[1]严 郁a,朱 伟a,蔡润秋a,等.基于超声射频信号的乳腺肿瘤分级算法研究[J].南京理工大学学报(自然科学版),2018,42(04):385.[doi:10.14177/j.cnki.32-1397n.2018.42.04.001]
 Yan Yua,Zhu Weia,Cai Runqiua,et al.Breast tumor classification algorithm based on ultrasoundradio frequency signal[J].Journal of Nanjing University of Science and Technology,2018,42(04):385.[doi:10.14177/j.cnki.32-1397n.2018.42.04.001]
点击复制

基于超声射频信号的乳腺肿瘤分级算法研究()
分享到:

《南京理工大学学报》(自然科学版)[ISSN:1005-9830/CN:32-1397/N]

卷:
42卷
期数:
2018年04期
页码:
385
栏目:
出版日期:
2018-08-30

文章信息/Info

Title:
Breast tumor classification algorithm based on ultrasoundradio frequency signal
文章编号:
1005-9830(2018)04-0385-07
作者:
严 郁12a朱 伟2a蔡润秋2a蔡晓巍2a张 宏1李千目1吴意赟2b
1.南京理工大学 计算机科学与工程学院,江苏 南京 210094; 2.南京中医药大学附属医院(江苏省中医院)a.设备处b.超声医学科,江苏 南京210029
Author(s):
Yan Yu12aZhu Wei2aCai Runqiu2aCai Xiaowei2aZhang Hong1Li Qianmu1Wu Yiyun2b
1.School of Computer Science and Engineering,Nanjing University of Science and Technology,Nanjing 210094,China; 2.a. Medical Equipment Department; b. Ultrasound Medical Department,Affiliated Hospital Nanjing University of TCM(Jiangsu Province Hospital of TCM),Nanjing 210029,China
关键词:
乳腺肿瘤 射频信号 感兴趣区 标准差 乳腺影像报告和数据系统 图像重建 分级
Keywords:
breast tumor radio frequency signals region of interest entropy standard deviation breast imaging reporting and data system image reconstruction classification
分类号:
TP391.7
DOI:
10.14177/j.cnki.32-1397n.2018.42.04.001
摘要:
为解决乳腺肿瘤超声的定量分级问题,从超声射频信号的角度提出了一种乳腺肿瘤分级的评价算法。以乳腺影像报告和数据系统(Breast imaging reporting and data system,BI-RADS)作为分级依据,将提取的超声射频(Radio frequency,RF)信号进行图像重建、图像分割并获取乳腺肿瘤感兴趣区(Region of interest,ROI)及其特征参数:熵和标准差。量化分析特征参数与病灶良恶性分级之间的关系,实现了对乳腺肿瘤的3级、4级、5级的分级,分类成功率达到84.9%。研究结果表明,超声射频信号对辅助临床诊断具有重要意义,熵和标准差可以有效地实现乳腺肿瘤超声分级。
Abstract:
To solve the problem of quantitative classification of breast tumor ultrasound,an evaluation algorithm for quantitative classification of breast tumor is proposed from the perspective of ultrasonic radio frequency(RF)signal. Using breast imaging reporting and data system(BI-RADS)as the classification basis,the extracted RF data are reconstructed and segmented to acquire the region of interest(ROI)and its characteristic parameters of entropy and standard deviation are acquired. This paper quantifies the relationship between the characteristic parameters and the classification of lesion,and achieves the quantitative classification of breast tumor level 3,level 4 and level 5 with a classification success rate of 84.9%. The results show that the ultrasound RF signals have important implications for clinical diagnosis. Entropy and standard deviation can effectively achieve the classification of breast tumor ultrasound.

参考文献/References:

