基于分形理论的肺部CT图像纹理分割算法研究
|
摘要
近年来,空气污染严重,肺癌的发病率越来越高,临床上通过CT成像技术辅助诊断肺癌,在很大程度上仅凭医生肉眼进行定性和经验性判断,具有一定的局限性,且误诊率较高。本文旨在通过计算机对肺部软组织CT图像的纹理分析研究,进一步挖掘图像信息,为CT诊断肺癌提供一种计算机辅助诊断的客观手段。
本文以分形理论为基础,通过分析多种描述纹理的方法及特点,研究并提出了一种肺部CT图像纹理分割算法,实现了肺部正常组织和异常的分割。该算法以分形维数作为纹理特征参量,利用分形布朗运动模型提取Hurst指数H,再利用H分布的累积直方图进行纹理分割。软件部分是由Matlab实现的,实验结果表明：该算法与现有的基于边缘的Canny分割算法和基于灰度分布的累积直方图分割方法相比,能更好地识别肿瘤区域。
Recently, with air pollution being serious, incidence of lung cancer is now increasing. The diagnosis using CT mainly depend on the experiences of physicians, so there are often wrong diagnosis. The objective of this research is to provide a computer-aided method for the diagnosis of lung cancer by applying texture analysis theory into CT lung images' analysis.
After analyzing kinds of approaches to characterize texture, the thesis studies and presents a suite of system to recognize Cancer Structure in CT lung images based on fractal geometry. The system uses fractal Brownian motion to extraction Hurst parameter, and then applies histogram accumulated by H to segment texture. The software program is finished through Matlab. The experimental result indicates:the approach can complete Cancer Structure recognition better than that based on Canny and histogram accumulated by grey level.
本文以分形理论为基础,通过分析多种描述纹理的方法及特点,研究并提出了一种肺部CT图像纹理分割算法,实现了肺部正常组织和异常的分割。该算法以分形维数作为纹理特征参量,利用分形布朗运动模型提取Hurst指数H,再利用H分布的累积直方图进行纹理分割。软件部分是由Matlab实现的,实验结果表明：该算法与现有的基于边缘的Canny分割算法和基于灰度分布的累积直方图分割方法相比,能更好地识别肿瘤区域。
Recently, with air pollution being serious, incidence of lung cancer is now increasing. The diagnosis using CT mainly depend on the experiences of physicians, so there are often wrong diagnosis. The objective of this research is to provide a computer-aided method for the diagnosis of lung cancer by applying texture analysis theory into CT lung images' analysis.
After analyzing kinds of approaches to characterize texture, the thesis studies and presents a suite of system to recognize Cancer Structure in CT lung images based on fractal geometry. The system uses fractal Brownian motion to extraction Hurst parameter, and then applies histogram accumulated by H to segment texture. The software program is finished through Matlab. The experimental result indicates:the approach can complete Cancer Structure recognition better than that based on Canny and histogram accumulated by grey level.
引文
[1]蒋平.基于胸部CT图像的肺区自动分割.西川大学硕士学位论文.2006.
[2]王家文,李仰军.MATLAB 7.0图形图像处理[M].国防工业出版社,2006：266-288.
[3]蒋勇.基于分形维数的肺部软组织CT图像的纹理特征研究[J].中国医学装备研究与报告.2004.11,1(3)：28-31.
[4]印鉴,郑鹏等.CT图像特征的Fuzzy识别法(二)[J].计算机工程与应用.1999,1(3)：25-27.
[5]伍飞.基于CT影像的肺部肿瘤计算机自动检测方法研究[M].电子科技大学硕士学位论文.2005.
[6]王德杭,汪家旺等.肺结节检测算法研究[J].上海生物医学工程.2005,26(1)：3-7.
[7]罗晓华,谭永明,何中市.肺结节特征提取的分形方法[J].2006,13(3)：57-62.
[8]高园园,吕庆文,郭宏等.一种新的肺结节检测算法[J].2007,43(23)：198-199.
[9]K. K anazawa, N.Niki et al, computer-aided diagnosis for pulmonary nodules based on helical CT images [J]. Computerized medical imaging and graphics, 1998,22(2):157-167.
[10]R. Wiemker, P.Rogalla, A.Zwartkruis et al, computer aided lung nodule detection on high resolution CT data [J]. Proceedings of SPIE, 2002,4684(3):677-688.
