Role of artificial intelligence in reducing unnecessary biopsies in breast lesions BI-RADS 4 in images
DOI:
https://doi.org/10.52611/confluencia.2026.1749Keywords:
Breast neoplasms, Artificial intelligence, Diagnostic imaging, Deep learning, RadiologyAbstract
Introduction: Breast cancer is the most common malignancy in women worldwide and a leading cause of female mortality. Diagnosis relies on imaging modalities—primarily mammography, ultrasound, and MRI—which present limited specificity, leading to unnecessary invasive procedures in a significant proportion of cases. In this context, artificial intelligence emerges as a complementary tool to radiological interpretation. Objective: To analyze the current scientific evidence on the application of AI in breast radiology and its impact on the reduction of unnecessary biopsies in BI-RADS 4 lesions. Methodology: A systematic search was conducted in PubMed, Google Scholar, ScienceDirect, RSNA and MDPI using MeSH descriptors related to breast cancer, breast imaging, AI and deep learning, restricted to the last 10 years (2015-2025). Of 134 articles identified, 21 were selected for final analysis. Discussion: The reviewed studies demonstrate that deep learning models improve diagnostic performance across the three main imaging modalities. In mammography, these algorithms identify a significant proportion of BI-RADS 4 lesions as potentially benign while maintaining high sensitivity, with potential to reduce unnecessary biopsies. In ultrasound and MRI, the integration of radiomics and artificial intelligence significantly improves diagnostic specificity in differentiating benign from malignant lesions compared to conventional visual assessment. Conclusion: AI has broad potential to optimize breast image interpretation, contributing to reducing unnecessary biopsies in BI-RADS 4 lesions and enabling more accurate and efficient diagnosis.
References
1. Bray F, Laversanne M, Sung H, Ferlay J, Siegel RL, Soerjomataram I, et al. Global cancer statistics 2022: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA Cancer J Clin [Internet]. 2024 [citado el 24 de febrero 2026];74(3):229-63. Disponible en: https://doi.org/10.3322/caac.21834
2. Sung H, Ferlay J, Siegel RL, Laversanne M, Soerjomataram I, Jemal A, et al. Global Cancer Statistics 2020: GLOBOCAN Estimates of Incidence and Mortality Worldwide for 36 Cancers in 185 Countries. CA Cancer J Clin [Internet]. 2021 [citado el 24 de febrero 2026];71(3):209-49. Disponible en: https://doi.org/10.3322/caac.21660
3. World Health Organization. International Agency for Research on Cancer. Cancer Today. Global Cancer Observatory [Internet]. Lyon: GCO; 2023 [citado el 24 de febrero 2026]. Disponible en: https://gco.iarc.fr/today
4. Wiesenthal J, Kaufmann D, Dolman S. Breast biopsy rates and market dynamics: how provider environment shaped diagnostic practice in 2023. Health Aff Scholar [Internet]. 2025 [citado el 25 de febrero 2026];3(9):qxaf171. Disponible en: https://doi.org/10.1093/haschl/qxaf171
5. Liu C, Sun M, Arefan D, Zuley M, Sumkin J, Wu S. Deep learning of mammogram images to reduce unnecessary breast biopsies: a preliminary study. Breast Cancer Res [Internet]. 2024 [citado el 24 de febrero 2026];26:52. Disponible en: https://doi.org/10.1186/s13058-024-01830-9
6. McKinney SM, Sieniek M, Godbole V, Godwin J, Antropova N, Ashrafian H, et al. International evaluation of an AI system for breast cancer screening. Nature [Internet]. 2020 [citado el 24 de febrero 2026];577(7788):89-94. Disponible en: https://doi.org/10.1038/s41586-019-1799-6
