用户名: 密码: 验证码:
前列腺超声图像的分割研究
详细信息    本馆镜像全文|  推荐本文 |  |   获取CNKI官网全文
摘要
随着医学影像技术的进步和超声医学的发展,前列腺疾病的检出率越来越高,引起了全社会范围的广泛关注。但由于同CT、MRI等图像相比超声图像的质量极差,存在大量的噪声,给医生正确判断前列腺的结构和病变与否带来了极大的困难。为了使医生可以对人体的解剖结构以及病变进行更有效的观察和诊断,提高前列腺疾病诊断的正确率,利用计算机图像技术准确分割前列腺体就成为一个紧迫的课题。
     本论文选取前列腺超声图像作为研究对象,首先系统地介绍了超声设备和B超的成像原理,接下来研究了前列腺的解剖学结构和超声图像的病理学和图像学特征,并对目前图像处理研究的现状进行了剖析,从中得出了超声图像分割的特殊性。
     在图像的预处理的过程中,论文首先改进了超声图像的Speckle噪声模型,其次在借鉴传统的方法的基础上,提出并实现了自适应图像增强和自适应滤波处理方法,较好地抑制了噪声。
     对于图像的特征提取和图像分割,论文在对传统的边缘提取和轮廓跟踪算法进行研究之后,提出了γ校正和Sobel算子相结合的边缘提取算法。结合超声图像的特点,改进了并实现了自适应阈值分割和最大方差比阈值分割算法。提出了全局比较探测、面积测定及空间优先、竞争机会均等三个有效的准则,利用灰度、纹理多特征矢量改进了传统的区域增长算法,并对纹理分析,神经网络分割和SNAKE活动轮廓分割进行了有益的探索。
     在以上的基础之上,论文设计实现了分别针对256色和24位真彩色的超声图像处理系统,并进行了一系列的图像分割实验。实验结果表明,本文所设计的自适应预处理算法能够有效地抑制噪声,改善了图像的质量;本文提
    
    出的图像分割方法能够较准确地对前列腺超声图像进行特征提取和分割,基
    本达到预期的效果。
With the progress of medical image processing technology and the development of ultrasonic medical, more and more prostate diseases were found and this arouse extensive attention. Comparing Ultrasonic Image (US) with CT and MRI, we can find the quality of the Ultrasonic Image is very bad for plenty of noise. In order to help doctor to check the tissue of prostate and diagnose illness exactly, it is increasingly demand that how to realize the automatic segmentation from ultrasonic image.
    The research object in this dissertation is prostate ultrasonic images. Firstly, the principle of ultrasound devices and the B ultrasonic imaging have been introduced, and then the anatomic structure of prostate and its pathology have been studied. The particularities of prostate ultrasonic image have been researched in detail as well.
    In the pretreatment of these images, the Speckle noise model has been improved in this dissertation. On the basis of traditional methods of neighborhood averaging and low-pass filtering, the methods of Adaptive Histogram Enhancement and the improved adaptive Weighted Median Filter have been presented, and the noise has been reduced greatly.
    After the study of the traditional algorithms of feature extraction and boundary tracking, the edge detection method based on combination of γ-correction and Sobel edge operator has been realized. After the discussion of several kinds of optimum threshold segmentation methods, a multi-feature vector space and three new criteria (Global Comparison Detection, Geography Priority Privilege, Equal Opportunity for Competence) are developed for region growing control, a new region growing method is brought forward. At last the region splitting and merging, region clustering, neural networks, SNAKE active contour model et al have been discussed.
    