[11]Mandelbrot B B. The fractal geometry of nature[M].San Franciaco.
[12]齐东旭.分形及其计算机生成[M].北京：科学出版社,1996.
[13]Harsh Potlapalli, Ren C. Luo. Fractal-Based Classification of Natural Textures[J]. IEEE Transactions On Industrial Electronics,1998, Vol.45.No.1,142-150.
[14]Klaus D.Toennies, Julia A.Schnabel et al. Edge Detection Using the Local Fractal dimension[C]. Seventh Annual IEEE Symposium on Computer-based Medical Systems,1998,34-39.
[15]S.Peleg, J.Naor, R.Hartley, and D.Avnir. Multiple Resolution Texture Analysis and Classification[J]. IEEE Tran. on Pattern Analysis and Machine Intelligence, 6:518-523,1984.
[16]Aura Conci, Claudia Belmiro Proenc. A fractal image analysis system for fabric inspection based on a box-counting method [J]. Computer Networks and ISDN Systems 30,1998,1887-1895.
[17]肖锋.基于BP神经网络的数字图像边缘检测算法的研究[J].西安科技大学学报,2005,25(3)：372-376.
[18]Hou Zhenjie, Ma Shuoshi, Pei Xichun, Pan Xin. Studies on Segmentation and Recognition of Marrow Cells Image[J]. Proceedings of ISCIT 2005,1216-1219.
[19]尹秀丽,张玉杰,张崇.基于四叉树小波分形的医学图像压缩[J].影像技术,2005,第5-6期,34-37.
[20]刘程远,王小铭.基于分形集的多层子块匹配图像压缩算法[J].华南师范大学学报,2005,2(2)：78-82.
[21]刘勃,张在峰,马义德,袁敏.基于分形理论的图像压缩编码技术[J].信息与电子工程,2004,2(4)：246-251.
[22]Kuo-Liang Chung, Chung-Hsiang Hsu. Novel prediction and subblock-based algorithm for fractal image compression. Chaos[J]. Solitons and Fractals 2006,29: 215-222.
[23]Shen Furao,Osamu Hasegawa. A fast no search fractal image coding method[J]. Signal Processing:Image Communication 19 (2004) 393-404.
[24]Antonio Turiel, Jacopo Grazzini, and Hussein Yahia. Multiscale Techniques for the Detection of Precipitation Using Thermal IR Satellite Images[J]. IEEE Geoscience and Remote Sensing Letters,2005,2(4):447-450.
[25]Jing Hu, Wen-Wen Tung, and Jianbo Gao. Detection of Low Observable Targets Within Sea Clutter by Structure Function Based Multifractal Analysis[J]. IEEE Transactions On Antennas and Propagation,2006,54(1),136-143.
[26]K. Uemura, H. Toyama, S. Baba, Y. Kimura, M. Senda, A. Uchiyama. Generation of fractal dimension images and its application to automatic edge detection in brain MRI[J]. Computerized Medical Imaging and Graphics 24 (2000),73-85.
[27]白建明,王之琼.分形理论在X光片图像边缘增强中的应用[J].黑龙江医药科学,2006,29(1)：78-79.
[28]鲁文,韩丰谈,张秀娟,李月卿,张芹英,李平.分形理论在医学图像边缘增强和检测中的应用研究[J].中国医学物理学杂志.1999,16(3)：148-150.
[29]Yong Xia, (David) Dagan Feng, and Rongchun Zhao. Morphology-Based Multifractal Estimation for Texture Segmentation[J]. IEEE Transactions on Image Processing,2006,15(3),614-623.
[30]H.Chen, W.Kinsner. Texture Segmentation using Multifractal Measures[J]. IEEE on Power and Computing Proceedings,1997,222-227.
[31]R.Chandrasekhar, Y.Attikiouzel. New range-based neighbourhood operator for extracting edge and texture information from mammograms for subsequent image segmentation and analysis[J].2000, IEE on proc-sci.Meas.Technol, vol. 147, No.6,408-413.
[32]Jacopo Grazzini, Antonio Turiel, Hussein Yahia, Isabelle Herlin. A multifractal approach for extracting relevant textural areas in satellite meteorological images[J].Environmental Modelling & Software xx (2006) 1-12.
[33]Du Gan, YEO Tat-soon. A Multifractal Approach for Auto-segmentation of SAR Images[J].IEEE2001,2301-2303.
