胸部DR图像分割在纹理检索中的研究及应用
|
摘要
近年来,数字化X线摄影,尤其是直接数字化X线摄影系统的应用,使传统的X线摄影技术进入数字化领域。它与传统的X线摄影相比,具有更高的影像质量,包含更多的影像信息。这种数字化信息经过后处理后,可以获得更多的科研、教育、诊断应用。
本文以数据库检索DR胸部图片为目的,研究了关于X光胸片的几个关键图像处理和分析技术。主要包括肺部分割、肋骨分割和基于纹理的数据库检索。具体内容如下：
对于DR胸片来说,肺部区域的分割是计算机辅助检测胸腔疾病的首要步骤。本文提出两种自动检测肺部边界点的位置的方法。第一种方法首先在图像中计算一系列的参考线来检测肺部区域在整个图像中的大致位置。然后,在对图像进行平滑处理后,在图像水平、垂直方向上,通过求得所在行或列范围内的候选点的灰度值差的极大、极小值来确定边界点的位置,差值为正的代表亮度由低到高,差值为负的代表亮度由高到低。在肺顶区域去除了锁骨的影响。第二种方法通过使用一系列的感兴趣的矩形区域来确定边界点的位置。最后,为了提高边界点的准确性,肺部近似边界的位置可以通过活动轮廓模型的方法被调整,也可以直接使用插值方法将边界点连起,删除肺野的外部区域。使用上述两种方法,对实际采集的DR图片进行测试,能够较好的分割出肺部边界。
在DR数字胸片图像中,肋骨区域对于准确分析肺部区域的纹理存在着较大的影响,在分析肺部区域之前,先将肋骨区域分割出来,然后再对分割后的肺部区域进行纹理分析,有利于DR数字胸片图像的准确分类,也对后继的病理诊断具有非常重要的意义。本文使用了三种分割肋骨的方法,分别是K—聚类均值法,高斯阈值曲面方法和霍夫变换方法,霍夫变换的方法结果好于其他的方法,在使用霍夫变换前需要对图像增强,细化肋骨区域,根据霍夫变换曲线受间断的影响较小,在已知曲线形状的条件下,利用分散的边缘点进行曲线逼近的优点,得到肋骨区域中心线,最后得到肋骨区域。
本文最后提出了基于胸部图像纹理特征的检索系统,使用共生矩阵的纹理特征检索方法,在检索前提出了减少肋骨阴影对最后的肺部区域的纹理检测的影响的算法,通过查全率和查准率评价检索结果。
Recent years, digital radiography, especially the application of the DR (direct digital radiography) system leads the traditional radiography into digital field. Comparing with traditional radiography image, direct digital radioghy image has higher quantity and includes more information. After image manipulation, the digital information can be applied in more clinical diagnosis.
This paper is based on the clinical application of CAD, and study several key technologies of image processing and analysis in X-ray. The main content includs lung segmentation, rib segmentation and texture-based image retrival techniques.
For DR chest images, the precise location of the lungs is the chief mission of a computer-aided diagnosis system to detecte chest disease. This paper proposed two methods to automatically detect the location of the lung boundary points. The first method calculates a set of reference lines to determine the relative position of the lungs in the image. Mediastinal and costal edge points are detected on the image which is the results of the application of a 1-D first derivative Gaussian filter to image rows. In this filtered image, positive values are associated with increasing intensity transitions, while negative values correspond to decreasing variations. Therefore, mediastinal and costal edge points are represented by maxima and minima derivative respectively. The methodology to detect top and bottom boundaries is similar to the one described for lateral border points, except for the use of image columns instead of image rows. To discriminate between lung and clavicle edges, all points locating beyond the exterior part of the costal boundary are eliminated. For improving the detection of lung contours, a method based on the use of active contours models was developed. Vertical and horizontal rectangular regions of interest (ROIs) are studied to identify the preliminary edge. These points are approximations to the lung edges which are adjusted using the active contours models. Interpolation method is used to directly connect the boundary points. The use of the above-mentioned two methods can get better lung border segmentation.