    
    
    Both the 256-color ultrasonic image processing system and 24-bits-color ultrasonic image processing system has been designed based on the methods above. The results of computer simulation show that the methods presented in this dissertation have the good effects on the segmentation of ultrasonic image.
引文
[1] 叶敏.“前列腺疾病新进展”专题研讨会简介.中华泌尿外科杂志,2002,23(8):506-506页
    [2] 刘积仁,张继武.数字化医学影像设备最新进展及发展趋势(上).医疗卫生装备,2002,23(4):10-14页
    [3] 曹辉,苟量等.超声、磁共振和核医学成像的发展现状和趋势.成都理工学院学报,2002,29(2):232-236页
    [4] 林瑶,阳捷.医学图像分割方法综述.模式识别与人工智能,2002,15(2):192-204页
    [5] 盛林,符勇.基于Internet的超声影像工作站的建立.北华大学学报:自然科学版,2001,2(2):179-181页
    [6] 高永慧.超声波与疾病诊断.现代物理知识,1999,11(4):27-29页
    [7] 杨跃模.B型超声波诊断仪的原理,维护和检修.临床超声医学杂志,1994,5(1):30-33页
    [8] 封海兵.医用超声诊断仪的原理与检定技术.计量与测试技术,2002,29(4):44-45页
    [9] 林仲茂.20世纪功率超声在国内外的发展.声学技术,2000,19(2):101-104页,F004
    [10] 王新房,张青萍.中华影像医学:超声诊断学卷.北京:人民卫生出版社.2002:576-578页
    [11] 朱英,何还珠.B型实时显象经直肠检测前列腺的探讨:附110例分析,上海医学,1994,17(12):733-734页
    [12] 张玉英,陈文奎.经直肠超声显象对前列腺检查的探讨.青海医药杂志,1995,25(2):22-23页
    [13] 连雪,田慧中.前列腺增生声象图的分析与分型.中国医学影像技术,1998,14(9):693-694页
    [14] 瞿连喜,王翔等.经直肠B超诊断前列腺癌.中国癌症杂志,
    
    2001,11(2):153-154页
    [15] 王修信,韩逸萍等.医学数字图像增强方法的研究.广西师范大学学报:自然科学版,2002,20(3):23-26页
    [16] 周孝宽.实用微机图像处理[M].北京:北京航空航天大学出版社.1994
    [17] Pizer S. Adaptive histogram equalization and its variations [J]. CVCIP, 1987,39(3):355-368P
    [18] Lee Jongsan. Digital image enhancement and noise filtering by use of local statistics. PAMI-I, 1980, (2):165-168P
    [19] Loupas T, An Adaptive Weighted Median Filter for Speckle Suppression in Medical ultrasonic Image. IEEE Trans on Circuits Syst, 1989, CAS-36(1):129-135P
    [20] 张海澜,王蜀楚,应崇福.B超图像的斑纹噪声和人体软组织的随机特性.应用声学,1990:35-37页
    [21] Dutt Vinayak. Adaptive Speckle Reduction Filter for Log-Compressed B-Scan Images. IEEE Trans. Med. Image, 1996,15(6):802-813P
    [22] Vishvjit S. Nalwa and Thomas O. Binfond. On Detecting Edges. IEEE Trans on Pattern analysis and Machine intelligence, 1986, PAM1-8 (6)
    [23] Lee J S. Digital Image Enhancement and noise (?)iltering by use of local statistics. IEEE Trans. 1980, PAMI-2:165P
    [24] Loupas T. An Adaptive Weighted Median Filter for Speckle Suppression in Medical ultrasonic Image. IEEE Trans on Circuits Syst. 1989, CAS-36(1):129-135P
    [25] Munakata M, Ukita HI, Deiet al. Sepctral and waveform characteristic of line and coarse crackles. Thorax, 1991:46-65P
    [26] 王新成编著.高级图像处理技术.北京:中国科学技术出版社.2001:176-181页
    [27] A. MURAT TEKALP. Digital Video Processing. PRENTICE HALL PRESS. 1998:453P
    
