Biopsy or Follow-up: AI Improves the Clinical Strategy of US BI-RADS 4A Breast Nodules Using a Convolutional Neural Network

To develop predictive nomograms based on clinical and ultrasound features and to improve the clinical strategy for US BI-RADS 4A lesions. Patients with US BI-RADS 4A lesions from 3 hospitals between January 2016 and June 2020 were retrospectively included. Clinical and ultrasound features were extra...

Full description

Saved in:
Bibliographic Details
Published in:Clinical breast cancer 2024-07, Vol.24 (5), p.e319-e332.e2
Main Authors: Yi, Mei, Lin, Yue, Lin, Zehui, Xu, Ziting, Li, Lian, Huang, Ruobing, Huang, Weijun, Wang, Nannan, Zuo, Yanling, Li, Nuo, Ni, Dong, Zhang, Yanyan, Li, Yingjia
Format: Article
Language:English
Subjects:
Breast cancer
Deep learning
Nomogram
Ultrasound
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:To develop predictive nomograms based on clinical and ultrasound features and to improve the clinical strategy for US BI-RADS 4A lesions. Patients with US BI-RADS 4A lesions from 3 hospitals between January 2016 and June 2020 were retrospectively included. Clinical and ultrasound features were extracted to establish nomograms CE (based on clinical experience) and DL (based on deep-learning algorithm). The performances of nomograms were evaluated by receiver operator characteristic curves, calibration curves and decision curves. Diagnostic performances with DL of radiologists were analyzed. 1616 patients from 2 hospitals were randomly divided into training and internal validation cohorts at a ratio of 7:3. Hundred patients from another hospital made up external validation cohort. DL achieved more optimized AUCs than CE (internal validation: 0.916 vs. 0.863, P < .01; external validation: 0.884 vs. 0.776, P = .05). The sensitivities of DL were higher than CE (internal validation: 81.03% vs. 72.41%, P = .044; external validation: 93.75% vs. 81.25%, P = .4795) without losing specificity (internal validation: 84.91% vs. 86.47%, P = .353; external validation: 69.14% vs. 71.60%, P = .789). Decision curves indicated DL adds more clinical net benefit. With DL's assistance, both radiologists achieved higher AUCs (0.712 vs. 0.801; 0.547 vs. 0.800), improved specificities (70.93% vs. 74.42%, P < .001; 59.3% vs. 81.4%, P = .004), and decreased unnecessary biopsy rates by 6.7% and 24%. DL was developed to discriminate US BI-RADS 4A lesions with a higher diagnostic power and more clinical net benefit than CE. Using DL may guide clinicians to make precise clinical decisions and avoid overtreatment of benign lesions. This study aimed to develop nomograms using clinical and ultrasound features and to improve the clinical strategy for US BI-RADS 4A lesions. One thousand seven hundred sixteen lesions were randomized into 3 groups to develop Nomogram CE and DL. DL achieved more optimized AUCs than CE, with higher sensitivities without losing specificity. With DL's assistance, radiologists achieved higher AUCs and decreased unnecessary biopsy rates. DL may guide clinicians to make precise clinical decisions and avoid biopsies of benign lesions.
ISSN:1526-8209
1938-0666
1938-0666
DOI:10.1016/j.clbc.2024.02.003