摘要
计算机辅助诊断是最近十几年发展起来的生物医学工程的一个重要分支。随着数字图像技术的发展,计算机辅助消化道内窥镜图像诊断成为可能。其充分利用合适的数字图像处理技术来分析处理医学图像信息,对组织结构信息进行定性和定量研究,从而辅助医生进行诊断治疗。本课题的研究目的是提出了一种新的计算机辅助消化道内窥镜图像诊断方法,用于消化道内窥镜图像的自动分析。
本文使用了一种基于多级同质的彩色消化道内窥镜图像分割方法。该方法首先计算出关于强度和同质的二维直方图,然后在二维直方图上利用峰值寻找算法将图像分割成若干个区域,接着利用色调域直方图分析法将前面所得的每个区域进行再分割,最后合并具有相同CIE(Lab)颜色度量的区域。
本文对彩色消化道内窥镜图像提取了基于直方图的颜色信息和基于纹理谱的纹理信息。综合颜色和纹理的图像特征将具有更强的鲁棒性。
Bayesian分类方法是一种常用的统计模式识别方法。本文将其首次应用于消化道内窥镜图像的诊断,并获得了较好的实验结果。
针对息肉的检测,本文提出了一种新的基于椭圆匹配的息肉检测算法。该算法首先对消化道内窥镜图像进行彩色边缘检测并最终处理成二值边界。接着用一种基于最小二乘法的随机化椭圆检测方法在二值边界图像中进行椭圆检测。实验取得了很好的效果,并弥补了Bayesian分类方法不能识别息肉的缺点。
实验结果初步显示了论文所提出的方法在消化道内窥镜图像诊断上的可行性,有望为消化道疾病的自动诊断提供一种新的分析方法。
Computer-aided diagnosis is developed in recent decades, which is an important branch of bio-medical engineering. With the development of digital image technology, computer-aided diagnosis of digestive endoscopic image becomes possible. It makes full use of appropriate digital image processing techniques to analyse medical image and gets qualitative and quantitative analysis of the tissue, which can facilitate the diagnosis and treatment of doctors. The purpose of this paper is to propose a new method of computer-aided diagnosis of digestive endoscopic image for the automatic analysis of digestive endoscopic image.
This paper uses a hierarchical approach to color digestive endoscopic image segmentation using homogeneity. In the first stage, the regions are segmented using a peak-finding algorithm on a 2-D histogram of homogeneity and intensity values. In the second stage, histogram analysis of the color feature hue is performed to subdivide the segmented regions obtained from the first stage. The subdivisions of different segmented regions having similar CIE(L*a*b) color measure are merged.
In this paper, both color-based and texture-based quantitative features of color digestive endoscopic image are extracted. Specifically, we extract texture-based features from texture spectra and color-based features from color histogram. Integrated color and texture features of the image will have a stronger robustness.
Bayesian classifier is one of the most commonly used method of statistical pattern recognition. This paper uses it to the diagnosis of digestive endoscopy image for the first time and obtains good results.
For polyp detection, this paper proposes a novel scheme based on ellipse fitting for polyp detection in digestive endoscopic image. Firstly, a color edge detection algorithm is used to get the binary image. Then, we adopt a randomized ellipse detection algorithm based on the least square approach to detect polyps in the binary image. Experiment has achieved very good results and the algorithm can overcome the shortcoming of Bayesian classifier's missing detection of polyps.
Experiment results suggest the feasibility of the proposed method for the diagnosis of digestive endoscopic image, which provides a new analysis method for the automatic diagnosis of digestive endoscopic image.
引文
[1]刘厚钰,姚礼庆.现代内镜学[M].复旦大学出版社,上海医科大学出版社,2001.
[2]J. S. Lin, K. S. Cheng, C. W. Mao. Modified HoPfleld neural network with fuzzy c-means technique for multispectral MR image segmentation[C]. IEEE International Conference on Image Processing. Vol.1, PP.327-330,1996.
[3]J. I. Hasegawa, K. Mori, J. I. Toriwaki, H. Anllo, K. Katada. Automated extraction of lung cancer lesions from multislice ehest CT images by using three-dimensional image Proeessing[J]. Systems&Computers in Japan, Vol.25, PP.68-77,1994.