[1] 李晓峰,沈毅.基于支持向量机的超声乳腺肿瘤图像计算机辅助诊断系统[J]. 光电子·激光,2008,19(1):115-119.
Li Xiaofeng,Shen Yi. Support vector machines based computer-aided diagnosis system of breast tumor with ultrasound images[J].Journal of Optoelectronics·Laser,2008,19(1):115-119.
[2]陈秋霞,向军,刘奇,等.乳腺肿瘤超声图像纹理特征分析[J]. 激光杂志,2014(3):65-66.
Chen Qiuxia,Xiang Jun,Liu Qi,et al. Textural feature analysis for ultrasound breast tumor images[J].Laser Journal,2014(3):65-66.
[3]Berg W A,Cosgrove D O,Doré C J,et al. Shear-wave elastography improves the specificity of breast US:the BE1 multinational study of 939 masses[J]. Radiology,2012,262(2):435.
[4]张耀楠,张永亮,肖杨.用于乳腺癌诊断的超声弹性图像特征选择与分类实验[J]. 中国医疗器械杂志,2016,40(6):397-402.
Zhang Yaonan,Zhang Yongliang,XiaoYang. Experi-ments on the feature selection and classiifcation of ultrasound elastography images for the diagnosis of breast cancers[J]. Chinese Journal of Medical Instrumentation,2016,40(6):397-402.
[5]Huang Q,Yang F,Liu L,et al. Automatic segmentation of breast lesions for interaction in ultrasonic computer-aided diagnosis[J]. Information Sciences:An International Journal,2015,314(C):293-310.
[6]Masotti L,Biagi E,Granchi S,et al.Tissue differentiation based on radiofrequency echographic signal local spectral content[C]//2003 IEEE International Ultrasonics Symposium. Piscataway,NJ,USA:IEEE,2003.
[7]Moradi M,Abolmaesumi P,Isotalo P A,et al. A new feature for detection of prostate cancer based on RF ultrasound echo signal[C]//2006 IEEE International Ultrasonics Symposium. Piscataway,NJ,USA:IEEE,2006.
[8]刘志东,罗燕,林江莉,等. 基于超声射频RF信号的脂肪肝分级量化方法[J]. 工程科学与技术,2011(s1):160-164.
Liu Zhidong,Luo Yan,Lin Jiangli,et al. Quantizing and grading of fatty liver based on ultrasonic rf signals[J]. Advanced Engineering Sciences,2011(s1):160-164.
[9]严郁,方舸,蔡润秋,等.基于乳腺肿块的超声射频信号特征算法识别[J].中国医学装备,2016,13(9):20-22.
Yan Yu,Fang Ge,Cai Runqiu,et al. Ultrasound radio frequency characteristic signal processing for breast lump recognition[J]. China Medical Equipment,2016,13(9):20-22.
[10]庄淑莲,周建华,王建伟,等.基于超声射频流的RF时间序列信号在乳腺病变良恶性鉴别中的价值[J].中华医学超声杂志:电子版,2016,13(5):393-397.
Zhuang Shulian,Zhou Jianhua,Wang Jianwei,et al. Differential diagnosis of breast lesions with RF time-series signal based on ultrasonic radio-frequency flow[J]. Chinese Journal of Medical Ultrasound(Electronic Edition),2016,13(5):393-397.
[11]Radiology A C O. Breast imaging reporting and data system(BI-RADS)[M]. Reston,VA,USA:American College of Radiology,2003.
[12]Hong A S,Rosen E L,Soo M S,et al. BI-RADS for sonography:positive and negative predictive values of sonographic features[J]. Ajr Am J Roentgenol,2005,184(4):1260-1265.
[13]Lazarus E,Mainiero M B,Schepps B,et al. BI-RADS lexicon for US and mammography:interobserver variability and positive predictive value[J]. Radiology,2006,239(2):385-391.
[14]陈家益,黄楠,熊刚强,等. 基于置信区间的自适应加权均值滤波算法[J]. 南京理工大学学报,2017,41(3):307-312.
Chen Jiayi,Huang Nan,Xiong Gangqiang,et al. Adaptive weighted mean filtering algorithm based on confidence interval[J]. Journal of Nanjing University of Science and Technology,2017,41(3):307-312.
[15]林其忠,余建国,赵暖,等. 乳腺肿瘤超声图像的特征分析[J].仪器仪表学报,2006,27(s1):744-746.
Lin Qizhong,Yu Jianguo,Zhao Nan,et al. Feature analysis of ultrasound breast tumor images[J]. Chinese Journal of Scientific Instrument,2006,27(s1):744-746.
[16]刘映,林江莉,陈科,等. 基于PCA的脂肪肝超声RF信号特征选择[J]. 实验科学与技术,2014,4:4-7.
Liu Ying,Lin Jiangli,Chen Ke,et al. Feature selection of fatty liver ultrasound radio frequency signal based on principal component analysis[J]. Experiment Science and Technology,2014,4:4-7.

备注/Memo

备注/Memo:
收稿日期:2017-09-02 修回日期:2018-03-24
基金项目:江苏省“六大人才高峰”高层次人才项目(WSN-058)
作者简介:严郁(1979-),男,博士生,高级工程师,主要研究方向:智能服务,E-mail:yanyucan@126.com;
通讯作者:吴意赟(1978-),男,副主任医师,主要研究方向:超声诊断,E-mail:wuyi425@sina.com。
引文格式:严郁,朱伟,蔡润秋,等. 基于超声射频信号的乳腺肿瘤分级算法研究[J]. 南京理工大学学报,2018,42(4):385-391. 投稿网址:http://zrxuebao.njust.edu.cn
更新日期/Last Update: 2018-08-30