[34]李会方,徐瑞萍,庞文俊.基于相对多重分形谱的感兴趣区域图像压缩[J].计算机应用,2005,25(12)：2840-2842.
[35]蒋爱平,王祁.分形多重相关方差X线颅颌影像边缘检测[J].哈尔滨工业大学学报,2006,38(6)：902-905.
[36]王东生,曹磊.混沌.分形及其应用[M].中国科技大学出版社,1995：35-70.
[37]H.Tamura, S.Mori, T.Yamawaki. Textural features corresponding to visual perception. IEEE Trans. on Systems, Man., and Cybernetics,1978, SMC-8(6):460-473.
[38]贾永红.数字图像处理[M].武汉大学出版社,2003：178-196.
[39]李丙春.基于共生矩阵的图像纹理特征提取及应用[J].喀什师范学院学报.2006,27(6)：35-37.
[40]陈真诚,周兆英,赵于前,蒋大宗.人体肝脏组织CT图像的分维特征研究[J].航天医学与医学工程学报.2005,6,1(3)：206-21.
[41]Tang YuanY, Tao Yu, Lam Ernest C M.New method for feature extraction based on fractal behavior [J].Pattern Recognition.2002,55(5):1071-1081.
[42]张济忠.分形[M].清华大学出版社,1995：2-40.
[43]孙霞,吴自勤,黄畇.分形原理及其应用[M].合肥：中国科学技术大学出版社.2003：23-24.
[44]申小娜.分形编码及其在数字水印中的应用.重庆大学硕士学位论文.2008.
[45]王华.基于分形理论的路面裂缝检测技术的研究[D].哈尔滨：哈尔滨工业大学,2004.
[46]王耀南,王绍源,毛建旭.基于分形维数的图像纹理分析[J].湖南大学学报.2006,33(5)：67-71.
[47]叶志前.肝纤维化B超图像的纹理分析研究[D].浙江：浙江大学,2006.
[48]田晓东,刘忠.基于分形理论的声纳图像人造目标检测算法[J].计算机工程与应用.2006.36：195-197.
[49]张红蕾,宋建社,张宪伟.一种基于多重分形的SAR图像边缘检测方法[J].电光与控制.2007,14(5)：86-88.
[50]杨悦华.基于多重分形的X线头影片边缘检测研究[D].哈尔滨：黑龙江大学硕士学位论文.2007.
[51]龚声蓉,刘纯平,王强.数字图像处理与分析[M].北京：清华大学出版社.2006： 272-279.
[52]李会方.多重分形理论及其在图像处理中的应用[D].西安：西北工业大学博士学位论文.2004.
[53]李锰.地貌与地震形变场分形与多重分形特征研究[D].北京：中国地震局地球物理研究所博士学位论文.2002.
[54]符维娟.基因序列CGR图形的多重分形分析及应用[D].上海：复旦大学博士学位论文.2005.
[55]肖亮.基于变分PDE和多重分形的图像建模理论、算法与应用[D].南京：南京理工大学博士学位论文.2003.
[56]马爽.基于多重分形理论的金融市场风险测度研究[D].哈尔滨：黑龙江大学硕士学位论文.2009.
[57]戚大伟.基于分形理论的原木缺陷X射线图像分析与处理[D].哈尔滨：东北大学博士学位论文.2003.
[58]贾永红.数字图像处理[M].武汉：武汉大学出版社,2004：150-152.
[59]蒋爱平,王祁.分数布朗运动在X线图像边缘提取中的应用[J].控制工程,2004,12(5)：476-479.
[60]龚声蓉,刘纯平,王强.数字图像处理与分析[M].北京：清华大学出版社,2004：169-177.
[2]王家文,李仰军.MATLAB 7.0图形图像处理[M].国防工业出版社,2006：266-288.
[3]蒋勇.基于分形维数的肺部软组织CT图像的纹理特征研究[J].中国医学装备研究与报告.2004.11,1(3)：28-31.
[4]印鉴,郑鹏等.CT图像特征的Fuzzy识别法(二)[J].计算机工程与应用.1999,1(3)：25-27.
[5]伍飞.基于CT影像的肺部肿瘤计算机自动检测方法研究[M].电子科技大学硕士学位论文.2005.
[6]王德杭,汪家旺等.肺结节检测算法研究[J].上海生物医学工程.2005,26(1)：3-7.
