprod. 1995;10(3):580-6. DOI: 10.1093/oxfordjournals.humrep.a135993
10. Cooper TG, Noonan E, von Eckardstein S, et al. World Health Organization reference values for human semen characteristics. Hum Reprod Update. 2010;16(3):231-45. DOI: 10.1093/humupd/dmp048
11. Agarwal A, Sharma RK. Automation is the key to standardized semen analysis using the automated SQA-V sperm quality analyzer. Fertil Steril. 2007;87:156-62. DOI: 10.1016/j.fertnstert.2006.05.083
12. Laboratornoe rukovodstvo VOZ po issledovaniyu i obrabotke eyakulyata cheloveka, shestoe izdanie. Geneva: World Health Organization; 2023. (In Russ).
13. Finelli R, Leisegang K, Tumallapalli S, et al. The validity and reliability of computer-aided semen analyzers in performing semen analysis: a systematic review. Transl Androl Urol. 2021;10(7):3069-79. DOI: 10.21037/tau-21-276
14. Kaznacheeva EI, Sosnin DYu, Petuhova AYu, et al. Evaluation of the accuracy of sperm morphology recognition by the VISION SPERM automatic sperm analysis system. Laboratory and Clinical Medicine. Pharmacy. 2024;4(2):10-6. (In Russ). DOI: 10.14489/lcmp.2024.02.pp.010-016
15. Choi JW, Alkhoury L, Urbano LF, et al. An assessment tool for computer-assisted semen analysis (CASA) algorithms. Sci Rep. 2022;12(1):16830. DOI: 10.1038/s41598-022-20943-9
16. Sosnin DYu, Belkin AN, Kataev GA, et al. Comparison of time costs using manual and automated approach to microscopic examinations of sperm in laboratory diagnostics. Laboratory and Clinical Medicine. Pharmacy. 2025;5(4):4-10. (In Russ). DOI: 10.14489/lcmp.2025.04.pp.004-010
17. Lipatova NA, Stolyarova SV, Sapozhkov VA, et al. Practical experience in automation, standardization and optimization of microscopic studies of urogenital tract material. Laboratory and Clinical Medicine. Pharmacy. 2023;3(4):4-10. (In Russ). DOI: 10.14489/lcmp.2023.04.pp.004-010
The article can be purchased
electronic!
PDF format
Free
DOI: 10.14489/lcmp.2026.02.pp.016-024
Article type:
Research Article
Make a request
