中国组织工程研究

中国组织工程研究 ›› 2010, Vol. 14 ›› Issue (26): 4836-4840.doi: 10.3969/j.issn.1673-8225.2010.26.021

• 骨与关节图像与影像 bone and joint imaging • 上一篇    下一篇

超声图像特征参数分析在乳腺肿瘤鉴别诊断中的应用

蒋 玲1，罗 莹2，彭玉兰3，刘 奇2   

  1. 1成都大学实验技术中心，四川省成都市  610106； 
    2四川大学电气信息学院，四川省成都市  610065； 
    3四川大学华西医院超声科，四川省成都市  610041
  • 出版日期:2010-06-25 发布日期:2010-06-25
  • 作者简介:蒋 玲，女，1968年生，四川省都江堰市人，汉族，1991年西南大学毕业，硕士，讲师，主要从事计算机应用研究。 liuqi@scu.edu.cn

Breast tumor differential diagnosis based on ultrasound image feature parameters analysis

Jiang Ling1, Luo Ying2, Peng Yu-lan3, Liu Qi2   

  1. 1Experiment Technology Center of Chengdu University, Chengdu  610106, Sichuan Province, China;
    2Electrical & Information School of Sichuan University, Chengdu  610065, Sichuan Province, China; 3Department of Ultrasonography, Huaxi Hospital of Sichuan University, Chengdu  610041. Sichuan Province, China
  • Online:2010-06-25 Published:2010-06-25
  • About author:Jiang Ling, Master, Lecturer, Experiment Technology Center of Chengdu University, Chengdu 610106, Sichuan Province, China liuqi@scu.edu.cn

PDF

488

被引次数

18

摘要：

背景：超声诊断具有无损伤、重复性好、适用于鉴别软组织等特点，被广泛地应用于乳腺肿瘤的辅助检测。但是，由于缺乏量化标准，在诊断上具有较大的主观性和不确定性。如何提高诊断的准确性，减少不必要的活检，是临床急待解决的难题。
目的：利用超声图像特征参数分析对经病理证实的乳腺良恶性肿瘤进行鉴别。
方法：利用Level set分割方法对100例乳腺肿瘤做超声图像分割，选用了伸长度、紧凑性和圆形度及7个Hu不变矩共10个特征值进行计算分析。
结果与结论：采用伸长度、紧凑性和圆形度3个参数做三维散点图观察，良性肿瘤和恶性肿瘤几乎集中在同一个区域，良恶性肿瘤的区分效果不好，再选用7个不变矩对目标肿瘤的周边信息进行分析，并用支持向量机进行分类，其中，Hu1和Hu2的判别性能较好，准确率分别为88%和88%，敏感性分别为86%和90%，特异性分别为90%和86%，阳性预测率分别为89.58%和86.54%，阴性预测率分别为86.54%和89.58%。提示超声图像特征参数分析对乳腺肿瘤的鉴别诊断具有辅助作用。

关键词: 超声图像, Level Set, 特征参数, 鉴别诊断, 数字化影像技术

Abstract:

BACKGROUND: Ultrasound diagnosis is non-invasive, reproducible and suitable for identification of soft tissue characteristics, which are widely used in the auxiliary detection of breast cancer. However, due to the lack of quantitative criteria, the diagnosis has shown a higher false positive rate with greater subjectivity and uncertainty. The problem is unsolved for clinicians regarding how to improve the diagnostic accuracy and reduce unnecessary biopsies.
OBJECTIVE: To detect breast tumors using ultrasound image feature parameters.
METHODS: Using level set method, 100 breast tumors were segmented and computed with 10 feature parameters including elongation factor, compactness factor, circularity factor and 7 Hu moment parameters.
RESULTS AND CONCLUSION: The scatter graph showed elongation, compactness and circularity points were not superposed but almost concentrated around the same area without good differential diagnosis, and then 7 Hu values were used to analyze local areas around tumors with support vector machine classification. Hu1 and Hu 2 exhibited better outcomes, the accuracy was 88% and 88%, sensitivity was 86% and 90%, specificity was 90% and 86%, positive predictive value was 89.58% and 86.54%, and the negative predictive value was 86.54% and 89.58%, respectively. It suggested that ultrasound image feature parameters analysis provides guidance to differential diagnosis of breast tumors.

中图分类号: