Feature Extraction Using Composite Individual Genetic Programming: An Application to Mass Classification

This paper proposes a novel method for breast cancer diagnosis using the features generated by genetic programming (GP). We developed a new individual combination pattern (Composite individual genetic programming) which regards several individual as one unity to generate more powerful features that can improve the discriminatory performance of a classifier and reducing the input feature dimensionality at the same time. The performance of the proposed method is demonstrated by extensive experiments on MIAS and DDSM mammographic image database.

[1]  M J Homer.  Breast imaging: pitfalls, controversies, and some practical thoughts. , 1985, Radiologic clinics of North America.

[2]  John R. Koza,et al.  Genetic programming - on the programming of computers by means of natural selection , 1993, Complex adaptive systems.

[3]  Heinz-Otto Peitgen,et al.  Fractal Geometry and Computer Graphics , 1992 .

[4]  M. Yaffe,et al.  Characterisation of mammographic parenchymal pattern by fractal dimension. , 1990, Physics in medicine and biology.

[5]  Berkman Sahiner,et al.  Classification of mass and normal breast tissue: a convolution neural network classifier with spatial domain and texture images , 1996, IEEE Trans. Medical Imaging.

[6]  Harris Georgiou,et al.  Significance analysis of qualitative mammographic features, using linear classifiers, neural networks and support vector machines. , 2005, European journal of radiology.

[7]  J.E.L. Desautels,et al.  Shape factors for analysis of breast tumors in mammograms , 1996, Proceedings of 1996 Canadian Conference on Electrical and Computer Engineering.

[8]  Asoke K. Nandi,et al.  Toward breast cancer diagnosis based on automated segmentation of masses in mammograms , 2009, Pattern Recognit..

[9]  H P Chan,et al.  Combined adaptive enhancement and region-growing segmentation of breast masses on digitized mammograms. , 1999, Medical physics.

[10]  Jonathan E. Fieldsend,et al.  Identification of masses in digital mammograms with MLP and RBF nets , 2000, Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000. Neural Computing: New Challenges and Perspectives for the New Millennium.

[11]  Pasquale Delogu,et al.  Characterization of mammographic masses using a gradient-based segmentation algorithm and a neural classifier , 2007, Comput. Biol. Medicine.

[12]  M. Giger,et al.  Automated computerized classification of malignant and benign masses on digitized mammograms. , 1998, Academic radiology.

[13]  L. Bruce,et al.  Classifying mammographic mass shapes using the wavelet transform modulus-maxima method , 1999, IEEE Transactions on Medical Imaging.

[14]  Martin J. Yaffe,et al.  Characterization Of Mammographic Parenchymal Pattern By Fractal Dimension , 1989, Medical Imaging.

[15]  Asoke K. Nandi,et al.  Detection of masses in mammograms via statistically based enhancement, multilevel-thresholding segmentation, and region selection , 2008, Comput. Medical Imaging Graph..

[16]  M. Homer,et al.  Imaging features and management of characteristically benign and probably benign breast lesions. , 1987, Radiologic clinics of North America.

[17]  N. Petrick,et al.  Design of a high-sensitivity classifier based on a genetic algorithm: application to computer-aided diagnosis , 1998, Physics in medicine and biology.

[18]  Ian W. Ricketts,et al.  The Mammographic Image Analysis Society digital mammogram database , 1994 .

[19]  José L. Encarnação,et al.  Modeling and Simulation , 1992 .

[20]  Berkman Sahiner,et al.  Computer-aided characterization of mammographic masses: accuracy of mass segmentation and its effects on characterization , 2001, IEEE Transactions on Medical Imaging.

[21]  Maryellen L. Giger,et al.  Computerized detection of masses in digital mammograms: Investigation of feature-analysis techniques , 1994, Journal of Digital Imaging.