Breast tumor detection in double views mammography based on extreme learning machine

Mammography is one of the most important methods for breast tumor detection, while existing computer-aided diagnosis (CAD) technology based on single-view mammograms ignores the contrastive feature between medio-lateral oblique (MLO) and cranio-caudal (CC) views, and CAD technology based on double-view overlooks features of single views. But in clinical environment, radiologists not only read both CC view images and MLO view images individually, but also contrast these two types of views to diagnose each case. Therefore, to simulate diagnosis process of radiologists, in this paper, a fused feature model which blends features of single views with contrastive features of double views is proposed. The fused feature model is optimized by means of feature selection methods. Then, a CAD detection method based on extreme learning machine, a classifier with wonderful universal approximation capability, is proposed to improve the effectiveness of breast tumor detection by applying the optimum fused feature. The effectiveness of proposed method is verified by 222 pairs of mammograms from 222 women in Northeast China through the complete experiment.

[1]  Chee Kheong Siew,et al.  Incremental extreme learning machine with fully complex hidden nodes , 2008, Neurocomputing.

[2]  David Gur,et al.  An ellipse-fitting based method for efficient registration of breast masses on two mammographic views. , 2008, Medical physics.

[3]  M. Giger,et al.  Computer vision and artificial intelligence in mammography. , 1994, AJR. American journal of roentgenology.

[4]  Nico Karssemeijer,et al.  Matching mammographic regions in mediolateral oblique and cranio caudal views: a probabilistic approach , 2008, SPIE Medical Imaging.

[5]  Lei Chen,et al.  Enhanced random search based incremental extreme learning machine , 2008, Neurocomputing.

[6]  C. Maggio.  State of the art of current modalities for the diagnosis of breast lesions , 2004, European Journal of Nuclear Medicine and Molecular Imaging.

[7]  Ge Yu,et al.  Breast tumor detection in digital mammography based on extreme learning machine , 2014, Neurocomputing.

[8]  N. Petrick,et al.  Computerized characterization of masses on mammograms: the rubber band straightening transform and texture analysis. , 1998, Medical physics.

[9]  Guang-Bin Huang,et al.  Convex incremental extreme learning machine , 2007, Neurocomputing.

[10]  K R Hoffman,et al.  In the next decade automated computer analysis will be an accepted sole method to separate "normal" from "abnormal" radiological images. , 1999, Medical physics.

[11]  N. Karssemeijer,et al.  Finding corresponding regions of interest in mediolateral oblique and craniocaudal mammographic views. , 2006, Medical physics.

[12]  Daniel B Kopans,et al.  The most recent breast cancer screening controversy about whether mammographic screening benefits women at any age: nonsense and nonscience. , 2003, AJR. American journal of roentgenology.

[13]  Chee Kheong Siew,et al.  Extreme learning machine: Theory and applications , 2006, Neurocomputing.

[14]  Dianhui Wang,et al.  Extreme learning machines: a survey , 2011, Int. J. Mach. Learn. Cybern..

[15]  N. Petrick,et al.  Computer-aided classification of mammographic masses and normal tissue: linear discriminant analysis in texture feature space. , 1995, Physics in medicine and biology.

[16]  Lubomir M. Hadjiiski,et al.  Characterization of mammographic masses based on level set segmentation with new image features and patient information. , 2007, Medical physics.

[17]  W. Philip Kegelmeyer.  EVALUATION OF STELLATE LESION DETECTION IN A STANDARD MAMMOGRAM DATA SET , 1993 .

[18]  A. Miller,et al.  Why is breast-cancer mortality declining? , 2003, The Lancet. Oncology.

[19]  Matti Pietikäinen,et al.  Multiresolution Gray-Scale and Rotation Invariant Texture Classification with Local Binary Patterns , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[20]  Xunkai Wei,et al.  Linear programming minimum sphere set covering for extreme learning machines , 2008, Neurocomputing.

[21]  C. Floyd,et al.  Evaluation of information-theoretic similarity measures for content-based retrieval and detection of masses in mammograms. , 2006, Medical physics.

[22]  Hongming Zhou,et al.  Optimization method based extreme learning machine for classification , 2010, Neurocomputing.

[23]  Matti Pietikäinen,et al.  A Generalized Local Binary Pattern Operator for Multiresolution Gray Scale and Rotation Invariant Texture Classification , 2001, ICAPR.

[24]  Narasimhan Sundararajan,et al.  A sequential multi-category classifier using radial basis function networks , 2008, Neurocomputing.

[25]  Rangaraj M. Rangayyan,et al.  Gradient and texture analysis for the classification of mammographic masses , 2000, IEEE Transactions on Medical Imaging.

[26]  Chee Kheong Siew,et al.  Universal Approximation using Incremental Constructive Feedforward Networks with Random Hidden Nodes , 2006, IEEE Transactions on Neural Networks.

[27]  Jun-Seok Lim.  Recursive DLS solution for extreme learning machine-based channel equalizer , 2008, Neurocomputing.

[28]  Lubomir M. Hadjiiski,et al.  Improvement of mammographic mass characterization using spiculation meausures and morphological features. , 2001, Medical physics.

[29]  Luisa P. Wallace,et al.  Multiview-based computer-aided detection scheme for breast masses. , 2006, Medical physics.

[30]  Nico Karssemeijer,et al.  Combining two mammographic projections in a computer aided mass detection method. , 2007, Medical physics.

[31]  Hongming Zhou,et al.  Extreme Learning Machine for Regression and Multiclass Classification , 2012, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[32]  Zexuan Zhu,et al.  A fast pruned-extreme learning machine for classification problem , 2008, Neurocomputing.

[33]  B. Zheng,et al.  Integrated density of a lesion: a quantitative, mammographically derived, invariable measure. , 2003, Medical physics.

[34]  Nico Karssemeijer,et al.  Detection of stellate distortions in mammograms , 1996, IEEE Trans. Medical Imaging.