乳腺肿块超声特征的判别分析研究  被引量:4

The study of discriminatory analysis of ultrasound characteristics from breast neoplasms

在线阅读下载全文

作  者:叶红梅[1] 

机构地区:[1]绵阳市第三人民医院,四川绵阳621000

出  处:《四川医学》2010年第3期387-389,共3页Sichuan Medical Journal

摘  要:目的探索判别分析法在乳腺肿块性质鉴别方面的应用价值。方法依据研究前确定的标准,选择2007年3月-2009年4月在我院接受乳腺肿块超声检查的患者共计128例作为研究对象,将肿块形态(X1)、钙化点(X2)、腋窝淋巴结(X3)、内部回声(X4)、肿块包膜(X5)、边界(X6)、后方回声(X7)设为观察指标。由同一检查者对超声扫描结果进行观察。数据处理用PEMS3.1统计软件进行处理。结果128例患者共计157个肿块,其中有恶性肿块患者73例,计86个肿块,良性肿块患者55例,计71个肿块;每一观察指标与乳腺肿块的性质均有相关性。判别方程是Y1=-0.8101+0.3762X1+0.0919X2+0.4720X3+0.0030X4-0.1641X5-0.0146X6-0.3131X7;Y2=-9.1910+8.5738X1+2.0948X2+10.7583X3+0.0674X4-3.7411X5-0.3305X6-7.1364X7;2χ=246.8031,P=0.0000;总回代率97.45%。结论利用乳腺肿块的超声特征进行判别分析,判别效果好,简便、快速、经济适用。Objectve To explore the value of discriminant analysis in identifing the nature of breast neoplasms.Methods To select the statistics from 128 cases as the research object,which were examined with ultrasound scan in our hospital from March,2007 to April,2009 in accordance with the pre-fixed standard.Mass forms(X1),calcification(X2),axillary lymph node(X3),internal echo(X4),tumor capsule(X5),the boundary(X6),rear echo(X7)are index of observation.To observe the image of ultrasound scan by the same examiner.Staistics processing with statistical software of PEMS3.1.Results 128 patients with a total of 157 masses,of which 73 cases of malignant tumor with 86 mass.Meanwhile,55 cases of benign tumor with 71 mass;each observed indicators are related to the naturee of breast Neoplasms.Discriminant equation is Y1=-0.8101+0.3762X1+0.0919X2+0.4720X3+0.0030X4-0.1641X5-0.0146X6-0.3131X7;Y2=-9.1910+8.5738X1+2.0948X2+10.7583X3+0.0674X4-3.7411X5-0.3305X6-7.1364X7;χ2=246.8031,P=0.0000.The rate of ringt discriminant is 97.45%. Conclusion The discriminant analysis of breast mass with ultrasound characteristics are effective,simple,fast and economical..

关 键 词:乳腺 肿块 超声 判别分析 影像 

分 类 号:R737.9[医药卫生—肿瘤] R445.1[医药卫生—临床医学]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象