[4]W. M. Jeng, D. J. Yang. Portable PET image reconstruction system for parallel Maehines[C]. Proceeding of the IEEE Symposium on Computer-Based Medical Systems, PP.137-142,1998.
[5]Y. M. Kim, J. H. Kim, C. Basoglu, T. C. Winter. Programmable ultrasound imaging using multimedia technologies:a next-generation ultrasound machine[J]. IEEE Transaction on Information Technology in Biomedicine, VOI. 11, PP.19-29,1997.
[6]G. N. Khan, D. F. Ginies. Vision based navigation system for an endoscope[J]. Image and Vision Computing, Vol.14, PP.763-772,1996.
[7]S. Dogramadzi, C. R. Allen, G. D. Bell. Computer controlled colonoscopy[C]. Conference Record-IEEE Instrumentation and Measurement Technology Conference Vol.1, PP.210-213,1998.
[8]Z.Y.Liang, F.Yang, M. Wax, J.Li, J.You, A.Kaufman, L. Hong, H.Li, A. Viswambharan. Inclusion of a priori information in segmentation of colon lumenfor 3D virtual colonoscopy[C]. IEEE Nuclear Science Symposium & Medical Imaging Conference, Vol.2, PP.1423-1427,1997.
[9]C. K. Kwoh, D. E. Gillies. Using Fourier information for the detection of the lumen in endoscope images[C]. Proc. IEEE Region 10's Annual International Conference, Vol.2, PP.981-985,1995.
[10]S. M. Krishnan, C. S. Tan, K. L. Chan. Closed-boundary extraction of largeintestinal lumen[C]. Proc. Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Vol.16, PP.610-611,1994.
[11]S. M. Krishnan, P. M. Y. Goh. Quantitative parameterization of colonoscopic images by applying fuzy technique[C]. In 19th IEEE/EMBS Int. Conf, PP1121-1123,1997.
[12]Shunren Xia, Shankar M. Krishnan, Marta P. Tjioa, et al. A novel approach for extracting colon's lumen from colonoscopic images[C]. Proeeeding of 6th world Multiconference on Systemics, Cybernetics and informatics, July 14-18, 2002, Florida, USA.
[13]Manuel M. Oliveira, Brian Bowen, Richard McKenna, Yu-Sung Chang. Fast Digital Image Inpainting[C]. Proceedings of the International Conference on Visualization, Imaging and Image Processing, PP.261-266, Marbella, Spain, Sept 3-5,2001.
[14]Heng-Da Cheng, Ying Sun. A Hierarchical Approach to Color Image Segmentation Using Homogeneity[J]. IEEE Transactions on Image Processing, Vol.9, No.12, PP.2071-2082,2000.
[15]Naik Sarif Kumar, Murthy. C. A. Hue-preserving color image enhancement without gamut problem[J]. IEEE Transacitona on Image Processing,2003, 12(12):1591-1598.
[16]H.D.Cheng, X.H.Jiang, Y. Sun, J. L. Wang. Color image segmentation: Advances and prospects[J]. Pattern Recognit., Vol.34, No.12, PP.2259-2281,2001.
[17]N. Pal, S. Pal. A reviewon image segmentation techniques[J]. Pattern Recognit., Vol.26, No.9, PP.1277-1294,1993.
[18]J. Gauch, C. Hsia. A comparison of three color images segmentation algorithms in four color spaces[C]. in Proc. SPIE Visual Communications Image Processing'92, Vol.1818.
[19]C.K.Yang, W. H. Tsai. Reduction of color space dimensionality by moment-preserving thresholding and its application for edge detection in color images[J]. Pattern Recognit. Lett., Vol.17, PP.481-490,1996.
[20]E. Littmann, H. Ritter. Adaptive color segmentation-A comparison of neural and statistical methods[J]. IEEE Trans. Neural Networks, Vol.8, Jan,1997.
[21]T. Uchiyama, M. A. Arbib. Color image segmentation using competitive learning[J]. IEEE Trans. Pattern Anal. Machine Intell., Vol.16, PP.1197-1206, Dec,1994.
[22]R. M. Haralick, L. G. Shapiro. Image segmentation techniques[R]. Tech. Rep. CVGIP 29,1985.
[23]B. Schacter, L. Davis, A. Rosenfeld. Scene segmentation by cluster detection in color space[R]. Dept. Comput. Sci., Univ. Maryland, College Park, Nov, 1975.
