Advanced Enhancement Techniques for Breast Cancer Classification in Mammographic Images

Sara EL. Mohamed1, Wael A. Mohamed1, Mohamed B. Abdelhalim2, Khaled EL. Ahmed1, *
1 Department of Electrical Engineering, Benha University, Benha, Egypt
2 Arab Academy of Science and Technology and Maritime Transport (AASTMT), Cairo, Egypt

Article Metrics

CrossRef Citations:
Total Statistics:

Full-Text HTML Views: 515
Abstract HTML Views: 185
PDF Downloads: 294
ePub Downloads: 114
Total Views/Downloads: 1108
Unique Statistics:

Full-Text HTML Views: 258
Abstract HTML Views: 153
PDF Downloads: 166
ePub Downloads: 94
Total Views/Downloads: 671

Creative Commons License
© 2022 Mohamed et al.

open-access license: This is an open access article distributed under the terms of the Creative Commons Attribution 4.0 International Public License (CC-BY 4.0), a copy of which is available at: This license permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.

* Address correspondence to this author at the Department of Electrical Engineering, Benha University, Benha, Egypt; E-mail:



Breast cancer is one of the most significant health problems in the world. Early diagnosis of breast cancer is very important for treatment. Image enhancement techniques have been used to improve the captured images for quick and accurate diagnosis. These techniques include median filtering, edge enhancement, dilation, erosion, and contrast-limited adaptive histogram equalization. Although these techniques have been used in many studies, their results have not reached optimum values based on image properties and the methods used for feature extraction and classification.


In this study, enhancement techniques were implemented to guarantee the best image enhancement. They were applied to 319 images collected from the Mammographic Image Analysis Society (MIAS) database. The Gabor filter and local binary pattern were used as feature extraction methods together with support vector machine (SVM), linear discriminant analysis (LDA), and nearest neighbor (KNN) classifiers.


The experimental work indicates that by merging the features of the Gabor filter and local binary pattern, the results were 97.8%, 100%, and 94.6% for normal/abnormal and 85.1%, 88.7%, and 81.9% for benign/malignant using the SVM, LDA, and KNN classifiers, respectively.


The best results were obtained by combining the features of the two tested strategies and using LDA as a classifier.

Keywords: Breast cancer, Gabor filter, Local binary pattern, LDA, Benign, Malignant.