Breast tumor classification based on serial grayscale ultrasound images.
- Author:
Zhang HA
1
;
Chuan-Fu LI
;
Jin-Ping WANG
;
Kang-Yuan ZHOU
;
Zhen-Sen YANG
Author Information
1. Department of Electronic Engineering and Information Science, USTC, Hefei. hazhang@mail.ustc.edu.cn
- Publication Type:Journal Article
- MeSH:
Algorithms;
Breast Neoplasms;
diagnostic imaging;
Elasticity Imaging Techniques;
Female;
Humans;
Sensitivity and Specificity;
Ultrasonography, Mammary;
methods
- From:Chinese Journal of Medical Instrumentation
2008;32(3):186-189
- CountryChina
- Language:Chinese
-
Abstract:
This paper proposes an algorithm of evaluating the compression depth, and then to extract four normalized mammary elasticity characteristic parameters with respect to the compression depth. The classification experiments show that these elasticity parameters have a good capability in determining whether the tumor is benign or malignant, and if combined with morphological parameters, the accuracy, sensitivity and specificity can be improved and increased to 95.19%, 98.82% and 92.16%, respectively.
