Application Value of Artificial Intelligence Ultrasound-Assisted Diagnosis System in the Diagnosis of BI-RADS 4 Breast Nodules
Abstract
To investigate the clinical application value of an artificial intelligence (AI) ultrasound-assisted diagnostic system in the diagnosis of Breast Imaging Reporting and Data System (BI-RADS) category 4 breast nodules. A retrospective analysis of 231 breast nodules from 226 patients (aged 26 to 80 years, mean 55.52 ± 12.32 years) was carried out from December 2024 to December 2025. Nodules were divided into a malignant group and a benign group according to the pathological results of biopsy or surgery. Four diagnostic approaches were compared: low-experience ultrasound physicians (<5 years, US), high-experience ultrasound physicians (>15 years, US+), AI-assisted diagnosis alone (AI), and AI-assisted diagnosis combined with low-experience physicians (AI+US), all based on the BI-RADS classification system. A result of BI-RADS 4a or lower was regarded as negative, whereas 4b or above was positive. Sensitivity (SE), specificity (SP), accuracy (ACC), positive predictive value (PPV), negative predictive value (NPV) and area under the receiver operating characteristic curve (AUC) were computed with the pathological results as the gold standard. 128 of 231 nodules were malignant and 103 benign. The AI group achieved SE 82.03%, SP 80.58%, ACC 81.38%, PPV 84.00%, NPV 78.30%, and AUC 0.813 (95% CI: 0.756–0.870), exceeding the US group (all p < 0.05 vs. US). The AI ultrasound-assisted diagnostic system shows good efficacy in the diagnosis of BI-RADS 4 breast nodules, especially for small nodules.
Keywords
References
- 1. Siegel, R.L.; Miller, K.D.; Wagle, N.S.; et al. Cancer statistics, 2023. CA Cancer J. Clin. 2023, 73, 17–48.
- 2. Burstein, H.J.; Curigliano, G.; Thürlimann, B.; et al. Customizing local and systemic therapies for women with early breast cancer: The St. Gallen International Consensus Guidelines for treatment of early breast cancer 2021. Ann. Oncol. 2021, 32, 1216–1235.
- 3. Lee, J. Practical and illustrated summary of updated BI-RADS for ultrasonography. Ultrasonography 2016, 36, 71–81.
- 4. Zhao, J.Q.; Diao, Z.; Xu, Q.; et al. New development of ultrasound medicine in the era of artificial intelligence. Acad. J. Second Mil. Med. Univ. 2019, 40, 478–482. (in Chinese)
- 5. Kim, K.; Song, M.K.; Kim, E.K.; et al. 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, 3–9.
- 6. Choi, J.H.; Kang, B.J.; Baek, J.E.; et al. Application of computer-aided diagnosis in breast ultrasound interpretation: Improvements in diagnostic performance according to reader experience. Ultrasonography 2018, 37, 217–225.
- 7. Wei, Q.; Yan, Y.J.; Wu, G.G.; et al. The diagnostic performance of ultrasound computer-aided diagnosis system for distinguishing breast masses: A prospective multicenter study. Eur. Radiol. 2022, 32, 4046–4055. DOI: https://doi.org/10.1007/s00330-021-08452-1
- 8. Lv, S.; Zhang, Y.; Zhang, M.; et al. The auxiliary role of an artificial intelligence-based automatic detection system in the diagnosis of small breast lumps by physicians with different experience. Chin. J. Med. Ultrasound (Electronic Edition) 2022, 19, 983. (in Chinese)
- 9. Xing, B.; Gu, C.; Fu, C.; et al. Diagnostic performance of ultrasound S-Detect technology in evaluating BI-RADS-4 breast nodules ≤20 mm and >20 mm. BMC Cancer 2025, 25, 1306. DOI: https://doi.org/10.1186/s12885-025-14760-2
- 10. Hejduk, P.; Marcon, M.; Unkelbach, J.; et al. Fully automatic classification of automated breast ultrasound imaging according to BI-RADS using a deep convolutional neural network. Eur. Radiol. 2022, 32, 4868–4878. DOI: https://doi.org/10.1007/s00330-022-08558-0
