CFP last date
22 April 2024
Reseach Article

Classification of Clustered Microcalcifications using Resilient Backpropagation Training Algorithm

Published on October 2011 by Baljit Singh Khehra, Amar Partap Singh
IP Multimedia Communications
Foundation of Computer Science USA
IPMC - Number 1
October 2011
Authors: Baljit Singh Khehra, Amar Partap Singh
cdcf9c88-f6ac-45be-942e-57c496311830

Baljit Singh Khehra, Amar Partap Singh . Classification of Clustered Microcalcifications using Resilient Backpropagation Training Algorithm. IP Multimedia Communications. IPMC, 1 (October 2011), 118-124.

@article{
author = { Baljit Singh Khehra, Amar Partap Singh },
title = { Classification of Clustered Microcalcifications using Resilient Backpropagation Training Algorithm },
journal = { IP Multimedia Communications },
issue_date = { October 2011 },
volume = { IPMC },
number = { 1 },
month = { October },
year = { 2011 },
issn = 0975-8887,
pages = { 118-124 },
numpages = 7,
url = { /specialissues/ipmc/number1/3763-ipmc027/ },
publisher = {Foundation of Computer Science (FCS), NY, USA},
address = {New York, USA}
}
%0 Special Issue Article
%1 IP Multimedia Communications
%A Baljit Singh Khehra
%A Amar Partap Singh
%T Classification of Clustered Microcalcifications using Resilient Backpropagation Training Algorithm
%J IP Multimedia Communications
%@ 0975-8887
%V IPMC
%N 1
%P 118-124
%D 2011
%I International Journal of Computer Applications
Abstract

Breast cancer continues to be the leading cause of death among women nowadays all over the world. Most frequent type of breast cancer is ductal carcinoma in situ (DCIS) and most frequent symptoms of DCIS recognized by mammography are clusters of Microcalcifications. In this paper, Resilient Backpropagation training algorithm is investigated for automated classification of clustered Microcalcifications (MCCs) as benign or malignant. The classifier is a part of computer aided disease diagnosis (CAD) system that is widely used to aid radiologists in the interpretation of mammograms. The performance of Resilient Backpropagation training algorithm is compared with a well known Batch Gradient Descent training algorithm. Such methods are explored not only for accuracy point of view but also for computational efficiency for MCCs characterization in mammograms. As input, these methods used mammogram features extracted from MCCs. Such methods are tested using images of mini-MIAS database (Mammogram Image Analysis Society database (UK)). Receiver operating characteristic (ROC) analysis is used to evaluate and compare classification performance of these methods. Experimental results demonstrate that Resilient Backpropagation training algorithm could greatly reduce the computational complexity of Multi layer Feed Forward Backpropagation Artificial Neural Network (MLFFBP-ANN) while maintaining its best classification accuracy. It can produce lower false positives and false negatives than Batch Gradient Descent training algorithm.

