检索结果-南通市图书馆

Detection and classification of breast lesions using multiple information on contrast-enhanced mammography by a multiprocess deep-learning system: A multicenter study

引用

中国癌症研究:英文版 2023年第4期35卷 408-423页

作者： Yuqian Chen Zhen Hua Fan Lin Tiantian Zheng Heng Zhou Shijie Zhang Jing Gao Zhongyi Wang Huafei Shao Wenjuan Li Fengjie Liu Simin Wang Yan Zhang Feng Zhao Hao Liu Haizhu Xie Heng Ma Haicheng Zhang Ning Mao School of Information and Electronic Engineering Shandong Technology and Business UniversityYantai 264005China Department of Radiology Yantai Yuhuangding HospitalAffiliated Hospital of Qingdao UniversityYantai 264000China School of Medical Imaging Binzhou Medical UniversityYantai 264003China Department of Radiology Fudan University Cancer CenterShanghai 200433China Department of Radiology Guangdong Maternal and Child Health HospitalGuangzhou 510010China School of Computer Science and Technology Shandong Technology and Business UniversityYantai 264005China Yizhun Medical AI Co.Ltd. Beijing 100080China Big Data and Artificial Intelligence Laboratory Yantai Yuhuangding HospitalAffiliated Hospital of Qingdao UniversityYantai 264000China

Objective: Accurate detection and classification of breast lesions in early stage is crucial to timely formulate effective treatments for patients. We aim to develop a fully automatic system to detect and classify breast lesions using multiple contrast-enhanced mammography(CEM) images.Methods: In this study, a total of 1,903 females who underwent CEM examination from three hospitals were enrolled as the training set, internal testing set, pooled external testing set and prospective testing set. Here we developed a CEM-based multiprocess detection and classification system(MDCS) to perform the task of detection and classification of breast lesions. In this system, we introduced an innovative auxiliary feature fusion(AFF)algorithm that could intelligently incorporates multiple types of information from CEM images. The average freeresponse receiver operating characteristic score(AFROC-Score) was presented to validate system’s detection performance, and the performance of classification was evaluated by area under the receiver operating characteristic curve(AUC). Furthermore, we assessed the diagnostic value of MDCS through visual analysis of disputed cases,comparing its performance and efficiency with that of radiologists and exploring whether it could augment radiologists’ performance.Results: On the pooled external and prospective testing sets, MDCS always maintained a high standalone performance, with AFROC-Scores of 0.953 and 0.963 for detection task, and AUCs for classification were 0.909[95% confidence interval(95% CI): 0.822-0.996] and 0.912(95% CI: 0.840-0.985), respectively. It also achieved higher sensitivity than all senior radiologists and higher specificity than all junior radiologists on pooled external and prospective testing sets. Moreover, MDCS performed superior diagnostic efficiency with an average reading time of 5 seconds, compared to the radiologists’ average reading time of 3.2 min. The average performance of all radiologists was also improved to varying degrees with MDCS assistance.Conclusion

关键词： Deep learning contrast-enhanced mammography breast lesions detection classification

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Application Value of Contrast-Enhanced Ultrasound in the Diagnosis of breast lesions

引用

Journal of Clinical and Nursing Research 2022年第4期6卷 102-107页

作者： Meiqing He Xixi Zhang Hui Li Tian Wang Ultrasonic Diagnosis Center of Shaanxi Provincial People’s Hospital Xi’an 710068Shaanxi ProvinceChina

Objective:To explore the value and effect of contrast-enhanced ultrasound in the diagnosis of breast lesions.Methods:Seventy-two patients with breast lesions in Shaanxi Provincial People’s Hospital from June 2020 to December 2021 were selected as the research subjects.All 72 patients met the diagnostic criteria of breast lesions.Two patients with incomplete clinical data were excluded;hence,there were 70 patients remaining.The diagnostic results of the two examination methods and the diagnostic value of the joint examination for breast lesions were analyzed and compared.Results:The results of benign,malignant,missed,and misdiagnosed breast lesions by contrast-enhanced ultrasound were 31,32,6,and 1 cases,respectively,accounting for 44.29%,45.71%,8.57%,and 1.43%,respectively.The results of benign,malignant,missed,and misdiagnosed breast lesions by ultrasound automatic volume imaging were 21,24,17,and 8 cases,respectively,accounting for 30.00%,34.28%,24.29%,and 11.43%,respectively.There were statistical differences between the two groups for missed diagnosis and misdiagnosis,but there was no significant difference between the two groups for benign and malignant lesions.The accuracy,sensitivity,and specificity of contrast-enhanced ultrasound were 87.69%,83.62%,and 83.45%,respectively;the accuracy,sensitivity,and specificity of ultrasound automatic volume imaging were 71.39%,68.99%,and 74.69%,respectively;the accuracy,sensitivity,and specificity of contrast-enhanced ultrasound combined with ultrasound automatic volume imaging were 96.29%,92.68%,and 91.78%,respectively.Conclusion:Contrast-enhanced ultrasonography has a high clinical application value and a low inspection error rate in the diagnosis of breast lesions.It merits clinical advancement since it helps doctors diagnose and treat breast lesions more effectively.

关键词： Contrast enhanced ultrasound breast lesions Application value Ultrasound automatic volume imaging

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Implementation of two-dimensional shear wave elastography and acoustic radiation force impulse induced strain elastography in combination with B-mode ultrasound:a method avoids unnecessary biopsies of breast lesions

Implementation of two-dimensional shear wave elastography an...

引用

中国超声医学工程学会第五届全国介入超声医学学术交流大会

作者： Jia-Wei Sun Xian-Li Zhou In-Patient Ultrasound Department Second Affiliated Hospital of Harbin Medical University

Purpose:To investigate the diagnostic performance of two-dimensional shear wave elastography and acoustic radiation force impulse induced strain elastography in diff erentiation benign and malignant breast lesions.And to explore the performance in avoiding unnecessary biopsies when they combine with B(mode ultrasound.Methods:One hundred fifty nine benign breast lesions and one hundred eleven malignant breast lesions were retrospectively analyzed.Conventional ultrasound(CUS) features and virtual touch imaging(VTI) and virtual touch tissue imaging and quantification(VTIQ) parameters of all the lesions were reviewed.The shear wave speed(SWS) and VTI score were acquired.The area under the receiver operating characteristic(AUCROC) curve analysis was performed to evaluate the best cut(off value of SWS and VTI score.We decreased the BI-RADS grade of the lesion form 4 a to 3 when either one of the VTIQ or VTI were negative.The reference standard was histopathological and/or core-needle biopsy(CNB) results.Results:The SWS and the VTI score of malignant lesions were significantly higher than those of benign lesions(P lesions on B-mode ultrasound degraded to 3 which avoided unnecessary biopsies.Conclusion:Combination of VTIQ and VTI is a strong complement to B-mode ultrasound,which is a promising method in the differential diagnosis of the breast lesions as well as reduce unnecessary biopsies.

关键词： Virtual touch tissue imaging and quantification breast lesions Virtual touch imaging Biopsy

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

欢迎您,

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

在线全文

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：