- 11. Islam, T.; Hoque, M.E.; Ullah, M.; et al. CNN-based deep learning approach for classification of invasive ductal and metastasis types of breast carcinoma. Cancer Med. 2024, 13, e70069. DOI: https://doi.org/10.1002/cam4.70069
- 12. Geras, K.J.; Mann, R.M.; Moy, L. Artificial intelligence for mammography and digital breast tomosynthesis: Current concepts and future perspectives. Radiology 2019, 293, 246–259. DOI: https://doi.org/10.1148/radiol.2019182627
- 13. Tsuyuzaki, S.; Fujioka, T.; Yamaga, E.; et al. Evaluation of AI diagnostic systems for breast ultrasound: Comparative analysis with radiologists and the effect of AI assistance. Jpn. J. Radiol. 2025, 43, 1643–1651. DOI: https://doi.org/10.1007/s11604-025-01809-2
- 14. Chen, R.; Wu, S.; Guo, J.; et al. Application value of an ultrasound artificial intelligence-assisted diagnostic system in the diagnosis of BI-RADS 4 breast nodules with a maximum diameter ≤2 cm. J. Nav. Med. Univ. 2024, 45, 592–598. (in Chinese)
- 15. Xing, B.; Chen, X.; Wang, Y.; et al. Evaluating breast ultrasound S-Detect image analysis for small focal breast lesions. Front. Oncol. 2022, 12, 1030624. DOI: https://doi.org/10.3389/fonc.2022.1030624
- 16. Fotouhi, S.; Asadi, S.; Kattan, M.W. A comprehensive data level analysis for cancer diagnosis on imbalanced data. J. Biomed. Inform. 2019, 90, 103089. DOI: https://doi.org/10.1016/j.jbi.2018.12.003
- 17. Shen, Y.; Shamout, F.E.; Oliver, J.R.; et al. Artificial intelligence system reduces false-positive findings in the interpretation of breast ultrasound exams. Nat. Commun. 2021, 12, 5645. DOI: https://doi.org/10.1038/s41467-021-26023-2
- 18. O’Connell, A.M.; Bartolotta, T.V.; Orlando, A.; et al. Diagnostic performance of an artificial intelligence system in breast ultrasound. J. Ultrasound Med. 2022, 41, 97–105. DOI: https://doi.org/10.1002/jum.15684
- 19. Qian, X.; Pei, J.; Zheng, H.; et al. Prospective assessment of breast cancer risk from multimodal multiview ultrasound images via clinically applicable deep learning. Nat. Biomed. Eng. 2021, 5, 522–532. DOI: https://doi.org/10.1038/s41551-021-00711-2
- 20. Zhang, N.; Li, X.T.; Ma, L.; et al. Application of deep learning to establish a diagnostic model of breast lesions using two-dimensional grayscale ultrasound imaging. Clin. Imaging 2021, 79, 56–63. DOI: https://doi.org/10.1016/j.clinimag.2021.03.024
- 21. Ciritsis, A.; Rossi, C.; Eberhard, M.; et al. Automatic classification of ultrasound breast lesions using a deep convolutional neural network mimicking human decision-making. Eur. Radiol. 2019, 29, 5458–5468. DOI: https://doi.org/10.1007/s00330-019-06118-7
- 22. Wang, X.Y.; Cui, L.G.; Feng, J.; et al. Artificial intelligence for breast ultrasound: An adjunct tool to reduce excessive lesion biopsy. Eur. J. Radiol. 2021, 138, 109624. DOI: https://doi.org/10.1016/j.ejrad.2021.109624
- 23. Amir, T.; Coffey, K.; Sevilimedu, V.; et al. A role for breast ultrasound artificial intelligence decision support in the evaluation of small invasive lobular carcinomas. Clin. Imaging 2023, 101, 77–85. DOI: https://doi.org/10.1016/j.clinimag.2023.05.005
- 24. Pfob, A.; Sidey-Gibbons, C.; Barr, R.G.; et al. The importance of multi-modal imaging and clinical information for humans and AI-based algorithms to classify breast masses (INSPiRED 003): An international, multicenter analysis. Eur. Radiol. 2022, 32, 4101–4115. DOI: https://doi.org/10.1007/s00330-021-08519-z
- 25. Wu, G.G.; Zhou, L.Q.; Xu, J.W.; et al. Artificial intelligence in breast ultrasound. World J. Radiol. 2019, 11, 19–26. DOI: https://doi.org/10.4329/wjr.v11.i2.19