References
  1. C. C. Boring, T. S. Squires, T. Tong and M. Montgomery, “Cancer Statistics 1994”, CA-Cancer J. Clinicians, 44, pp.7-26, 1994.
  2. H. D. Cheng and Muyi Cu, “Mass Lesion Detection with a Fuzzy Neural Network”, J. Pattern Recognition, 37, pp.1189-1200, 2004.
  3. Jun Xu and Jinshan Tang, “Detection of Clustered Microcalcifications using an Improved Texture based Approach for Computer Aided Breast Cancer Diagnosis System”, J. CSI Communications, vol. 31, no. 10, pp. 17-20, 2008.
  4. Sickles E, “Breast Calcifications: Mammographic Evaluation”, J. Radiology, 160, pp.289-293, 1986.
  5. Wallis M, Walsh M and Lee J, “A Review of False Negative Mammography in a Symptomatic Population”, J. Clin. Radiology, 144, pp.13-15, 1991.
  6. Celia Varela, Pablo G. Tahoces, Arturo J. Mendez, Miguel Souto and Juan J. Vidal, “Computerized Detection of Breast Masses in Digitized Mammograms”, J. Computers in Biology and Medicine, 37, pp.214-226, 2007.
  7. J. C. Fu, S. K. Lee, S. T. C. Wong, J. Y. Yeh, A. H. Wang and H. K. Wu, “Image Segmentation Features Selection and Pattern Classification for Mammographic Microcalcifications”, J. Computer Methods and Programs in Biomedicine, 29, pp.419-429, 2005.
  8. Thor. Ole Gulsrud and J. H. Husoy, “Optimal Filter-based Detection of Microcalcifications”, IEEE trans. on Biomedical Engineering, vol.48, no.11, pp.1272-1280, Nov 2001.
  9. M. G. Linguraru, K. Marias, R. English and M. Brady, “A Biologically Inspired Algorithm for Microcalcification Cluster Detection”, J. Medical Image Analysis, 10, pp.850-862, 2006.
  10. Huai Li, K. J. Ray Liu and Shih-Chung B. Lo, “Fractal Modeling and Segmentation for the Enhancement of Microcalcifications in Digital Mammograms”, IEEE trans. on Medical Imaging, vol.16, no.6, pp. 785-798, Dec1997.
  11. Brijesh Verma and Ping Zhang, “A Novel Neural-Genetic Algorithm to find the Most Significant Combination of Features in Digital Mammograms”, J. Applied Soft Computing, 7, pp.612-625, 2007.
  12. D. Kramer and F. Aghdasi, “Classifications of Microcalcifications in Digitized Mammograms using Multi-scale Statistical Texture Analysis”, Proc. of the South African Symposium on Communications and Signal Processing, Sept. 7-8,1998, pp.121-126.
  13. Nakayama R, Uchiyama Y, Hatsukade I, Yamamoto K, Watanabe R, Namba L et al., “Discrimination of Malignant and Benign Microcalcification Clusters on Mammograms”, J. Computer Aided Diagnosis of Medical Images ,3, pp.1-7,1999.
  14. Bottema MJ and Slavotinek JP, “Detection and Classification of Lobular and DCIS (small cell) Microcalcifications in Digital Mammograms”, J. Pattern Recognition Letters, 21, pp.1209-1214, 2000.
  15. Hamid Soltanian-Zadeh, Farshid Rafiee-Rad and Siamak Pourabdollah-Nejad D, “Comparison of Multi wavelet, Wavelet, Haralick and Shape Features for Microcalcification Classification in Mammograms”, J. Pattern Recognition, 37, pp.1973-1986, 2004.
  16. Nicandro Cruz-Ramirez, Hector Gabriel Acosta-Mesa, Humberto Carrillo-Calvet, Luis Alonso Nava-Fernandez et al., “Diagnosis of Breast Cancer using Bayesian Networks : A Case Study”, J. Computers in Biology and Medicine, 37, pp.1553-1564, 2007.
  17. AboulElla Hassanien, “Fuzzy Rough Sets Hybrid Scheme for Breast Cancer Detection”, J. Image and Vision Computing, 25, pp.172-183, 2007.
  18. I. Christoyianni, A. Koutras, E. Dermatas and G. Kokkinakis, “Computer Aided Diagnosis of Breast Cancer in Digitized Mammograms”, J. Computerized Medical Imaging and Graphics, 26, pp.309-319, 2002.
  19. Stelios Halkiotis, Taxiarchis Botsis and Maria Rangoussi, “Automatic Detection of Clustered Microcalcifications in Digital Mammograms using Mathematical Morphology and Neural Networks”, J. Signal Processing, 87, pp.1559-1568, 2007.
  20. Maciej A. Mazurowski, Piotr A. Habas, Jacek M. Zurada, Joseph Y. Lo, Jay A. Baker and Georgia D. Tourassi, “Training Neural Network Classifiers for Medical Decision Making: The Effects of Imbalanced Datasets on Classification Performance”, J. Neural Networks, 21, pp.427-436, 2008.
  21. Dursun Delen, Glenn Walker and Amit Kadam, “Predicting Breast Cancer Survivability: A Comparison of Three Data Mining Methods”, J. Artificial Intelligence in Medicine, 34, pp.113-127, 2005.
  22. Amar Partap Singh, Tara Singh Kamal and Shakti Kumar, “Virtual Curve Tracer for Estimation of Static Response Characteristics of Transducers”, J. Measurement, 38, pp. 166-175, 2005.
  23. Nikhil R. Pal, Brojeshwar Bhowmick, S. K. Patel, S. Pal and J. Das, “A Multi-stage Neural Network Aided System for Detection of Microcalcifications in Digitized Mammograms”, J. Neurocomputing, 71, pp.2625-2634, 2008.
Index Terms

Computer Science
Information Sciences

Keywords

Batch Gradient Descent Breast Cancer Mammography Microcalcification Resilient Backpropagation