[24]A. Sarabi, J. K. Aggarwal. Segmentation of chromatic images[J]. Pattern Recognit., Vol.13, No.6, PP.417-427,1981.
[25]S. A. Underwood, J. K. Aggarwal. Interactive computer analysis of aerial color infrared photographs [J]. Computer Graphics and Image Processing, Vol.6, No.1, PP.1-24,1977.
[26]J. M. Tenenbaum, T. D. Garvey, S. Weyl, H. C. Wolf. An interactive facility for scene analysis research[J]. Artif. Intell. Center, Stanford Res. Institute, Menlo Park, CA, Tech. Rep.87,1974.
[27]R. Ohlander, K. Price, D. R. Reddy. Picture segmentation using a recursive region splitting method[J]. Computer Graphics and Image Processing, Vol.8, No.3, PP.313-333,1978.
[28]R.C.Gonzalez, P.Wintz.Digital Image Processing[M].Reading, MA: Addison-Wesley,1987.
[29]J. R. Parker. Algorithms for Image Processing and Computer Vision[M]. New York:Wiley,1997.
[30]G. Robinson. Color edge detection[J]. Optical Engineering, Vol.16, PP.479-484,1977.
[31]P. Wang, S. M. Krishnan, C. Kugean, M. P. Tjoa. Classification of Endoscopic Images Based on Texture and Neural Network[C]. Proceedings of the 23rd Annual EMBS International Conference, PP.3691-3695, Istanbul, Turkey, October 25-28,2001.
[32]S. M. Krishnan, X.Yang, K.L.Chan, S.Kumar, P. M. Y. Goh. Intestinal Abnormality Detection from Endoscopic Images [C]. the 20th Annual International Conference of the IEEE Engineering in Medicine and Biology Society(EMBS 98), PP.895-898, Hongkong, China, October 29-November 1,1998.
[33]B. V. Dhandra, Ravindra Hegadi, Mallikarjun Hangarge, V. S. Malemath. Endoscopic image classification based on active contours without edges [C].1st International Conference on Digital Information Management, PP.167-172, Bangalore, India, December 6-8,2006.
[34]M. P. Tjoa, S. M. Krishnan, M. M. Zheng. A Novel Endoscopic Image Analysis Approach using Deformable Region Model to Aid in Clinical Diagnosis[C]. Proceedings of the 25th Annual EMBS International Conference, PP.710-713, Cancun, Mexico, September 17-21,2003.
[35]阮秋琦.数字图像处理学[M].电子工业出版社,2001.
[36]朱志刚,林学阎.石定机.数字图像处理[M].电子工业出版社,2002.
[37]D. K. Panjwani, G.Healey. Markov random field models for unsupervised segmentation of texture colour images[J]. IEEE Trans. Pattern Anal. Machine Intel., Vol.17, PP.939-954,1995.
[38]R. Krishnamoorthi, P. Bhattacharyya. On unsupervised segmentation of colour texture images, High-Performance[C]. Proc. Fourth International Conference on, PP.500-504,1997.
[39]T. Ojala, M. Pietikainen. Unsupervised texture segmentation using feature distribution[J]. Pattern Recognition, Vol.32, PP.477-486,1999.
[40]M. Celenk. Hierarchical colour clustering for segmentation of textured images[C]. System Theory, Proceedings of the Twenty-Ninth Southeastern Symposium on, PP.483-487,1997.
[41]Dong-Chen He, Li Wang. Texture Features Based On Texture Spectrum[J]. Pattern Recognition, Vol.24, No.5, PP.391-399,1991.
[42]D. K. Iakovidis, D. E. Maroulis, S. A. Karkanis, A. Brokos. A Comparative Study of Texture Features for the Discrimination of Gastric Polyps in Endoscopic Video [C].18th IEEE Symposium on Computer-Based Medical Systems, PP.575-580, Dublin, Ireland, June 23-24,2005.
[43]Sea Hwang, JungHwan Oh, Wallapak Tavanapong, Johnny Wong, Piet C.de Groen. Polyp Detection in Colonoscopy Video Using Elliptical Shape Feature [C]. IEEE International Conference on Image Processing PP.465-468, San Antonio, TX, USA, Sept 16-19,2007.