[7]罗晓华,谭永明,何中市.肺结节特征提取的分形方法[J].2006,13(3)：57-62.
[8]高园园,吕庆文,郭宏等.一种新的肺结节检测算法[J].2007,43(23)：198-199.
[9]K. K anazawa, N.Niki et al, computer-aided diagnosis for pulmonary nodules based on helical CT images [J]. Computerized medical imaging and graphics, 1998,22(2):157-167.
[10]R. Wiemker, P.Rogalla, A.Zwartkruis et al, computer aided lung nodule detection on high resolution CT data [J]. Proceedings of SPIE, 2002,4684(3):677-688.
[11]Mandelbrot B B. The fractal geometry of nature[M].San Franciaco.
[12]齐东旭.分形及其计算机生成[M].北京：科学出版社,1996.
[13]Harsh Potlapalli, Ren C. Luo. Fractal-Based Classification of Natural Textures[J]. IEEE Transactions On Industrial Electronics,1998, Vol.45.No.1,142-150.
[14]Klaus D.Toennies, Julia A.Schnabel et al. Edge Detection Using the Local Fractal dimension[C]. Seventh Annual IEEE Symposium on Computer-based Medical Systems,1998,34-39.
[15]S.Peleg, J.Naor, R.Hartley, and D.Avnir. Multiple Resolution Texture Analysis and Classification[J]. IEEE Tran. on Pattern Analysis and Machine Intelligence, 6:518-523,1984.
[16]Aura Conci, Claudia Belmiro Proenc. A fractal image analysis system for fabric inspection based on a box-counting method [J]. Computer Networks and ISDN Systems 30,1998,1887-1895.
[17]肖锋.基于BP神经网络的数字图像边缘检测算法的研究[J].西安科技大学学报,2005,25(3)：372-376.
[18]Hou Zhenjie, Ma Shuoshi, Pei Xichun, Pan Xin. Studies on Segmentation and Recognition of Marrow Cells Image[J]. Proceedings of ISCIT 2005,1216-1219.
[19]尹秀丽,张玉杰,张崇.基于四叉树小波分形的医学图像压缩[J].影像技术,2005,第5-6期,34-37.
[20]刘程远,王小铭.基于分形集的多层子块匹配图像压缩算法[J].华南师范大学学报,2005,2(2)：78-82.
[21]刘勃,张在峰,马义德,袁敏.基于分形理论的图像压缩编码技术[J].信息与电子工程,2004,2(4)：246-251.
[22]Kuo-Liang Chung, Chung-Hsiang Hsu. Novel prediction and subblock-based algorithm for fractal image compression. Chaos[J]. Solitons and Fractals 2006,29: 215-222.
[23]Shen Furao,Osamu Hasegawa. A fast no search fractal image coding method[J]. Signal Processing:Image Communication 19 (2004) 393-404.
[24]Antonio Turiel, Jacopo Grazzini, and Hussein Yahia. Multiscale Techniques for the Detection of Precipitation Using Thermal IR Satellite Images[J]. IEEE Geoscience and Remote Sensing Letters,2005,2(4):447-450.
[25]Jing Hu, Wen-Wen Tung, and Jianbo Gao. Detection of Low Observable Targets Within Sea Clutter by Structure Function Based Multifractal Analysis[J]. IEEE Transactions On Antennas and Propagation,2006,54(1),136-143.
[26]K. Uemura, H. Toyama, S. Baba, Y. Kimura, M. Senda, A. Uchiyama. Generation of fractal dimension images and its application to automatic edge detection in brain MRI[J]. Computerized Medical Imaging and Graphics 24 (2000),73-85.
[27]白建明,王之琼.分形理论在X光片图像边缘增强中的应用[J].黑龙江医药科学,2006,29(1)：78-79.
[28]鲁文,韩丰谈,张秀娟,李月卿,张芹英,李平.分形理论在医学图像边缘增强和检测中的应用研究[J].中国医学物理学杂志.1999,16(3)：148-150.
[29]Yong Xia, (David) Dagan Feng, and Rongchun Zhao. Morphology-Based Multifractal Estimation for Texture Segmentation[J]. IEEE Transactions on Image Processing,2006,15(3),614-623.
[30]H.Chen, W.Kinsner. Texture Segmentation using Multifractal Measures[J]. IEEE on Power and Computing Proceedings,1997,222-227.
