This article has been reviewed according to Science X's editorial process and policies. Editors have highlighted the following attributes while ensuring the content's credibility:


peer-reviewed publication

trusted source


Computer‐aided diagnosis improves breast ultrasound expertise in multicenter study

Computer‐aided diagnosis improves breast ultrasound expertise in multicenter study
Long-axis gray-scale ultrasound image shows hypoechoic lesion. Lesion was classified by study radiologist as BI-RADS category 4A. Credit: ARRS/AJR

According to an accepted manuscript published in ARRS' own American Journal of Roentgenology (AJR), deep learning–based computer-aided diagnosis (CAD) for breast lesion classification on ultrasound significantly improved radiologists' diagnostic performance—particularly for reducing the frequency of benign breast biopsies.

Compared with the literature supporting CAD at tertiary and/or urban centers, results from this prospective multicenter study of radiologists without breast ultrasound expertise "support CAD in settings with incomplete access to breast imaging expertise," wrote corresponding author Li-Gang Cui, MD, from Peking University Third Hospital in Beijing, China.

The study included scheduled to undergo or surgical resection of a breast lesion, classified as BI-RADS category 3-5 on prior breast ultrasound, at eight Chinese secondary or rural hospitals from November 2021 to September 2022. Patients underwent an additional investigational breast ultrasound, both performed and interpreted by a with no expertise in the modality. Hybrid body-breast imagers—radiologists lacking breast subspecialty training or in whom breast ultrasound accounted for less than 10% of their ultrasounds performed annually—then assigned a BI-RADS category. CAD results were used to upgrade reader-assigned BI-RADS category 3 lesions to category 4A, as well as for downgrading BI-RADS 4A lesions to 3. Histologic results of biopsy or resection served as the researchers' reference standard.

Computer‐aided diagnosis improves breast ultrasound expertise in multicenter study
Long-axis greyscale ultrasound image shows results of CAD analysis. CAD provided result of “possibly benign” for both images. Lesion was therefore downgraded to category 3 based on CAD output. Pathologic assessment based on surgical resection was fibroadenoma. Credit: ARRS/AJR

Ultimately, application of CAD to interpretations by radiologists without breast ultrasound expertise resulted in upgrade of 6.0% (6/100) of BI-RADS category 3 assessments to category 4A, of which 16.7% (1/6) were malignant, and downgrade of 79.1% (87/110) of category 4A assessments to category 3, of which 4.6% (4/87) were malignant.

Because institutions lacking breast imaging expertise may also suffer from capacity issues to perform image-guided breast biopsies and pathologic evaluation of biopsy specimens, decreasing benign biopsies care of CAD "would be impactful," the authors of this manuscript added.

More information: Deep Learning–Based Computer‑Aided Diagnosis for Breast Lesion Classification on Ultrasound: A Prospective Multicenter Study of Radiologists Without Breast Ultrasound Expertise, American Journal of Roentgenology (2023). DOI: 10.2214/AJR.23.29328

Citation: Computer‐aided diagnosis improves breast ultrasound expertise in multicenter study (2023, May 24) retrieved 4 October 2023 from
This document is subject to copyright. Apart from any fair dealing for the purpose of private study or research, no part may be reproduced without the written permission. The content is provided for information purposes only.

Explore further

AI helpful in triaging breast masses in low-resource areas


Feedback to editors