International Journal of Scientific & Technology Research

Home About Us Scope Editorial Board Blog/Latest News Contact Us
10th percentile
Powered by  Scopus
Scopus coverage:
Nov 2018 to May 2020


IJSTR >> Volume 9 - Issue 3, March 2020 Edition

International Journal of Scientific & Technology Research  
International Journal of Scientific & Technology Research

Website: http://www.ijstr.org

ISSN 2277-8616

Abnormality Detection And Classification Using Artificial Neural Network

[Full Text]



R.Rajakumari, L.Kalaivani



Mammogram, Gray Level Co-occurrence Matrix, Feed forward Neural Network, Receiver operating characteristic curve.



Among women community, the most dangerous disease is breast cancer. If it is detected in the early stage, the women will be rescued by giving proper treatment. The early detection is possible only by screening in regular interval. It will decrease the mortality rate. Mammography is a specialized medical imaging phenomenon that uses a low-dose x-ray system to see inside the breasts. It is called as mammogram, given support to the early detection and diagnosis of breast diseases in women. In this paper, an automated system is proposed to classify the breast tissues as normal or benign or malignant. Artifacts in the images are removed using Gaussian Mixture Model. Contrast-Limited Adaptive Histogram Equalization (CLAHE) algorithm is used to improve the appearance of the image. The features of the region of mammogram are extracted using hybrid feature extraction which includes Gray Level Co-occurrence Matrix (GLCM), texture and gradient. The features such as contrast, correlation, energy, homogeneity, global mean, uniformity, entropy and skewness are the best features that guarantee the improvement of classification with less feature dimension. K-Means clustering based segmentation is performed to identify the abnormality in the mammogram. The MIAS database images are considered for the evaluation. The feed forward Neural Network classifier is used for classification. Based on the classifier, the given input image is classified as normal or benign or malignant image. From the results, it shows that the proposed breast cancer identification method offers high accuracy and low complexity than the all other existing method.



[1] Anette Kniberg and David Nokto, “ A Benchmark of Prevalent Feature Selection Algorithms on a Diverse Set of Classification Problems”, Degree project in medical engineering, second cycle, stockholm sweden 2018
[2] Sarmistha Chakraborty, Mrinal Kanti Bhowmik, Anjan Kumar Ghosh and Tannistha Pal, Automated Edge Detection of Breast Masses on Mammograms, 978-1-5090-2597-8/16/$31.00 © 2016 IEEE.
[3] G.R. Jothilakshmi and Arun Raaza, “ Effective Detection of Mass Abnormalities and its Classification Using Multi-SVM Classifier with Digital Mammogram Images”, IEEE International Conference on Computer, Communication, and Signal Processing (ICCCSP-2017)
[4] A Computer-Aided Diagnosis System for Digital Mammograms Based on Fuzzy-Neural and Feature Extraction Techniques, Brijesh Verma and John Zakos, IEEE Transactions on Information Technology in Biomedicine, Vol. 5, No. 1, March 2001.
[5] Pavankumar M.Ahuja,R.D.Ghongade and Dr.D.G.Wakde, “Detection and Diagnosis of BreastTumors using Digital Mammogram Images: A fuzzy Approach”, International Journal of Science and Research (IJSR), Volume 5 Issue 12, December 2016.
[6] Wenfeng Han, Jianwei Dong, Yuting Guo, Ming Zhang and Jianzhong Wang, “ Identification of Masses in Digital Mammogram Using an Optimal Set of Features”, IEEE 10th International Conference on Trust, Security and Privacy in Computing and Communications 2011.
[7] N.M.Sangeetha and Dr.(Mrs).D.Pugazhenthi, “A novel shape and boundary extraction image processing technique for detecting the breast abnormalities using digital mammogram -Labview implementation”, Online International Conference on Green Engineering and Technologies (IC-GET), 2016.
[8] R. Dobrescu, L. Ichim, and D. Crisan, “Diagnosis of Breast Cancer from Mammograms by Using Fractal Measures,” International Journal of Medical Imaging, vol.1, no. 2, pp. 32-38, 2013.
[9] A.K. Mohanty, S. Beberta and S. K. Lenka, “Classifying Benign and Malignant Mass using GLCM and GLRLM based Texture Features from Mammograms,” International Journal of Engineering Research and Applications (IJERA), vol.1, no. 3, pp. 687-693, 2011
[10] Ankita Satyendra Singh, Prof. M. M. Pawar, “Mass Classification of Mammogram Images using Selected Textural Features with PNN Classifier”, 2nd National Conference on Recent Advances in Engineering and Technology (NCRAET_17), Vol.5, Special Issue 4, June 2017.