[31]R.Chandrasekhar, Y.Attikiouzel. New range-based neighbourhood operator for extracting edge and texture information from mammograms for subsequent image segmentation and analysis[J].2000, IEE on proc-sci.Meas.Technol, vol. 147, No.6,408-413.
[32]Jacopo Grazzini, Antonio Turiel, Hussein Yahia, Isabelle Herlin. A multifractal approach for extracting relevant textural areas in satellite meteorological images[J].Environmental Modelling & Software xx (2006) 1-12.
[33]Du Gan, YEO Tat-soon. A Multifractal Approach for Auto-segmentation of SAR Images[J].IEEE2001,2301-2303.
[34]李会方,徐瑞萍,庞文俊.基于相对多重分形谱的感兴趣区域图像压缩[J].计算机应用,2005,25(12)：2840-2842.
[35]蒋爱平,王祁.分形多重相关方差X线颅颌影像边缘检测[J].哈尔滨工业大学学报,2006,38(6)：902-905.
[36]王东生,曹磊.混沌.分形及其应用[M].中国科技大学出版社,1995：35-70.
[37]H.Tamura, S.Mori, T.Yamawaki. Textural features corresponding to visual perception. IEEE Trans. on Systems, Man., and Cybernetics,1978, SMC-8(6):460-473.
[38]贾永红.数字图像处理[M].武汉大学出版社,2003：178-196.
[39]李丙春.基于共生矩阵的图像纹理特征提取及应用[J].喀什师范学院学报.2006,27(6)：35-37.
[40]陈真诚,周兆英,赵于前,蒋大宗.人体肝脏组织CT图像的分维特征研究[J].航天医学与医学工程学报.2005,6,1(3)：206-21.
[41]Tang YuanY, Tao Yu, Lam Ernest C M.New method for feature extraction based on fractal behavior [J].Pattern Recognition.2002,55(5):1071-1081.
[42]张济忠.分形[M].清华大学出版社,1995：2-40.
[43]孙霞,吴自勤,黄畇.分形原理及其应用[M].合肥：中国科学技术大学出版社.2003：23-24.
[44]申小娜.分形编码及其在数字水印中的应用.重庆大学硕士学位论文.2008.
[45]王华.基于分形理论的路面裂缝检测技术的研究[D].哈尔滨：哈尔滨工业大学,2004.
[46]王耀南,王绍源,毛建旭.基于分形维数的图像纹理分析[J].湖南大学学报.2006,33(5)：67-71.
[47]叶志前.肝纤维化B超图像的纹理分析研究[D].浙江：浙江大学,2006.
[48]田晓东,刘忠.基于分形理论的声纳图像人造目标检测算法[J].计算机工程与应用.2006.36：195-197.
[49]张红蕾,宋建社,张宪伟.一种基于多重分形的SAR图像边缘检测方法[J].电光与控制.2007,14(5)：86-88.
[50]杨悦华.基于多重分形的X线头影片边缘检测研究[D].哈尔滨：黑龙江大学硕士学位论文.2007.
[51]龚声蓉,刘纯平,王强.数字图像处理与分析[M].北京：清华大学出版社.2006： 272-279.
[52]李会方.多重分形理论及其在图像处理中的应用[D].西安：西北工业大学博士学位论文.2004.
[53]李锰.地貌与地震形变场分形与多重分形特征研究[D].北京：中国地震局地球物理研究所博士学位论文.2002.
[54]符维娟.基因序列CGR图形的多重分形分析及应用[D].上海：复旦大学博士学位论文.2005.
[55]肖亮.基于变分PDE和多重分形的图像建模理论、算法与应用[D].南京：南京理工大学博士学位论文.2003.
[56]马爽.基于多重分形理论的金融市场风险测度研究[D].哈尔滨：黑龙江大学硕士学位论文.2009.
[57]戚大伟.基于分形理论的原木缺陷X射线图像分析与处理[D].哈尔滨：东北大学博士学位论文.2003.
[58]贾永红.数字图像处理[M].武汉：武汉大学出版社,2004：150-152.
[59]蒋爱平,王祁.分数布朗运动在X线图像边缘提取中的应用[J].控制工程,2004,12(5)：476-479.
[60]龚声蓉,刘纯平,王强.数字图像处理与分析[M].北京：清华大学出版社,2004：169-177.