Value of computer-aided detection combined with automated breast ultrasound system in breast cancer diagnosis in doctors with different seniority

YAN Jingru; YANG Shanling; SONG Hongping; ZHOU Xiaodong

doi:10.16245/j.cnki.issn1008-6978.2020.03.013

您当前的位置：

首页 >

文章列表页 >

Value of computer-aided detection combined with automated breast ultrasound system in breast cancer diagnosis in doctors with different seniority

更新时间：2021-10-13

- Value of computer-aided detection combined with automated breast ultrasound system in breast cancer diagnosis in doctors with different seniority
- Journal of Clinical Ultrasound in Medicine Vol. 22, Issue 3, Pages: 194-197(2020)
- 作者机构：
  
  1. 西安国际医学中心医院超声诊疗中心
  2. 西京医院超声医学科
- 作者简介：
- 基金信息：
- DOI：10.16245/j.cnki.issn1008-6978.2020.03.013
  CLC： R737.9;R445.1;TP391.7
- Published：2020，
扫描看全文
[1]闫静茹,杨珊灵,宋宏萍,周晓东.不同年资医师应用自动乳腺超声诊断系统结合CAD对乳腺恶性病灶的诊断价值[J].临床超声医学杂志,2020,22(03):194-197.

YAN Jingru, YANG Shanling, SONG Hongping, et al. Value of computer-aided detection combined with automated breast ultrasound system in breast cancer diagnosis in doctors with different seniority. [J]. Journal of Clinical Ultrasound in Medicine 22(3):194-197(2020)
[1]闫静茹,杨珊灵,宋宏萍,周晓东.不同年资医师应用自动乳腺超声诊断系统结合CAD对乳腺恶性病灶的诊断价值[J].临床超声医学杂志,2020,22(03):194-197. DOI： 10.16245/j.cnki.issn1008-6978.2020.03.013.

YAN Jingru, YANG Shanling, SONG Hongping, et al. Value of computer-aided detection combined with automated breast ultrasound system in breast cancer diagnosis in doctors with different seniority. [J]. Journal of Clinical Ultrasound in Medicine 22(3):194-197(2020) DOI： 10.16245/j.cnki.issn1008-6978.2020.03.013.

摘要

目的探讨不同年资医师应用计算机辅助诊断系统（CAD）辅助自动乳腺超声诊断系统（ABUS）对于诊断乳腺恶性病灶的价值。方法收集行ABUS检查的乳腺病灶患者1452例

其中

恶性270例

共282个病灶;良性674例

共695个病灶;阴性508例。比较6名医师（3名低年资医师与3名高年资医师）使用CAD系统前后的诊断敏感性、特异性、受试者工作特征（ROC）曲线下面积及平均阅读时间。结果应用CAD前

低年资医师与高年资医师诊断恶性病灶的敏感性分别为87%、93%

使用CAD后均提高至94%

低年资医师使用CAD前、后诊断敏感性比较差异有统计学意义（P<0.05）

高年资医师差异无统计学意义。6名医师在使用CAD系统前后诊断特异性无变化。低年资医师在使用CAD系统后的诊断准确率有所提高

曲线下面积由0.85提高至0.89

差异有统计学意义（P<0.05）;而高年资医师在使用CAD系统后

虽然ROC曲线下面积由0.91提高至0.92

但差异无统计学意义。所有医师使用CAD后的平均阅读时间均有不同程度的延长

差异有统计学意义（P<0.05）。结论虽然使用CAD后的平均阅读时间有所延长

但在可接受范围内

ABUS结合CAD能大大提高超声医师诊断乳腺恶性病灶的准确率和敏感性

且对低年资医师帮助更大。

Abstract

ObjectiveTo investigate the value of computer-aided detection（CAD）assisted automated breast ultrasound system（ABUS）for malignant breast lesions diagnosis in doctors with different seniority.MethodsOf the 1452 breast cases

270 cases were malignant with a total of 282 lesions

674 cases were benign with a total of 695 lesions

and 508 were negative.The diagnostic sensitivity

specificity

area under the ROC curve

and average reading time were compared among 6 doctors（3 junior and 3 senior）before and after using the CAD system.Results Before the application of CAD system

the sensitivity of junior and senior doctors were 87% and 93%

respectively

and both increased to 94% after using CAD.There was significant difference in the sensitivity of junior doctors before and after using CAD（P<0.05）

while no statistic difference was found in the senior doctors before and after using CAD.Diagnostic specificity of the 6 doctors decreased slightly before and after using the CAD system

but the difference was not significant.The diagnostic accuracy of junior doctors has improved

and the area under the curve has increased from 0.85 to 0.89

the differences was statistically significant（P<0.05）. The area under the curve has increased from 0.91 to 0.92 in senior doctors after using CAD

but there was no significant difference.The mean reading time of all doctors after using CAD was prolonged to varying degrees

and the difference was statistically significant（P<0.05）.Conclusion Although the average reading time after using CAD has been extended

within the acceptable range

the reading mode of ABUS combined with CAD can greatly improve the accuracy and sensitivity of ultrasonic doctors in diagnosing malignant breast lesions

and it is more helpful to junior doctors.

关键词

自动乳腺超声诊断系统计算机辅助诊断系统乳腺肿瘤良恶性医师不同年资

Keywords

Automated breast ultrasound systemComputer-aided detectionBreast tumorbenign and malignantDoctordifferent seniority

references

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Clinical value of virtual touch image quantification in differentiating benign and malignant breast lesions

Value of acceleration time index and ratio of elastic strain rate in the differential diagnosis of benign and malignant breast tumors

Establishment of predictive models of contrast-enhanced ultrasound in the evaluation of BI-RADS 4 category breast lesions

Differential diagnostic value of ultrasomics in benign and malignant breast lesions of BI-RADS category 4

Related Author

宋宏萍

杨珊灵

闫静茹

GUO Ruiqiang

XU Fenfen

LIU Na

PENG Juan

PU Huan

Related Institution

Xi'an International Medical Center Hospital

空军军医大学第一附属医院

Department of Medical Ultrasound,Renmin Hospital of Wuhan University

Department of Ultrasound,the Second People’s Hospital of Huai’an

江苏省淮安市第二人民医院检验科

⁰