The effectiveness of artificial intelligence to support the diagnosis of breast lesions by ultrasound: an integrative review

Autores

DOI:

https://doi.org/10.29289/2594539420260013

Palavras-chave:

artificial intelligence, breast, biopsy, breast cancer

Resumo

Breast cancer remains the most common malignant neoplasm among women worldwide, and early detection and diagnostic accuracy are fundamental to reducing mortality. Although mammography is the standard screening method, breast ultrasound plays an essential complementary role, despite being operator-dependent, with high inter-observer variability and lower specificity. In this context, artificial intelligence emerges as a promising tool for improving image interpretation, serving as a clinical decision-making aid. This integrative review analyzed comparative studies obtained between January 2016 and January 2024 from the PubMed/MEDLINE, LILACS, SciELO, and Connected Papers databases, including original articles with histopathological confirmation as the gold standard and excluding other imaging methods and studies outside the scope. A total of 14 studies (2016–2023) were included, involving 3,144 patients and 3,524 lesions (2,318 benign and 1,206 malignant), evaluated by approved artificial intelligence systems (Koios DS and S-Detect), with heterogeneity regarding evaluator experience and methodological criteria. The results demonstrate that artificial intelligence exhibits high diagnostic performance, with sensitivity and area under the curve comparable to those of experienced radiologists, in addition to improving standardization, reducing inter-observer variability, and increasing accuracy—especially among less experienced professionals—with high negative predictive value and the potential to reduce unnecessary biopsies. However, specificity is variable, and when artificial intelligence is used alone, it may be lower than that of specialists. The combined use of a radiologist and artificial intelligence yielded better results. Methodological and technical limitations—including a predominance of retrospective studies, data heterogeneity, and system constraints in evaluating certain findings—hinder the generalizability of results. Artificial intelligence emerges as a promising complementary tool in breast ultrasound, with the potential to improve diagnostic accuracy and clinical management. Prospective, multicenter, and standardized studies are needed to consolidate its application in clinical practice.

Downloads

Não há dados estatísticos.

Referências

1. Brasil. Instituto Nacional de Câncer. Estimativa 2026: incidência de câncer no Brasil. Rio de Janeiro: INCA; 2026; 168 p.

2. Boyd NF, Guo H, Martin LJ, Sun L, Stone J, Fishell E, et al. Mammographic density and the risk and detection of breast cancer. N Engl J Med. 2007;356(3):227-36. https://doi.org/10.1056/nejmoa062790

3. Berg WA, Blume JD, Cormack JB, Mendelson EB, Lehrer D, Böhm-Vélez M, et al. Combined screening with ultrasound and mammography compared to mammography alone in women at elevated risk of breast cancer: results of the first-year screen in ACRIN 6666. JAMA. 2008;299(18):2151-63. https://doi.org/10.1001/jama.299.18.2151

4. Lee SE, Moon JE, Rho YH, Kim EK, Yoon JH. Which supplementary imaging modality should be used for breast ultrasonography? Comparison of the diagnostic performance of elastography and computer-aided diagnosis. Ultrasonography. 2017;36(2):153-9. https://doi.org/10.14366/usg.16033

5. Calas MJG, Alvarenga AV, Gutfilen B, Pereira WCA. Avaliação de parâmetros morfométricos calculados a partir do contorno de lesões de mama em ultrassonografias na distinção das categorias do sistema BI-RADS. Radiol Bras. 2011;44(5):289-96. https://doi.org/10.1590/S0100-39842011000500006

6. Gómez-Flores W, Gregorio-Calas MJ, Pereira WCA. BUS-BRA: A breast ultrasound dataset; for assessing computer-aided diagnosis systems. Med Phys. 2024;51(4):3110-23. https://doi.org/10.1002/mp.16812

7. Taylor CR, Monga N, Johnson C, Hawley JR, Patel M. Artificial intelligence applications in breast imaging: current status and future directions. Diagnostics (Basel). 2023;13(12):2041. https://doi.org/10.3390/diagnostics13122041

8. Brunetti N, Calabrese M, Martinoli C, Tagliafico AS. Artificial intelligence in breast ultrasound: from diagnosis to prognosis—a rapid review. Diagnostics (Basel). 2023;13(1):58. https://doi.org/10.3390/diagnostics13010058

9. Calas MJG, Lemos ML, Bello MA, Gutfilen B, Bergmann A. Validation of an artificial intelligence program in the characterization of breast nodules by ultrasound. Clin Imaging. 2026;130:110691. https://doi.org/10.1016/j.clinimag.2025.110691

10. Mahant SS, Varma AR. Artificial intelligence in breast ultrasound: the emerging future of modern medicine. Cureus. 2022;14(9):e28945. https://doi.org/10.7759/cureus.28945

11. Liu Q, Qu M, Sun L, Wang H. Accuracy of ultrasonic artificial intelligence in diagnosing benign and malignant breast diseases: a protocol for systematic review and meta-analysis. Medicine (Baltimore). 2021;100(50):e28289. https://doi.org/10.1097/MD.0000000000028289

12. Bahl M, Chang JM, Mullen LA, Berg WA. Artificial intelligence for breast ultrasound: AJR expert panel narrative review. AJR Am J Roentgenol. 2024;223(6):e2330645. https://doi.org/10.2214/ajr.23.30645

