AI: Can It Make a Difference to the Predictive Value of Ultrasound Breast Biopsy?
Open accessAbstract
(1) Background: This study aims to compare the ground truth (pathology results) against the BI-RADS classification of images acquired while performing breast ultrasound diagnostic examinations that led to a biopsy and against the result of processing the same images through the AI algorithm KOIOS DS TM (KOIOS). (2) Methods: All results of biopsies performed with ultrasound guidance during 2019 were recovered from the pathology department. Readers selected the image which better represented the BI-RADS classification, confirmed correlation to the biopsied image, and submitted it to the KOIOS AI software. The results of the BI-RADS classification of the diagnostic study performed at our institution were set against the KOIOS classification and both were compared to the pathology reports. (3) Results: 403 cases were included in this study. Pathology rendered 197 malignant and 206 benign reports. Four biopsies on BI-RADS 0 and two images are included. Of fifty BI-RADS 3 cases biopsied, only seven rendered cancers. All but one had a positive or suspicious cytology; all were classified as suspicious by KOIOS. Using KOIOS, 17 B3 biopsies could have been avoided. Of 347 BI-RADS 4, 5, and 6 cases, 190 were malignant (54.7%). Because only KOIOS suspicious and probably malignant categories should be biopsied, 312 biopsies would have resulted in 187 malignant lesions (60%), but 10 cancers would have been missed. (4) Conclusions: KOIOS had a higher ratio of positive biopsies in this selected case study vis-à-vis the BI-RADS 4, 5 and 6 categories. A large number of biopsies in the BI-RADS 3 category could have been avoided.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
One of the two studies on avoiding breast biopsies used an AI-assisted multi-modal shear wave elastography model.
“of which one used an AI-assisted multi-modal shear wave elastography model [199,200].”
From Evolving the Era of 5D Ultrasound? A Systematic Literature Review on the Applications for Artificial Intelligence Ultrasound Imaging in Obstetrics and Gynecology (2023) · cites this paper as [199]
The Abstract reports that KOIOS AI analysis could have avoided 17 BI-RADS 3 biopsies. But Materials and Methods describes submitting a single ultrasound image to KOIOS, not using an AI-assisted multimodal shear-wave elastography model. The paper also does not establish the citing document’s count of two studies. (LLM, conf=0.87)
Experimental — accuracy not yet measuredAI-assisted US has the potential to allow for cost-effective, population-based screening methods, e.g., for breast US.
“AI-assisted US also has the potential to allow for cost-effective, population-based screening methods, e.g., for breast US [193,198,199].”
From Evolving the Era of 5D Ultrasound? A Systematic Literature Review on the Applications for Artificial Intelligence Ultrasound Imaging in Obstetrics and Gynecology (2023) · cites this paper as [199]
The Introduction says AI may help address limitations of breast ultrasound, and the Conclusions suggest it could help trained non-medical operators triage symptomatic women where expert opinions are unavailable. Neither section establishes cost-effectiveness or the potential for population-based screening; the proposed use is symptomatic triage, not screening a general population. (LLM, conf=0.86)
Experimental — accuracy not yet measuredThe use of AI-assisted US has been shown to reduce unnecessary breast biopsies.
“the use of AI-assisted US has been shown to reduce the amount of unnecessary hospital admissions due to misdiagnosis and unnecessary breast biopsies [197,199,200].”
From Evolving the Era of 5D Ultrasound? A Systematic Literature Review on the Applications for Artificial Intelligence Ultrasound Imaging in Obstetrics and Gynecology (2023) · cites this paper as [199]
The Abstract reports that 17 BI-RADS 3 biopsies could have been avoided using KOIOS. But the Discussion describes a retrospective comparison of images from cases already biopsied, not an observed reduction in biopsies in clinical practice; the Conclusions call for prospective testing of biopsy triage. (LLM, conf=0.88)
Experimental — accuracy not yet measuredTwo further studies resulted in the possibility of avoiding unnecessary breast biopsies.
“The possibility of avoiding unnecessary breast biopsies was the result of two further studies”
The use of AI-assisted US has been shown to reduce the amount of unnecessary hospital admissions due to misdiagnosis.