[44]Da-Chuan Cheng, Wen-Chien Ting, Yung-Fu Chen, Qin Pu, Xiaoyi Jiang. Colorectal Polyps Detection Using Texture Features and Support Vector Machine[C].3rd International Conference on Advances in Mass Data Analysis of Images and Signals in Medicine, Biotechnology, Chemistry and Food Industry, PP.62-72, Leipzig, Germany, July 14,2008.
[45]L. A. Alexandre, N. Nobre, J. Casteleiro. Color and Position versus Texture Features for Endoscopic Polyp Detection[C].1st International Conference on Biomedical Engineering and Informatics. PP.38-42, Sanya, China, May 27-30,2008.
[46]Jin Zou, Hongsong Li, Bin Liu, Renfei Zhang. Color Edge Detection Based on Morphology[C].2006 First International Conference on Communications and Electronics, Proceedings, PART 1, PP.291-293,2006.
[47]Lianqiang Niu, Wenju Li. Color Edge Detection Based on Direction Information Measure [C]. Proceedings of the World Congress on Intelligent Control and Automation, Vol.2, PP.9533-9536,2006.
[48]Jian Fan. A Local Orientation Coherency Weighted Color Gradient for Edge Detection[C]. Proceedings-International Conference on Image Processing, Vol.3, PP.1132-1135,2005.
[49]Fabrizio Russo, Annarita Lazzari. Color Edge Detection in Presence of Gaussian Noise Using Nonlinear Prefiltering[J]. IEEE Transactions on Instrumentation and Measurement, Vol.54, No.1, PP.352-358, January, 2005.
[50]W. H. Tsang, P. W. M. Tsang. Edge gradient method on object color[C]. Proceedings of the 1996 IEEE Region 10 TENCON-Digital Signal Processing Applications Conference, Part 2 (of 2), PP.304-310, Perth, Australia, Nov 26-29,1996.
[51]何斌,马天予,王运坚,朱红莲.Visual C++数字图像处理[M].人民邮电出版社,2002.
[52]黎自强,滕弘飞.广义Hough变换:多个圆的快速随机检测[J].计算机辅助设计与图形学学报,Vol.18, No.1, PP.27-33,2006.
[53]H. K. Yuen, J. Illingworth, J. Kittler. Detecting partially occluded ellipses using the Hough transform[J]. Image and Computer Vision, Vol.7, No.1, PP.31-37, February,1989.
[54]L. Xu, E. Oja, P. Kultanen. A new curvedetection method, Randomized Hough Transform(RHT) [J]. Pattern Recognition Letters, Vol.11, No.5, PP.331-338, 1990.
[55]L. Xu, E. Oja. Further Developmentson RHT:Basic Mechanisms, Algorithms and Computational Complexities. Proceedings 11th I APR International Conference on Pattern Recognition, Vol.1, Conference A:Computer Vision and Applications,1992, PP.125-128, IEEE Computer Society Press.
[56]L. Xu, E. Oja. Randomized Hough Transform(RHT):Basic Mechanisms, Algorithms and Computational Complexities. CVGIP:Image Understanding, Vol.57, No.2, March,1993, PP.131-154, Academic Press Inc.
[57]Robert A. McLaughlin. Randomized Hough Transform:Better Ellipse Detection[C]. IEEE Region 10 Annual International Conference Proceedings, Voll, PP.409-414,1996.
[58]Cheng Zhiguo, Liu Yuncai. Efficient Technique for Ellipse Detection Using Restricted Randomized Hough Transform [C]. International Conference on Information Technology:Coding Computing, Vol 2, PP.714-718,2004.
[59]Bennett Nick, Burridge Robert, Saito Naoki. A Method to Detect and Characterize Ellipses Using the Hough Transform [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol 21, No7, PP.652-657,1999.
[60]李良福,冯祖仁,贺凯良.一种基于随机Hough变换的椭圆检测算法[J].模式识别与人工智能,Vol.18, No.4, PP.459-464,2005.
[61]R. Halir, J. Flusser. Numerically Stable Direct Least Squares Fitting of Ellipses [J].6th International Conference in Central Europe on Computer Graphics and Visualization, PP.125-132, Plzen, Czech Republic, Feb 9-13, 1998.