Rib region influences the texture analysis of lung area. We need to extracte the rib region before analyzing the texture feature in lung region. Several segmentation methods are presented to detect the ribs in digital chest radiographs, including K—means clustering, Gaussian curve plane threshold methods and hough transform. The evaluations of their results are present in the end of the paper. The experimental results indicate that hough transform method is more effective than the others to detect the ribs in digital chest radiographs. The hough transform is carried out after enhancing the image and thinning the image. Hough transform curve has less effect on the intermittent and has an advantage of curve approximation, so it can get the centerline of the ribs region.
Finally, analysis of texture feature extracted by gray level co-occurrence matrix is presented. The rib borders are plotted on the original input image. The difference between rib shadow and lung part without rib shadow is subtracted from the rib shadow since the rib shadow has higher. The recall and precision ratio reveals the retrieval result.
本文以数据库检索DR胸部图片为目的,研究了关于X光胸片的几个关键图像处理和分析技术。主要包括肺部分割、肋骨分割和基于纹理的数据库检索。具体内容如下：
对于DR胸片来说,肺部区域的分割是计算机辅助检测胸腔疾病的首要步骤。本文提出两种自动检测肺部边界点的位置的方法。第一种方法首先在图像中计算一系列的参考线来检测肺部区域在整个图像中的大致位置。然后,在对图像进行平滑处理后,在图像水平、垂直方向上,通过求得所在行或列范围内的候选点的灰度值差的极大、极小值来确定边界点的位置,差值为正的代表亮度由低到高,差值为负的代表亮度由高到低。在肺顶区域去除了锁骨的影响。第二种方法通过使用一系列的感兴趣的矩形区域来确定边界点的位置。最后,为了提高边界点的准确性,肺部近似边界的位置可以通过活动轮廓模型的方法被调整,也可以直接使用插值方法将边界点连起,删除肺野的外部区域。使用上述两种方法,对实际采集的DR图片进行测试,能够较好的分割出肺部边界。
在DR数字胸片图像中,肋骨区域对于准确分析肺部区域的纹理存在着较大的影响,在分析肺部区域之前,先将肋骨区域分割出来,然后再对分割后的肺部区域进行纹理分析,有利于DR数字胸片图像的准确分类,也对后继的病理诊断具有非常重要的意义。本文使用了三种分割肋骨的方法,分别是K—聚类均值法,高斯阈值曲面方法和霍夫变换方法,霍夫变换的方法结果好于其他的方法,在使用霍夫变换前需要对图像增强,细化肋骨区域,根据霍夫变换曲线受间断的影响较小,在已知曲线形状的条件下,利用分散的边缘点进行曲线逼近的优点,得到肋骨区域中心线,最后得到肋骨区域。
本文最后提出了基于胸部图像纹理特征的检索系统,使用共生矩阵的纹理特征检索方法,在检索前提出了减少肋骨阴影对最后的肺部区域的纹理检测的影响的算法,通过查全率和查准率评价检索结果。
Recent years, digital radiography, especially the application of the DR (direct digital radiography) system leads the traditional radiography into digital field. Comparing with traditional radiography image, direct digital radioghy image has higher quantity and includes more information. After image manipulation, the digital information can be applied in more clinical diagnosis.
This paper is based on the clinical application of CAD, and study several key technologies of image processing and analysis in X-ray. The main content includs lung segmentation, rib segmentation and texture-based image retrival techniques.
For DR chest images, the precise location of the lungs is the chief mission of a computer-aided diagnosis system to detecte chest disease. This paper proposed two methods to automatically detect the location of the lung boundary points. The first method calculates a set of reference lines to determine the relative position of the lungs in the image. Mediastinal and costal edge points are detected on the image which is the results of the application of a 1-D first derivative Gaussian filter to image rows. In this filtered image, positive values are associated with increasing intensity transitions, while negative values correspond to decreasing variations. Therefore, mediastinal and costal edge points are represented by maxima and minima derivative respectively. The methodology to detect top and bottom boundaries is similar to the one described for lateral border points, except for the use of image columns instead of image rows. To discriminate between lung and clavicle edges, all points locating beyond the exterior part of the costal boundary are eliminated. For improving the detection of lung contours, a method based on the use of active contours models was developed. Vertical and horizontal rectangular regions of interest (ROIs) are studied to identify the preliminary edge. These points are approximations to the lung edges which are adjusted using the active contours models. Interpolation method is used to directly connect the boundary points. The use of the above-mentioned two methods can get better lung border segmentation.
