Clinical Application of Computer-Aided Diagnosis According to S-Detect in Category 4 Breast Lesions: Prospective Single-Center Study (Preprint)

Author:

Sun PengfeiORCID,Chen ChenORCID,Wang WeiqiORCID,Liang LeiORCID,Luo DanORCID,Guo JunORCID

Abstract

BACKGROUND

Computer-aided diagnosis (CAD) is a useful tool that can provide a reference for the differential diagnosis of benign and malignant breast lesion. Previous studies have demonstrated that CAD can improve the diagnostic performance. However, conventional ultrasound (US) combined with CAD were used to adjust the classification of category 4 lesions has been few assessed.

OBJECTIVE

The objective of our study was to evaluate the diagnosis performance of conventional ultrasound combined with a CAD system S-Detect in the category of BI-RADS 4 breast lesions.

METHODS

Between December 2018 and May 2020, we enrolled patients in this study who received conventional ultrasound and S-Detect before US-guided biopsy or surgical excision. The diagnostic performance was compared between US findings only and the combined use of US findings with S-Detect, which were correlated with pathology results.

RESULTS

A total of 98 patients (mean age 51.06 years, range 22-81, SD16.25) with 110 breast masses (mean size1.97±1.38cm, range0.6-8.5cm) were included in this study. Of the 110 breast masses, 64/110 (58.2%) were benign, 46/110 (41.8%) were malignant. Compared with conventional ultrasound, a significant increase in specificity (0% to 53.12%, P<.001), accuracy (41.81% to70.19%, P<.001) were noted, with no statistically significant decrease on sensitivity (100% to 95.65%, P=.48). According to S-Detect-guided US BI-RADS re-classification, 30 out of 110 (27.3%) breast lesions underwent a correct change in clinical management, 74of 110 (67.3%) breast lesions underwent no change and 6 of 110 (5.5%) breast lesions underwent an incorrect change in clinical management. The biopsy rate decreased from 100.0% to 67.3 % (P<.001).Benign masses among subcategory 4a had higher rates of possibly benign assessment on S-Detect for the US only (60.0% to 0.0%, P<.001).

CONCLUSIONS

S-Detect can be used as an additional diagnostic tool to improve the specificity and accuracy in clinical practice. S-Detect have the potential to be used in downgrading benign masses misclassified as BI-RADS category 4 on US by radiologist, and may reduce unnecessary breast biopsy.

CLINICALTRIAL

None

Publisher

JMIR Publications Inc.

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3