Unsupervised Segmentation of Medical Images using DCT Coefficients

Image segmentation is a prerequisite process for image content understanding and visual object recognition in medical images for the development of a computer aided diagnosis(CAD) system. An unsupervised segmentation method is proposed which uses discrete cosine transform (DCT) coefficients for extraction of feature vectors and the Fisher Discriminant K-means (FDK) technique for clustering image pixels. In this study, the parenchymal region in HRCT lung images is separated first and then feature vectors using the deviation in local variance in DCT coefficients are determined for each pixels of parenchyma regions. The extracted feature vectors are used for selection of the best feature sets by reducing the dimensionality of the feature vector. The reduced feature vector is used for unsupervised classification using the K-means clustering algorithm which is guided by Fisher linear discriminant parameters for determining number of distinguishable regions in the image.

[1]  Chee Sun Won.  Improved block-based image segmentation , 1999, Proceedings 1999 International Conference on Image Processing (Cat. 99CH36348).

[2]  A. Gupta,et al.  Text segmentation in mixed-mode images , 1994, Proceedings of 1994 28th Asilomar Conference on Signals, Systems and Computers.

[3]  Josef Kittler,et al.  On local linear transform and Gabor filter representation of texture , 1992, Proceedings., 11th IAPR International Conference on Pattern Recognition. Vol. III. Conference C: Image, Speech and Signal Analysis,.

[4]  Nuggehally Sampath Jayant,et al.  An adaptive clustering algorithm for image segmentation , 1989, International Conference on Acoustics, Speech, and Signal Processing,.

[5]  Jie Wei.  Image segmentation based on situational DCT descriptors , 2002, Pattern Recognit. Lett..

[6]  Morton Nadler,et al.  Pattern recognition engineering , 1993 .

[7]  Tamer Ölmez,et al.  Segmentation of ultrasound images by using a hybrid neural network , 2002, Pattern Recognit. Lett..

[8]  John E. Moody,et al.  Fast adaptive k-means clustering: some empirical results , 1990, 1990 IJCNN International Joint Conference on Neural Networks.

[9]  Thrasyvoulos N. Pappas,et al.  An Adaptive Clustering Algorithm For Image Segmentation , 1988, [1988 Proceedings] Second International Conference on Computer Vision.

[10]  Roberto Manduchi,et al.  Bayesian fusion of color and texture segmentations , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[11]  S J Swensen,et al.  High-resolution computed tomography of the lung. , 1989, Mayo Clinic proceedings.

[12]  Jianmin Jiang,et al.  JPEG compressed image retrieval via statistical features , 2003, Pattern Recognit..

[13]  Josef Kittler,et al.  Defect detection in random colour textures , 1996, Image Vis. Comput..

[14]  Robert Reeves,et al.  Texture characterization of compressed aerial images using DCT coefficients , 1997, Electronic Imaging.

[15]  David A. Clausi,et al.  K-means Iterative Fisher (KIF) unsupervised clustering algorithm applied to image texture segmentation , 2002, Pattern Recognit..