Rib region influences the texture analysis of lung area. We need to extracte the rib region before analyzing the texture feature in lung region. Several segmentation methods are presented to detect the ribs in digital chest radiographs, including K—means clustering, Gaussian curve plane threshold methods and hough transform. The evaluations of their results are present in the end of the paper. The experimental results indicate that hough transform method is more effective than the others to detect the ribs in digital chest radiographs. The hough transform is carried out after enhancing the image and thinning the image. Hough transform curve has less effect on the intermittent and has an advantage of curve approximation, so it can get the centerline of the ribs region.
Finally, analysis of texture feature extracted by gray level co-occurrence matrix is presented. The rib borders are plotted on the original input image. The difference between rib shadow and lung part without rib shadow is subtracted from the rib shadow since the rib shadow has higher. The recall and precision ratio reveals the retrieval result.
引文
1.邹鲁民.DR技术的发展和应用[J],医疗保健器具：医疗器械版,2003,6(2)：45-45,70-73.
2.于子晓,张敏.常规x线图像数字化的CR和DR技术[J],医疗设备信息,2002,2(5)：30-41.
3.陈绿娇,陈义雄.数字化X线摄影技术及其临床应用[J],现代医用影像学,2005,14(3)：142-143.
4.王克扬,贺文,何茜.胸部DR影像后处理对肺结节检出的影响[J],中国医学影像技术,2007,23(11)：1727-1729.
5.李世国.胸部X线平片的计算机辅助诊断(CAD)[J],国外医学临床放射学分册,2004,27(5)：335-337.
6.王俊.我国医学影像技术近十年发展综述[J],影像技术,2004,3(3)：6-11.
7.朱立祥,潘永泉,赵政文.DR技术与临床应用[J],中国医学影像技术,2004,20(6)：152-153.
8. Xu X W, Doi K. Image feature analysis for computer-aided diagnosis:detection of right and left hemidaphragm edges and delineation of lung field in chest radiographs[J], Medical Physics,1996,23(1):1613-1624.
9. Armoto S G, Goger M L, MacMahon H. Computerized delineation and analysis of cousophrenic angles in digital chest radiographs[J], Academic Radiol,1998,5(5):329-335.
10. Pietka E. Lung segmentation in digital chest radiographs[J], Digit Imaging, Imaging, 1994,7(2):79-84.
11. Duryea J, Boone J. A fully automatic algorithm for the segmentation of lung fields in digital chest radiographic images[J], Medical Physics,1995,22(2):183-191.
12. Armoto S G, Giger M L, Ahizawa K et al. Automated Lung segmentation in digital lateral chest radiogrphs[J], Medical Physics,1998,24(8):1507-1520.
13. Carrascal F M, Carreira J M, Souto M et al. Automatic calculation of total lung capacity from automatically traced lung boundaries in postero-anterior and lateral digital chest radiographs[J], Medical Physics,1998,25(7):1118-1131.
14. Ginneken B, Romeny B. Automatic segmentation of lung fields in chest readiographs[J], Medical Physics,2000,27(10):2445-2455.
15. McNitt-Gray M F, Huang H K, Sayre J W. Feature selection in the pattern classification problem of digital cheat radiograph segmentation[J], IEEE Trans. On medical Imaging,1995,14(3):537-547.
16. Vittitoe N F, Vargas-Voracek R, Floyd C E et al. Identification of lung regiond in chest radiographs using Markov Random Field modeling[J], Medical Phsics,1998,2(6):976-985.
17. Tsujii O, Freedman M T, Mun S K. Automated segmentation of anatomic regions in chest radiographs using a adaptive-sized hybrid neural network[J], Medical Physics,1998, 25(6):998-1007.