7. Rodriguez-Ruiz A, Lång K, Gubern-Merida A, Broeders M, Gennaro G, Clauser P, et al. Stand-Alone Artificial Intelligence for Breast Cancer Detection in Mammography: Comparison With 101 Radiologists. J Natl Cancer Inst [Internet]. 2019 [citado el 27 de febrero 2026];111(9):916-22. Disponible en: https://doi.org/10.1093/jnci/djy222
8. Abu Abeelh E, AbuAbeileh Z. Comparative Effectiveness of Mammography, Ultrasound, and MRI in the Detection of Breast Carcinoma in Dense Breast Tissue: A Systematic Review. Cureus [Internet]. 2024 [citado el 4 de marzo 2026];16(4):e59054. Disponible en: https://doi.org/10.7759/cureus.59054
9. Lohitvisate W, Kaeorat C, Kwankua A. Mammography of suspicious calcifications among ductal carcinoma in situ and benign breast disease. SA J Radiol [Internet]. 2024 [citado el 4 de marzo 2026];28(1):2852. Disponible en: https://doi.org/10.4102/sajr.v28i1.2852
10. Ghaemian N, Haji Ghazi Tehrani N, Nabahati M. Accuracy of mammography and ultrasonography and their BI-RADS in detection of breast malignancy. Caspian J Intern Med [Internet]. 2021 [citado el 5 de marzo 2026];12(4):573-9. Disponible en: https://doi.org/10.22088/cjim.12.4.573
11. He P, Chen W, Bai MY, Li J, Wang QQ, Fan LH, et al. Deep Learning-Based Computer-Aided Diagnosis for Breast Lesion Classification on Ultrasound: A Prospective Multicenter Study of Radiologists Without Breast Ultrasound Expertise. AJR Am J Roentgenol [Internet]. 2023 [citado el 28 de febrero 2026];221(4):450-9. Disponible en: https://doi.org/10.2214/AJR.23.29328
12. Oh KE, Vasandani N, Anwar A. Radiomics to Differentiate Malignant and Benign Breast Lesions: A Systematic Review and Diagnostic Test Accuracy Meta-Analysis. Cureus [Internet]. 2024 [citado el 27 de febrero 2026];5(11):e49015. Disponible en: https://doi.org/10.7759/cureus.49015
13. Wang W, Li J, Wang Z, Liu Y, Yang F, Cui S. Study on the classification of benign and malignant breast lesions using a multi-sequence breast MRI fusion radiomics and deep learning model. Eur J Radiol Open [Internet]. 2024 [citado el 28 de febrero 2026];13:100607. Disponible en: https://doi.org/10.1016/j.ejro.2024.100607
14. Hellerhoff K, Dietrich H, Schinner R, Rjosk-Dendorfer D, Sztrókay-Gaul A, Reiser M, et al. Assessment of MRI-Detected Breast Lesions: A Benign Correlate on Second-Look Ultrasound Can Safely Exclude Malignancy. Breast Care (Basel) [Internet]. 2021 [citado el 27 de febrero 2026];16(5):435-43. Disponible en: https://doi.org/10.1159/000513443
15. Guirguis MS, Adrada B, Santiago L, Candelaria R, Arribas E. Mimickers of breast malignancy: imaging findings, pathologic concordance and clinical management. Insights Imaging [Internet]. 2021 [citado el 27 de febrero 2026];12(1):53. Disponible en: https://doi.org/10.1186/s13244-021-00991-x
16. Su Y, Qiu Y, Huang X, Peng Y, Yang Z, Ding M, et al. Benign and Malignant Breast Lesions: Differentiation Using Microstructural Metrics Derived from Time-Dependent Diffusion MRI. Radiol Imaging Cancer [Internet]. 2025 [citado el 24 de febrero 2026];7(3):e240287. Disponible en: https://doi.org/10.1148/rycan.240287
17. Ghunaim HA, Alatawi RE, Borhan WM, Daqqaq TS, Alhasan AS, Aboualkheir MM, et al. Accuracy of imaging of BI-RADS 4 subcategorizations in breast lesion diagnosis: Radiologic-pathologic correlation. Saudi Med J [Internet]. 2024 [citado el 26 de febrero 2026];45(11):1228-37. Disponible en: https://doi.org/10.15537/smj.2024.45.11.20240001
18. Nguyen DL, Myers KS, Oluyemi E, Mullen LA, Panigrahi B, Rossi J, et al. BI-RADS 3 Assessment on MRI: A Lesion-Based Review for Breast Radiologists. J Breast Imaging [Internet]. 2022 [citado el 24 de febrero 2026];4(5):460-73. Disponible en: https://doi.org/10.1093/jbi/wbac032
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Revista Confluencia
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