“the use of AI-assisted US has been shown to reduce the amount of unnecessary hospital admissions due to misdiagnosis and unnecessary breast biopsies [197,199,200].”
From Evolving the Era of 5D Ultrasound? A Systematic Literature Review on the Applications for Artificial Intelligence Ultrasound Imaging in Obstetrics and Gynecology (2023) · cites this paper as [199]
The Results and Discussion describe how AI-assisted breast ultrasound might avoid some unnecessary biopsies, but they do not report hospital admissions or show a reduction in admissions due to misdiagnosis. Searches for hospital admissions and misdiagnosis found no passage addressing that claim. (LLM, conf=0.76)
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Can we open the black box of AI?
Castelvecchi, D. (2016) · Nature · doi:10.1038/538020a · Cited by 1,773 · see citing works
Artificial intelligence and the future of global health
Schwalbe, N., & Wahl, B. (2020) · The Lancet · doi:10.1016/s0140-6736(20)30226-9 · Cited by 912 · see citing works
On the interpretability of artificial intelligence in radiology: challenges and opportunities
Reyes, M., Meier, R., Pereira, S., Silva, C. A., Dahlweid, F.-M., Tengg-Kobligk, H. V., Summers, R. M., & Wiest, R. (2020) · Radiology: Artificial Intelligence · doi:10.1148/ryai.2020190043 · Cited by 484 · see citing works
What the radiologist should know about artificial intelligence – an ESR white paper
European Society of Radiology (2019) · Insights into Imaging · doi:10.1186/s13244-019-0738-2 · Cited by 338 · see citing works
Ultrasound as the Primary Screening Test for Breast Cancer: Analysis From ACRIN 6666
Berg, W. A., Bandos, A. I., Mendelson, E. B., Lehrer, D. E., Jong, R. A., & Pisano, E. D. (2015) · JNCI Journal of the National Cancer Institute · doi:10.1093/jnci/djv367 · Cited by 310 · see citing works
Shen, Y., Shamout, F. E., Oliver, J. R., Witowski, J. S., Kannan, K., Park, J., Wu, N., Huddleston, C., Wolfson, S., Millet, A., et al. (2021) · Nature Communications · doi:10.1038/s41467-021-26023-2 · Cited by 278 · see citing works
Introduction to artificial intelligence in ultrasound imaging in obstetrics and gynecology
Drukker, L., Noble, J. A., & Papageorghiou, A. T. (2020) · Ultrasound in Obstetrics & Gynecology · doi:10.1002/uog.22122 · Cited by 240 · see citing works
Artificial intelligence for global health
Hosny, A., & Aerts, H. J. W. L. (2019) · Science · doi:10.1126/science.aay5189 · Cited by 177 · see citing works
Artificial Intelligence in Radiology—Ethical Considerations
Brady, A. P., & Neri, E. (2020) · Diagnostics · doi:10.3390/diagnostics10040231 · Cited by 150 · see citing works
Mango, V. L., Sun, M., Wynn, R. T., et al. (2020) · American Journal of Roentgenology · doi:10.2214/ajr.19.21872 · Cited by 114 · see citing works
Performance of ultrasonography screening for breast cancer: a systematic review and meta-analysis
Yang, L., Wang, S., Zhang, L., Sheng, C., Song, F., Wang, P., & Huang, Y. (2020) · BMC Cancer · doi:10.1186/s12885-020-06992-1 · Cited by 102 · see citing works
Kim, K.-W., Song, M. K., Kim, E., et al. (2016) · ULTRASONOGRAPHY · doi:10.14366/usg.16012 · Cited by 101 · see citing works
Park, H. J., Kim, S. M., Yun, B. L., Jang, M., Kim, B., Jang, J. Y., Lee, J. Y., & Lee, S. H. (2019) · Medicine · doi:10.1097/md.0000000000014146 · Cited by 91 · see citing works
The ethical adoption of artificial intelligence in radiology
Mudgal, K. S., & Das, N. (2020) · BJR|Open · doi:10.1259/bjro.20190020 · Cited by 52 · see citing works