18. Vittitoe N F, Vargas Voracek R, Floyd C E et al, Markov random field modeling in posteroanterior chest radiograph segmentation[J], Medical Physics,1999,26(8):1670-1677.
19. Mira Park, Laurence S. Wilson, Jesse S. Jin. Automatic Extraction of Lung Boundaries by a Knowledge-Based Method[J], Australian Computer Society,2000,2(2):11-16.
20. Hui Luo, R. Gaborski, R. Acharya. Automatic segmentation of lung regions in chest radiographs:a model guided approch[J], Image Processing,2000. Proceedings.2000 International Conference on,2000,2(3):483-486.
21. Bram van Ginneken and Bart M. ter Haar Romeny. Automatic Segmentation of Lung Fields in Chest Radiographs[J], Proceedings of the Second International Conference on Medical Image Computing and Computer-Assisted Intervention,1999,1679(3):184-191.
22. Jeff Duryea and John M.Boone. A fully automated algorithm for the segmentation of lung fields on digital chest radiographics images[J], Medical Physics,1995,22(2):183-191.
23. Samuel G. Armato Ⅲ, Maryellen L. Giger, and Heber MacMahon. Automated lung segmentation in digitized postero-anterior chest radiographs[J], Acad. Radiol.,1998,5(2):245-255.
24. Francisco M. Carrascal, Jos'e M. Carreira, Miguel Souto, Pablo G. Tahoces, Lorenzo G'omez, and Juan J. Vidal. Automatic calculation of total lung capacity from automatically traced lung boundaries in postero-anteior and lateral digital chest radiographs[J], Medical Physics,1998,25 (7):1118-1131.
25. Ballard D H. Model-directed detection of ribs in chest radiographs[J], Proceeding of 4th International Joint Conference on Pattern Recognition,1978,23(5):907-910.
26. Yue Z J, Goshtasby A, Ackerman L. Automatic detection of rib borders in chest radiographs[J], IEEE Trans. On Medical Imaging,1995,14{3):525-536.
27. Ginneken B, Romeny B. Automatic delineation of ribs in chest radiographs[J], Proceedings of SPIE,2000,3979(3):825-836.
28.姚敏,数字图像处理[M],北京：机械工业出版社,2005,264-291.
29.曹新华,蒋大宗,郑崇勋.一种数字胸片图像肺部区域的自动分割方法[J],生物医学工程学杂志,1998,15(4)：393-396.
30. Zhanjun Yue, Ardeshir Goshtasby, Laurens V. Ackerman. Automatic Detection of Rib Borders in Chest Radiographs [J], IEEE transactions of medical medical imaging,1995, 14(3):525-536.
31. Marco loog, Bram van Ginneken. Segmentation of the Posterior Ribs in Chest Radiographs Using Iterated Contextual Pixel Classification[J], IEEE transaction mecical imaging,2006,25(5):602-611.
32. Ana Maria Mendonca, Jorge Alves da Silval, Aurelio Campilho. Automatic delimitation of lung fields of chest radiographs[J], Image Analysis and Recognition,2004, 2(4):1287-1290.
33. M. Kass, A. Witkin, and D. Terzopoulos. Snakes:Active contour models[J], International journal of computer vision,1988,4(3):321-331.
34. D. J. Williams and M. Shah. A fast algorithm for active contour and curvature estimation[J], CVGIP:Image Understanding,1992,55(1):14-26.
35.王强,张天桥,张灿龙,陈常祥,陈洪波,徐晓蓉.改进型Snake算法在尿沉渣图像处理中的应用[J],Journal of Guangxi Normal University:Natural Science Edition,2006, 24(4):215-218.
36.李丽勤,高焕文,周兴祥Snake模型初始轮廓选取的研究[J],计算机工程与应用,2004,11(2)：43-45.
37. Isaac Iglesias, Pablo G. Tahoces, Miguel Souto3, Anxo Martimez de Alegria, Maria J. Lado, and Juan J. Vidal. Lung Segmentation on Postero-anterior Digital Chest Radiographs Using Active Contours[J], SSPR&SPR,2004,3138(2):538-546.
38.李潇,李平,文玉梅,叶波,郭军.基于改进蛇模型的步态轮廓提取[J],Computer Application,2007,27(6)：1468-1471.
