基于双边滤波-距离正则化水平集演化算法的甲状腺超声图像分割  

Ultrasound image segmentation of thyroid gland based on bilateral filters-distance regularized level set evolution algorithm

作　　者：冉冬梅 严加勇 崔崤峣[3] 于振坤[4] RAN Dongmei;YAN Jiayong;CUI Yaoyao;YU Zhenkun(University of Shanghai for Science and Technology,Shanghai 200093,China;School of Medical Instrument,Shanghai University of Medical &Health Science,Shanghai 201318;Institute of Biomedical Engineering and Technology,Chinese Academy of Sciences,Suzhou 215163,China;Tongren Hospital of Nanjing,Nanjing 211102,China)

机构地区：[1]上海理工大学医疗器械与食品学院,上海200093 [2]上海健康医学院医疗器械学院,上海201318 [3]中科院苏州生物医学工程技术研究所,苏州215163 [4]南京同仁医院,南京211102

出　　处：《生物医学工程研究》2019年第2期170-175,共6页Journal Of Biomedical Engineering Research

基　　金：江苏省省级重点研发专项资金资助项目(BE2017601);上海市浦东新区科技发展基金民生科研专项医疗卫生项目(PKJ2017-Y41)

摘　　要：超声图像有斑点噪声,且对比度低、边界模糊,所以甲状腺超声图像分割较为困难。针对此问题,本研究提出一种结合双边滤波(bilateral filters,BF)和改进边缘指示函数的距离正则化水平集演化(distance regularized level set evolution,DRLSE)模型的分割算法。先对甲状腺超声图像进行双边滤波,然后采用改进的DRLSE模型对甲状腺进行分割。通过与采用另外两种边缘指示函数的DRLSE模型对比,本研究提出的BF-DRLSE模型能减少斑点噪声对分割过程的影响,并在明显减少曲线演化运行时间和迭代次数的情况下有效分割甲状腺。Diagnosis of thyroid disease often requires segmentation of the thyroid gland from the ultrasound image.Because of speckle noise,low contrast,blurred boundary,it is difficult to segment the thyroid ultrasound image.To solve the problem,a segmentation algorithm that combines Bilateral Filters(BF)and improved Distance Regularized Level Set Evolution(DRLSE)model with improved edge indication function was proposed.The thyroid ultrasound image was bilaterally filtered first,and then the thyroid was segmented using the improved DRLSE model.Comparing with DRLSE model experiments using two other kinds of edge indicator functions,the BF-DRLSE model proposed in this paper can reduce the effect of speckle noise on the segmentation process and effectively segment the thyroid under the condition that the curve evolution running time and iteration times are obviously reduced.

关 键 词：甲状腺超声图像 图像分割 距离正则化水平集演化模型 双边滤波模型 边缘指示函数 

分 类 号：R318[医药卫生—生物医学工程]