数据采集与处理2016，Vol.31Issue(5)：1004-1009,6.DOI:10.16337/j.1004-9037.2016.05.018
基于多尺度融合的甲状腺结节图像特征提取
Image Feature Extraction of Thyroid Nodule Based on Multi-scale Fusion
摘要
Abstract
Thyroid nodule is a kind of frequently-occurring disease.Ultrasound technology is the preferred examination method for the disease.Extracting the texture feature distinguishing the benign and malig-nancy in the ultrasound images and discriminate them has a wide prospect of clinical application.Dual-tree complex wavelet transform (DT-CWT)and Gabor wavelet are the important approaches to texture feature extraction.Here,we present an approach of thyroid nodules recognition by fusing multi-scale DT-CWT and Gabor wavelet features.Firstly,we use Gaussian pyramid to decompose the thyroid ultra-sound image into multi-scale space.Followed by extracting DT-CWT and Gabor multi-scale features,the feature fusion is performed.Support vector machine (SVM)is applied to classify so as to verify the effec-tiveness of the proposed method.Experimental results show that the proposed method can achieve a high recognition rate.关键词
双数复小波变换/Gabor变换/高斯金字塔/特征融合Key words
dual-tree complex wavelet transform/Gabor transform/Gaussian pyramid/feature fusion分类
信息技术与安全科学引用本文复制引用
王昊,彭博,陈琴,杨燕..基于多尺度融合的甲状腺结节图像特征提取[J].数据采集与处理,2016,31(5):1004-1009,6.基金项目
国家自然科学基金(61202190,61572407)资助项目 （61202190,61572407）
四川省科技支撑计划(2014SZ0207)资助项目。 （2014SZ0207）