39.唐荣锡.等计算机图形学教程(修订版)[M],北京：科学出版社,2005,155—161.
40.高晶Bezier曲线的算法研究[J],辽宁师专学报,2008,10(2)：25-46
41.徐甜,刘凌霞Bezier曲线的算法描述及程序实现[J],安阳师范学院学报,2006,5(3)：49-52.
42.赵建蕾,王汇源.高帽变换[J],计算机工程,2008,34(6)：210-213.
43.姜珊,王跃存.基于中值滤波和形态学的去噪算法[J],2007,14(4)：106-107.
44.许朝晖,张黎椿,张道兵.CR数字胸片图像的几种肋骨分割方法[J],中国图象图形学报,2004,9(10)：1239-1244.
45.许朝晖,张黎椿,张道兵.基于高斯曲面阈值的CR数字胸片图像分割[J],视屏技术应用与工程,2005,1(2)：92-94.
46.工鑫,庄天戈.x光胸片中肋骨框架自动检测方法的综述[J],中国医学物理学杂志,2005,22(3)：522-525.
47.王鑫,庄天戈.基于解剖结构知识的X光胸片中肺部肋骨边缘检测[J],航天医学与医学工程,2005,18(6)：456-460.
48.吴熙,钱盛友.基于LoG算子的图像边缘增强算法的改进[J],电气电子教学学报,2007,29(4)：25-27.
49.欧珊瑚,王倩丽Visual C++.NET数字图像处理技术与应用[M],北京：清华大学出版社,2004,379-386.
50.崔凤奎,王晓强,张丰收.二值图像细化算法的比较与改进[J],洛阳工学院学报,1997,18(4)：48-52
51.包建军,樊菁.鲁棒的二值图像并行细化算法[J],计算机辅助工程,2006,15(4)：43-46.
52.章毓晋.基于内容的视觉信息检索[M],北京：科学出版社,2003,56-77.
53. Mira Park, Jesse S Jin and Laurence S.Wilson. Detection of Abnormal Texture in Chest X-rays with Reduction of Ribs[J], Conferences in Research and Practice in Information Technology,2004,36(3):71-74.
54.王波,姚宏宇,李弼程.一种有效的基于灰度共生矩阵的图像检索方法[J],武汉大学学报,2006,31(9)：761-764.
55.苑丽红,付丽,杨勇,苗静.灰度共生矩阵提取纹理特征的实验结果分析[J],计算机用,2009,29(4)：1018-1021.
56.丁国祥,吴仁炳,汪祖媛,王煦法.组合颜色、空问和纹理特征的图像检索[J],小型微型计算机系统,2004,25(12)：2251-2253.
2.于子晓,张敏.常规x线图像数字化的CR和DR技术[J],医疗设备信息,2002,2(5)：30-41.
3.陈绿娇,陈义雄.数字化X线摄影技术及其临床应用[J],现代医用影像学,2005,14(3)：142-143.
4.王克扬,贺文,何茜.胸部DR影像后处理对肺结节检出的影响[J],中国医学影像技术,2007,23(11)：1727-1729.
5.李世国.胸部X线平片的计算机辅助诊断(CAD)[J],国外医学临床放射学分册,2004,27(5)：335-337.
6.王俊.我国医学影像技术近十年发展综述[J],影像技术,2004,3(3)：6-11.
7.朱立祥,潘永泉,赵政文.DR技术与临床应用[J],中国医学影像技术,2004,20(6)：152-153.
8. Xu X W, Doi K. Image feature analysis for computer-aided diagnosis:detection of right and left hemidaphragm edges and delineation of lung field in chest radiographs[J], Medical Physics,1996,23(1):1613-1624.
9. Armoto S G, Goger M L, MacMahon H. Computerized delineation and analysis of cousophrenic angles in digital chest radiographs[J], Academic Radiol,1998,5(5):329-335.
10. Pietka E. Lung segmentation in digital chest radiographs[J], Digit Imaging, Imaging, 1994,7(2):79-84.
11. Duryea J, Boone J. A fully automatic algorithm for the segmentation of lung fields in digital chest radiographic images[J], Medical Physics,1995,22(2):183-191.