13. Brot HF, Mango VL. Artificial intelligence in breast ultrasound: application in clinical practice. Ultrasonography. 2024;43(1):3-14. https://doi.org/10.14366/usg.23116

14. Zhao C, Xiao M, Jiang Y, Liu H, Wang M, Wang H, et al. Feasibility of computer-assisted diagnosis for breast ultrasound: the results of the diagnostic performance of S-detect from a single center in China. Cancer Manag Res. 2019;11:921-30. https://doi.org/10.2147/cmar.s190966

15. Choi JH, Kang BJ, Baek JE, Lee HS, Kim SH. Application of computer-aided diagnosis in breast ultrasound interpretation: improvements in diagnostic performance according to reader experience. Ultrasonography. 2018;37(3):217-25. https://doi.org/10.14366/usg.17046

16. Xing B, Chen X, Wang Y, Li S, Liang YK, Wang D. Evaluating breast ultrasound S-detect image analysis for small focal breast lesions. Front Oncol. 2022;12:1030624. https://doi.org/10.3389/fonc.2022.1030624

17. O'Connell AM, Bartolotta TV, Orlando A, Jung SH, Baek J, Parker KJ. Diagnostic performance of an artificial intelligence system in breast ultrasound. J Ultrasound Med. 2022;41(1):97-105. https://doi.org/10.1002/jum.15684

18. Bartolotta TV, Orlando A, Cantisani V, Matranga D, Lenzi R, Cirino A, et al. Focal breast lesion characterization according to the BI-RADS US lexicon: role of a computer-aided decision-making support. Radiol Med. 2018;123(7):498-506. https://doi.org/10.1007/s11547-018-0874-7

19. Kim K, Song MK, Kim EK, Yoon JH. Clinical application of S-Detect to breast masses on ultrasonography: a study evaluating the diagnostic performance and agreement with a dedicated breast radiologist. Ultrasonography. 2017;36(1):3-9. https://doi.org/10.14366/usg.16012

20. Xia Q, Cheng Y, Hu J, Huang J, Yu Y, Xie H, et al. Differential diagnosis of breast cancer assisted by S-Detect artificial intelligence system. Math Biosci Eng. 2021;18(4):3680-9. https://doi.org/10.3934/mbe.2021184

21. Wanderley MC, Soares CMA, Morais MMM, Cruz RM, Lima IRM, Chojniak R, et al. Application of artificial intelligence in predicting malignancy risk in breast masses on ultrasound. Radiol Bras. 2023;56(5):329-36. https://doi.org/10.1590/0100-3984.2023.0034

22. Di Segni M, Soccio V, Cantisani V, Bonito G, Rubini A, Di Segni G, et al. Automated classification of focal breast lesions according to S-detect: validation and role as a clinical and teaching tool. J Ultrasound. 2018;21(2):105-18. https://doi.org/10.1007/s40477-018-0297-2

23. Park HJ, Kim SM, Yun BL, Jang M, Kim B, Jang JY, et al. A computer-aided diagnosis system using artificial intelligence for the diagnosis and characterization of breast masses on ultrasound: added value for the inexperienced breast radiologist. Medicine (Baltimore). 2019;98(3):e14146. https://doi.org/10.1097/MD.0000000000014146

24. Guldogan N, Taskin F, Icten GE, Yilmaz E, Turk EB, Erdemli S, et al. Artificial Intelligence in BI-RADS Categorization of Breast Lesions on Ultrasound: Can We Omit Excessive Follow-ups and Biopsies? Acad Radiol. 2024;31(6):2194-202. https://doi.org/10.1016/j.acra.2023.11.031

25. Heller SL, Wegener M, Babb JS, Gao Y. Can an artificial intelligence decision aid decrease false-positive breast biopsies? Ultrasound Q. 2021;37(1):10-15. https://doi.org/10.1097/ruq.0000000000000550

26. Çelebi F, Tuncer O, Oral M, Duymaz T, Orhan T, Ertaş G. Artificial intelligence in diagnostic breast ultrasound: a comparative analysis of decision support among radiologists with various levels of expertise. Eur J Breast Health. 2025;21(1):33-9. https://doi.org/10.1016/j.ultrasmedbio.2023.02.012

27. Lee SE, Moon JE, Rho YH, Kim EK, Yoon JH. Which supplementary imaging modality should be used for breast ultrasonography? Comparison of the diagnostic performance of elastography and computer-aided diagnosis. Ultrasonography. 2017;36(2):153-9. https://doi.org/10.14366/usg.16033

28. Wang XY, Cui LG, Feng J, Chen W. Artificial intelligence for breast ultrasound: an adjunct tool to reduce excessive lesion biopsy. Eur J Radiol. 2021;138:109624. https://doi.org/10.1016/j.ejrad.2021.109624

Downloads

Publicado

2026-11-16

Como Citar

Lemos, M. L., Gutfilen, B., & Calas, M. J. G. (2026). The effectiveness of artificial intelligence to support the diagnosis of breast lesions by ultrasound: an integrative review. Mastology, 36. https://doi.org/10.29289/2594539420260013

Edição

Seção

Review Articles