    
    [28] 鲁文等.分性理论在医学图像边缘增强和检测中的应用研究.中国医学物理学杂志,1997,16(3):148-150页
    [29] 何斌.Visual C++数字图像处理.北京:人民邮电出版社.2002:464页
    [30] 王新成编著.高级图像处理技术.北京:中国科学技术出版社.2001:178页
    [31] 姚炜.计算机纹理分析在超声诊断中的应用.第二军医大学硕士学位论文.
    [32] 李军,丁明跃.一种B超图像的边缘提取算法.计算机与数字工程,2000,28(2):13页
    [33] 章毓晋.图像工程(附册)——教学参考及习题解答.北京:清华大学出版社.2002:71-72页
    [34] 王磊等.基于Canny理论的边缘提取改善方法.中国图像图形学报,1996,1(3):191-193页
    [35] 何斌.Visual C++数字图像处理.北京:人民邮电出版社.2002:435-436页
    [36] 顾顺德,聂生东等.基于K-最近邻规则的磁共振颅脑图像分割算法的应用研究.上海医科大学学报,2000,27(2):108-109页
    [37] 赵荣椿,迟耀斌,朱重光.图象分割技术进展.中国体视学与图像分析,1998,3(2):121-124页
    [38] D. Yanowitz, A.M. Bruckstein. A new method for image segmentation. Compu Vision Graphics: Image Process. 1989, 46:82-95P
    [39] Kittler J, Illingworth J. Minimum Error Thresholding. Pattern Recognition. 1986,19:41-47P
    [40] Cho S, Haralick R, Yi S. Improvement of Kittler and Illing Worth's Minimum Error Thresholding. Pattern Recognition. 1989,22:609-617P
    [41] N. Otau. A Threshold Selection Method from Gray-Level Histograms. IEEE Trans. 1979, SMC-9(1):62-66P
    [42] W. Entenmann. Optimierungsverfahren. Huthig, Heidelberg. 1976
    
    
    [43] (日)谷口庆治编,朱虹,廖学成等译.数字图像处理——基础篇.北京:科学出版社.2001:105页
    [44] 弗里得里希 M.华尔著,王宗海,张存帧,吕英等译.数字图像信号处理“原理、方法与实例”.上海:上海远东出版社.1993.7
    [45] 徐建华.图像处理与分析.北京:科学出版社.1994
    [46] Kaleen Siddiqi, Yves Berube Lauziere, Allen Tannenbaum. Area and Length Minimizing Flows for Shape Segmentation. IEEE Transactions on Image Processing, 1998, 7(3):433-435P
    [47] (日)谷口庆治编,朱虹,廖学成等译.数字图像处理——基础篇.北京:科学出版社.2001:118页
    [48] L. Abele. Statistische und strukturelle Texturanalyse mit Anwendungen in der Bildsegmentierung. Nachrichtentechnische Berichte Bd. 6. Lehrstuhlfur Nachrichtentechnik, TU Munchen. 1982
    [49] 王耀南,李树涛,毛建旭编著.计算机图像处理与识别技术.北京:高等教育出版社.2001.6
    [50] Tekalp A M. Digital Video Processing. Prentice-Hall. 1995
    [51] Murphy RI.H Hofford SK. Knowler W.C. Visual lungsound characterization by time-expanded waveform analysis. New Eng. J.Med. 1978:296-968P
    [52] 杜干,孙肖子.医学图像分割的神经网络方法.西安电子科技大学学报,1998,25(5):603-606页
    [53] 汪天富,郑昌琼等.用神经网络进行超声医学图像分割.生物医学工程学杂志,1998,15(4):397-399页
    [54] 沈定刚,戚飞虎.基于神经网络的自适应图像分割.上海交通大学学报,1994,28:39-41页
    [55] Laurent D. Cohen. On Active Contour Models and Balloons. CVGIP:Image Understanding, 1991, 53(2):211-218P
    [56] 夏利民,谷士文.基于形变模型的图像分割和非刚性目标的跟踪.模式识别与人工智能,2000,13(1):64-66页

© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号

地址:北京市海淀区学院路29号 邮编:100083

电话:办公室:(+86 10)66554848;文献借阅、咨询服务、科技查新:66554700