12. Armoto S G, Giger M L, Ahizawa K et al. Automated Lung segmentation in digital lateral chest radiogrphs[J], Medical Physics,1998,24(8):1507-1520.
13. Carrascal F M, Carreira J M, Souto M et al. Automatic calculation of total lung capacity from automatically traced lung boundaries in postero-anterior and lateral digital chest radiographs[J], Medical Physics,1998,25(7):1118-1131.
14. Ginneken B, Romeny B. Automatic segmentation of lung fields in chest readiographs[J], Medical Physics,2000,27(10):2445-2455.
15. McNitt-Gray M F, Huang H K, Sayre J W. Feature selection in the pattern classification problem of digital cheat radiograph segmentation[J], IEEE Trans. On medical Imaging,1995,14(3):537-547.
16. Vittitoe N F, Vargas-Voracek R, Floyd C E et al. Identification of lung regiond in chest radiographs using Markov Random Field modeling[J], Medical Phsics,1998,2(6):976-985.
17. Tsujii O, Freedman M T, Mun S K. Automated segmentation of anatomic regions in chest radiographs using a adaptive-sized hybrid neural network[J], Medical Physics,1998, 25(6):998-1007.
18. Vittitoe N F, Vargas Voracek R, Floyd C E et al, Markov random field modeling in posteroanterior chest radiograph segmentation[J], Medical Physics,1999,26(8):1670-1677.
19. Mira Park, Laurence S. Wilson, Jesse S. Jin. Automatic Extraction of Lung Boundaries by a Knowledge-Based Method[J], Australian Computer Society,2000,2(2):11-16.
20. Hui Luo, R. Gaborski, R. Acharya. Automatic segmentation of lung regions in chest radiographs:a model guided approch[J], Image Processing,2000. Proceedings.2000 International Conference on,2000,2(3):483-486.
21. Bram van Ginneken and Bart M. ter Haar Romeny. Automatic Segmentation of Lung Fields in Chest Radiographs[J], Proceedings of the Second International Conference on Medical Image Computing and Computer-Assisted Intervention,1999,1679(3):184-191.
22. Jeff Duryea and John M.Boone. A fully automated algorithm for the segmentation of lung fields on digital chest radiographics images[J], Medical Physics,1995,22(2):183-191.
23. Samuel G. Armato Ⅲ, Maryellen L. Giger, and Heber MacMahon. Automated lung segmentation in digitized postero-anterior chest radiographs[J], Acad. Radiol.,1998,5(2):245-255.
24. Francisco M. Carrascal, Jos'e M. Carreira, Miguel Souto, Pablo G. Tahoces, Lorenzo G'omez, and Juan J. Vidal. Automatic calculation of total lung capacity from automatically traced lung boundaries in postero-anteior and lateral digital chest radiographs[J], Medical Physics,1998,25 (7):1118-1131.
25. Ballard D H. Model-directed detection of ribs in chest radiographs[J], Proceeding of 4th International Joint Conference on Pattern Recognition,1978,23(5):907-910.
26. Yue Z J, Goshtasby A, Ackerman L. Automatic detection of rib borders in chest radiographs[J], IEEE Trans. On Medical Imaging,1995,14{3):525-536.
27. Ginneken B, Romeny B. Automatic delineation of ribs in chest radiographs[J], Proceedings of SPIE,2000,3979(3):825-836.
28.姚敏,数字图像处理[M],北京：机械工业出版社,2005,264-291.
29.曹新华,蒋大宗,郑崇勋.一种数字胸片图像肺部区域的自动分割方法[J],生物医学工程学杂志,1998,15(4)：393-396.
30. Zhanjun Yue, Ardeshir Goshtasby, Laurens V. Ackerman. Automatic Detection of Rib Borders in Chest Radiographs [J], IEEE transactions of medical medical imaging,1995, 14(3):525-536.
31. Marco loog, Bram van Ginneken. Segmentation of the Posterior Ribs in Chest Radiographs Using Iterated Contextual Pixel Classification[J], IEEE transaction mecical imaging,2006,25(5):602-611.