Barinov, L., Jairaj, A., Becker, M. D., Seymour, S. E., Lee, E. S., Schram, A. M., Lane, E., Goldszal, A. F., Quigley, D. A., & Paster, L. (2018) · Journal of Imaging Informatics in Medicine · doi:10.1007/s10278-018-0132-5 · Cited by 48 · see citing works
Characteristics of breast cancers detected by ultrasound screening in women with negative mammograms
Bae, M. S., Han, W., Koo, H. R., Cho, N., Chang, J. M., Yi, A., Park, I., Noh, D., Choi, W. S., & Moon, W. K. (2011) · Cancer Science · doi:10.1111/j.1349-7006.2011.02034.x · Cited by 44 · see citing works
Love, S. M., Berg, W. A., Podilchuk, C. I., Aldrete, A. L. L., Mascareño, A. P. G., Pathicherikollamparambil, K., Sankarasubramanian, A., Eshraghi, L., & Mammone, R. J. (2018) · Journal of Global Oncology · doi:10.1200/jgo.17.00222 · Cited by 39 · see citing works
Zhang, D., Jiang, F., Yin, R. M., Wu, G.-G., Wei, Q., Cui, X., Zeng, S., Ni, X., & Dietrich, C. F. (2021) · Medical Science Monitor · doi:10.12659/msm.931957 · Cited by 39 · see citing works
Karako, K., Song, P., Chen, Y., et al. (2020) · BioScience Trends · doi:10.5582/bst.2020.03364 · Cited by 36 · see citing works
Decision quality support in diagnostic breast ultrasound through artificial Intelligence
Barinov, L., Jairaj, A., Paster, L., Hulbert, W., Mammone, R. J., & Podilchuk, C. I. (2016) · IEEE Signal Processing in Medicine and Biology Symposium · doi:10.1109/spmb.2016.7846873 · Cited by 15 · see citing works
Flagged first, then by citations
Research works printed but not linked: 2
- [11]Yiming G. Can an Artificial Intelligence Decision Aid Decrease False Positive Breast Biopsies? Retrospective Study With vs Without AI Decision Support Proceedings of the SBI ACR Breast Imaging Symposium Denver, CO, USA 16–19 April 2020
- [12]Cavallo J. A.I. Analysis of Ultrasound Images Could Decrease the Rate of Benign Breast Biopsies. Retrospective Study of Biopsied BI-RADS 4 and 5 Lesions In Proceedings of the SBI ACR Breast Imaging Symposium Denver, CO, USA 16–19 April 2020
Cited by
Sorted by citations
Jost, E., Kosian, P., Jimenez Cruz, J., Albarqouni, S., Gembruch, U., Strizek, B., & Recker, F. (2023) · Journal of Clinical Medicine · doi:10.3390/jcm12216833 · Cited by 44 · see citing works
- Authors
- Browne, J. L., Pascual, M. Á., Perez, J., Salazar, S., Valero, B., Rodriguez, I., Cassina, D., Alcázar, J. L., Guerriero, S., & Graupera, B.
- Affiliations
- Hospital Universitario Dexeus (ES)
- Department of Obstetrics, Gynecology, and Reproduction, Hospital Universitari Dexeus, 08028 Barcelona, Spain
- Clinica Universidad de Navarra (ES)
- University of Cagliari (IT)
- ORCID
- Venue
- Diagnostics
- Publisher
- MDPI AG
- Published
- 2023-02-20
- Volume
- 13
- Issue
- 4
- Pages
- 811
- ISSN
- 2075-4418 (ISSN-L)
- PMC
- PMC9955683
- OpenAlex
- W4321459805
- Cited by
- 20
- References
- 20
- Citations by year
- 2026: 6 · 2025: 8 · 2024: 2 · 2023: 4
- FWCI
- 1.89
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Diagnostics (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- UNICA IRIS Institutional Research Information System (University of Cagliari) (submittedVersion, other-oa)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › AI in cancer detection
- Health Sciences › Medicine › Pathology and Forensic Medicine › Breast Lesions and Carcinomas
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Keywords
- breast ultrasound, BI-RADS, breast biopsy, breast cancer, BI-RADS 3, unnecessary biopsy reduction, diagnostic accuracy
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
