Unsupervised Detection of Suspicious Tissue Using Data Modeling and PCA

Breast cancer is a major cause of death and morbidity among women all over the world, and it is a fact that early detection is a key in improving outcomes. Therefore development of algorithms that aids radiologists in identifying changes in breast tissue early on is essential. In this work an algorithm that investigates the use of principal components analysis (PCA) is developed to identify suspicious regions on mammograms. The algorithm employs linear structure and curvelinear modeling prior to PCA implementations. Evaluation of the algorithm is based on the percentage of correct classification, false positive (FP) and false negative (FN) in all experimental work using real data. Over 90% accuracy in block classification is achieved using mammograms from MIAS database.

[1]  Chin-Chen Chang,et al.  A near pattern-matching scheme based upon principal component analysis , 1995, Pattern Recognit. Lett..

[2]  Zhengmao Ye,et al.  Principal component analysis approach for biomedical sample identification , 2004, 2004 IEEE International Conference on Systems, Man and Cybernetics (IEEE Cat. No.04CH37583).

[3]  N. Dubrawsky.  Cancer statistics , 1989, CA: a cancer journal for clinicians.

[4]  R Swiniarski,et al.  Comparison of Feature Extraction and Selection Methods in Mammogram Recognition , 2002, Annals of the New York Academy of Sciences.

[5]  Reyer Zwiggelaar.  Separating Background Texture, Image Structure in Mammograms , 1999, BMVC.

[6]  Shiming Zhan,et al.  A zero-crossing-based optimal three-dimensional edge detector , 1994 .

[7]  A. Ardeshir Goshtasby,et al.  Edge detection by curve fitting , 1995, Image Vis. Comput..

[8]  Ben Pinkowski.  Principal component analysis of speech spectrogram images , 1997, Pattern Recognit..

[9]  K. Drouiche,et al.  Highly regular wavelets for the detection of clustered microcalcifications in mammograms , 2003, IEEE Transactions on Medical Imaging.

[10]  K L Lam,et al.  Computerized classification of malignant and benign microcalcifications on mammograms: texture analysis using an artificial neural network. , 1997, Physics in medicine and biology.

[11]  Shan Duan,et al.  Edge detection based on dynamic morphology , 2005, International Symposium on Multispectral Image Processing and Pattern Recognition.

[12]  Richard O. Duda,et al.  Use of the Hough transformation to detect lines and curves in pictures , 1972, CACM.

[13]  William E. Higgins,et al.  Edge detection using two-dimensional local structure information , 1994, Pattern Recognit..

[14]  Milan Sonka,et al.  Directional 3D Edge Detection in Anisotropic Data: Detector Design and Performance Assessment , 2000, Comput. Vis. Image Underst..

[15]  Rangaraj M. Rangayyan,et al.  Region-based contrast enhancement of mammograms , 1992, IEEE Trans. Medical Imaging.

[16]  Clark F. Olson,et al.  Constrained Hough Transforms for Curve Detection , 1999, Comput. Vis. Image Underst..

[17]  Song Ming,et al.  Image edge detection based on omnidirectional multiscale morphology , 2005 .

[18]  Nicolaos B. Karayiannis,et al.  Detection of microcalcifications in digital mammograms using wavelets , 1998, IEEE Transactions on Medical Imaging.

[19]  T. Rabbani,et al.  EFFICIENT HOUGH TRANSFORM FOR AUTOMATIC DETECTION OF CYLINDERS IN POINT CLOUDS , 2005 .

[20]  Rangaraj M. Rangayyan,et al.  Application of shape analysis to mammographic calcifications , 1994, IEEE Trans. Medical Imaging.

[21]  Karla Kerlikowske,et al.  Benefit of mammography screening in women ages 40–49 years: Current evidence from randomized controlled trials , 1995, Cancer.

[22]  V. F. Leavers,et al.  Which Hough transform , 1993 .

[23]  Rajiv Mehrotra,et al.  A Computational Approach to Zero-Crossing-Based Two-Dimensional Edge Detection , 1996, CVGIP Graph. Model. Image Process..

[24]  T. Tong,et al.  Cancer statistics, 1994 , 1994, CA: a cancer journal for clinicians.

[25]  Robert M. Haralick,et al.  Integrated Directional Derivative Gradient Operator , 1987, IEEE Transactions on Systems, Man, and Cybernetics.