32. Ana Maria Mendonca, Jorge Alves da Silval, Aurelio Campilho. Automatic delimitation of lung fields of chest radiographs[J], Image Analysis and Recognition,2004, 2(4):1287-1290.
33. M. Kass, A. Witkin, and D. Terzopoulos. Snakes:Active contour models[J], International journal of computer vision,1988,4(3):321-331.
34. D. J. Williams and M. Shah. A fast algorithm for active contour and curvature estimation[J], CVGIP:Image Understanding,1992,55(1):14-26.
35.王强,张天桥,张灿龙,陈常祥,陈洪波,徐晓蓉.改进型Snake算法在尿沉渣图像处理中的应用[J],Journal of Guangxi Normal University:Natural Science Edition,2006, 24(4):215-218.
36.李丽勤,高焕文,周兴祥Snake模型初始轮廓选取的研究[J],计算机工程与应用,2004,11(2)：43-45.
37. Isaac Iglesias, Pablo G. Tahoces, Miguel Souto3, Anxo Martimez de Alegria, Maria J. Lado, and Juan J. Vidal. Lung Segmentation on Postero-anterior Digital Chest Radiographs Using Active Contours[J], SSPR&SPR,2004,3138(2):538-546.
38.李潇,李平,文玉梅,叶波,郭军.基于改进蛇模型的步态轮廓提取[J],Computer Application,2007,27(6)：1468-1471.
39.唐荣锡.等计算机图形学教程(修订版)[M],北京：科学出版社,2005,155—161.
40.高晶Bezier曲线的算法研究[J],辽宁师专学报,2008,10(2)：25-46
41.徐甜,刘凌霞Bezier曲线的算法描述及程序实现[J],安阳师范学院学报,2006,5(3)：49-52.
42.赵建蕾,王汇源.高帽变换[J],计算机工程,2008,34(6)：210-213.
43.姜珊,王跃存.基于中值滤波和形态学的去噪算法[J],2007,14(4)：106-107.
44.许朝晖,张黎椿,张道兵.CR数字胸片图像的几种肋骨分割方法[J],中国图象图形学报,2004,9(10)：1239-1244.
45.许朝晖,张黎椿,张道兵.基于高斯曲面阈值的CR数字胸片图像分割[J],视屏技术应用与工程,2005,1(2)：92-94.
46.工鑫,庄天戈.x光胸片中肋骨框架自动检测方法的综述[J],中国医学物理学杂志,2005,22(3)：522-525.
47.王鑫,庄天戈.基于解剖结构知识的X光胸片中肺部肋骨边缘检测[J],航天医学与医学工程,2005,18(6)：456-460.
48.吴熙,钱盛友.基于LoG算子的图像边缘增强算法的改进[J],电气电子教学学报,2007,29(4)：25-27.
49.欧珊瑚,王倩丽Visual C++.NET数字图像处理技术与应用[M],北京：清华大学出版社,2004,379-386.
50.崔凤奎,王晓强,张丰收.二值图像细化算法的比较与改进[J],洛阳工学院学报,1997,18(4)：48-52
51.包建军,樊菁.鲁棒的二值图像并行细化算法[J],计算机辅助工程,2006,15(4)：43-46.
52.章毓晋.基于内容的视觉信息检索[M],北京：科学出版社,2003,56-77.
53. Mira Park, Jesse S Jin and Laurence S.Wilson. Detection of Abnormal Texture in Chest X-rays with Reduction of Ribs[J], Conferences in Research and Practice in Information Technology,2004,36(3):71-74.
54.王波,姚宏宇,李弼程.一种有效的基于灰度共生矩阵的图像检索方法[J],武汉大学学报,2006,31(9)：761-764.
55.苑丽红,付丽,杨勇,苗静.灰度共生矩阵提取纹理特征的实验结果分析[J],计算机用,2009,29(4)：1018-1021.
56.丁国祥,吴仁炳,汪祖媛,王煦法.组合颜色、空问和纹理特征的图像检索[J],小型微型计算机系统,2004,25(12)：2251-2253.