Improving the effectiveness of population-based breast cancer screening using artificial intelligence: results of a pilot implementation in regions of the Russian Federation

Breast cancer (BC) remains the leading cancer morbidity among women in Russia. Despite widespread screening, early-stage (0-II) incidence rates are low due to insufficient radiology staff, high consultation loads, and the combination of unsatisfactory mammograms.

Objective. To evaluate the effectiveness of artificial intelligence (AI) technology in interpreting mammography results during preventive medical examinations (PMEs) and early adult screenings (EAS) in reducing the detection rate of malignant breast tumors.

Materials and methods. A multicenter observational study with historical control was conducted at healthcare facilities in six constituent entities of the Russian Federation (Bryansk, Saratov, Novosibirsk, and Sakhalin Oblasts, Kamchatka Krai, and Khabarovsk Krai). During the study period, 677,652 mammography examinations were performed in the pilot regions under the Primary Medical Association (PMA) and the Department of State Health Supervision (DOGVN), of which 247,514 (36.6%) were performed using the Third Opinion AI analysis service (RZN 2022/16534). The share of examinations submitted for AI processing ranged from 18.0% (Khabarovsk Krai) to 79.6% (Kamchatka Krai). The comparison group included 553,011 examinations from the same regions in 2023. Correlation analysis was performed using the Spearman rank correlation method.

Results. The primary BC incidence rate in 6 regions increased from 165.5 (2023) to 270.3 (2024-2025) per 100,000 mammograms (+63.4%). The incidence of stages 0-II increased from 144.5 to 212.4 (+47.0%). The share of BI-RADS 4-5 was 23.6% with the use of AI versus 10.8% with routine screening. A statistically significant rank correlation was found between AI coverage and the share of BI-RADS 4-5 (ρ = 0.886; p = 0.019; n = 6).

Conclusion. The introduction of AI in the description of mammography results during primary medical examinations/preclinical screening is associated with an increase in the primary BC detection rate and the number of cases diagnosed at early stages. Medical effectiveness is consistent with data from large randomized trials. Scaling up requires organizational support.

1. [Zlokachestvennye novoobrazovaniya v Rossii v 2023 godu (zabolevaemost' i smertnost'). AD Kaprin, VV Starinskiy, GV Petrova, editors. Moskva: MNIOI im. P. A. Gercena, 2024. 252 s. Available at: oncology-association.ru Accessed 08.02.2026. (In Russ.)]

2. [Drapkina OM, et al. Organizaciya profilakticheskih medicinskih osmotrov i dispanserizacii: metodicheskie rekomendacii. Moskva: FGBU NMIC TPM Minzdrava Rossii, 2023. 164 s. (In Russ.)] doi: 10.17116/profmed2023260210.

3. Yoon JH, Kim HJ, Kwon TG, et al. Standalone AI for Breast Cancer Detection at Screening Digital Mammography and Digital Breast Tomosynthesis: A Systematic Review and Meta-Analysis. Radiology. 2023; 307(5): e222639. doi: 10.1148/radiol.e222639.

4. [Pavlova VI, Belaya YUA, Voroncov AYU, et al. Ispol'zovanie iskusstvennogo intellekta dlya rannego vyyavleniya raka molochnoj zhelezy: rezul'taty nauchno-issledovatel'skoj raboty. Opuholi zhenskoj reproduktivnoj sistemy. 2023; 19(2): 54-60. (In Russ.)] doi: 10.17650/1994-4098-2023-19-2-54-60.

5. Lång K, Josefsson V, Larsson A-M, et al. Interval cancer, sensitivity, and specificity comparing AI-supported mammography screening with standard double reading without AI in the MASAI study: a randomised, controlled, non-inferiority, single-blinded, population-based, screening-accuracy trial. The Lancet. 2026; 407(10527): 505-514. doi: 10.1016/S0140-6736(25)02464-X.

6. Eisemann N, Sinner J, Müller L, et al. Nationwide real-world implementation of AI for cancer detection in mammography screening: the PRAIM study. Nature Medicine. 2025; 31(1): 112-121. doi: 10.1038/ s41591-024-03408-6.

7. [Vasil'ev YUA, Tyrov IA, Vladzimirskij AV, et al. Dvojnoj prosmotr rezul'tatov mammografii s primeneniem tekhnologij iskusstvennogo intellekta: novaya model' organizacii massovyh profilakticheskih issledovanij. Digital Diagnostics. 2023; 4(2): 93-104. (In Russ.)] doi: 10.17816/DD321423.

8. [Arzamasov KM, Basargina AV, Gombolevskij VA, et al. Vliyanie tekhnologij iskusstvennogo intellekta na effektivnost' raboty vrachej-rentgenologov pri skrininge raka molochnoj zhelezy. Profilakticheskaya medicina. 2024; 27(5): 103-110. (In Russ.)] doi: 10.17116/profmed202427051103.

9. [Omel'yanovskij VV, Fedyaev VV, Suhorukih MV, et al. Osobennosti ocenki ekonomicheskoj effektivnosti onkomammoskrininga s primeneniem tekhnologij iskusstvennogo intellekta. Medicinskij alfavit. 2022; 30: 48-54. (In Russ.)] doi: 10.33667/2078-5631-2022-30-48-54.

10. [Bochkareva EV, Butina EK, Bajramkulova NH, et al. Associaciya kal'cinoza arterij molochnoj zhelezy i ateroskleroza sonnyh arterij — markera serdechno-sosudistogo riska. Racional'naya farmakoterapiya v kardiologii. 2023; 19(5): 435-443. (In Russ.)] doi: 10.20996/1819-6446-2023-2950.

11. [Bochkareva EV, Kim IV, Metel'skaya VA. , et al. Associaciya kal'cinoza arterij molochnoj zhelezy s pokazatelyami reproduktivnoj funkcii i kardiovaskulyarnymi faktorami riska u zhenshchin. Kardiovaskulyarnaya terapiya i profilaktika. 2025; 24(8): 53-62. (In Russ.)] doi: 10.15829/1728-8800-2025-4455.

12. Chidurala S, Charkhchi P, Komirisetty R, et al. A review of artificial intelligence models for detecting breast arterial calcification on mammograms and their clinical implications. Cureus. 2025; 17(6): e86894. doi: 10.7759/cureus.86894.

13. [ O razvitii iskusstvennogo intellekta v Rossijskoj Federacii: Ukaz Prezidenta Rossijskoj Federacii ot 10.10.2019 № 490: s izmeneniyami ot 15.02.2024 № 124. Available at: kremlin.ru. Accessed 08.02.2026. (In Russ.)]

14. [Federal'nyj proekt «Bor'ba s onkologicheskimi zabolevaniyami. Available at: https://minzdrav.gov.ru. Accessed 08.02.2026. (In Russ.)]