Performance of an artificial intelligence tool in percutaneous breast biopsies
Austral Journal of Imaging (English Edition) · 30.04.2026 · 32 (2)
DOI: 10.24875/aji.25000031 ↗Kurz gefasst
Fachartikel in der Zeitschrift Austral Journal of Imaging (English Edition), online erschienen am 30.04.2026. Verfasst von Paulina Neira-Vallejos und 5 weiteren Autor:innen.
Abstract (Originalsprache)
Introduction
The use of artificial intelligence (AI) tools in breast ultrasound has shown an increase in the diagnostic accuracy of breast cancer.
Objective
To evaluate the diagnostic performance of artificial intelligence (AI) software in the detection of breast cancer in breast lesions biopsied under ultrasound guidance. Material and methods: This prospective diagnostic testing study included the results of patients who underwent ultrasound-guided percutaneous breast biopsy. Images were analyzed and classified by degree of suspicion, first with an ACR BI-RADS category assigned by a specialist radiologist and then by AI software. These were subsequently correlated with the histopathology results obtained from the biopsy, which served as the reference standard.
Results
181 lesions were included in this study, of which 80 were malignant and 101 benign lesions. The sensitivity of the AI tool was 95%, specificity 58%, positive predictive value (PPV) 64%, negative predictive value (NPV) 93%, and accuracy 0.74. The values obtained by the radiologists were 98% sensitivity, 19% specificity, 49% PPV, 95% NPV, and 0.54 accuracy.
Conclusions
The AI software demonstrated superior specificity and PPV compared to radiologists in lesions biopsied and could therefore be used to reduce the number of biopsies with benign results.
Zitieren
APA
Neira-Vallejos, P., Vial, M. C., Behnke, C., Poblete-Becker, M., Wersch, M. R. V., & Santelices, E. (2026). Performance of an artificial intelligence tool in percutaneous breast biopsies. Austral Journal of Imaging (English Edition), 32(2). https://doi.org/10.24875/aji.25000031
Vancouver
Neira-Vallejos P, Vial MC, Behnke C, Poblete-Becker M, Wersch MRV, Santelices E. Performance of an artificial intelligence tool in percutaneous breast biopsies. Austral Journal of Imaging (English Edition). 2026;32(2). doi:10.24875/aji.25000031
BibTeX
@article{NeiraVallejos2026,
author = {Neira-Vallejos, Paulina and Vial, María C. and Behnke, Carolina and Poblete-Becker, Marcelo and Wersch, M. Rosario van and Santelices, Emilia},
title = {Performance of an artificial intelligence tool in percutaneous breast biopsies},
journal = {Austral Journal of Imaging (English Edition)},
year = {2026},
volume = {32},
number = {2},
doi = {10.24875/aji.25000031}
}
EUVIMED