Benign and Malignant Breast Cancer Features Based on Region Characteristics
Breast cancer is one of the most common malignant diseases among women. Mammography is at present one of the available method for early detection of abnormalities, which is related to breast cancer; there are different lesions that are breast cancer characteristic such as masses, which can be detected through this technique. In this work, we explore the application of density slicing and region growing techniques to the problem of finding the boundary of different breast tissue regions in mammograms and extracting these regions. The goal of the segmentation algorithm is to see if density slices images and region growing algorithm could separate different densities for the different breast patterns and calculating there features. Segmentation of the mammogram into different mammographic densities is useful for risk assessment and quantitative evaluation of density changes and for extracting the cancer regions. Our proposed methodology for the segmentation of mammograms has been tested on Mini-MIAS database images. The final result is the segmentation of Region of I interest (ROI) with edge map and different features extraction for analysis where the extracted regions are saved as images and the texture features were calculated using Gray Level Co-Occurrence Matrix (GLCM) along 0^°such as contrast, correlation, homogeneity, sum variance, entropy, energy, mean values and others to differentiate between the Benign and Malignant images. It was found that the features such as contrast, correlation, smoothness, and difference variance are the optimal features to differentiate between benign and malignant regions where the other features are approximately the same. Also region growing method is very fast for extracting cancer regions. Our results are important to design artificial intelligence system to diagnostic breast cancer into benign and malignant cancer.
Dhahbi S, Barhoumi W, Zagrouba E (2015) Breast cancer diagnosis in digitized mammograms using curve let moments. ComputBiol Med 64: 79-90.
Dheeba J, Singh NA, Selvi ST (2014) Computer-aided detection of breast cancer on mammograms: A swarm intelligence optimized wavelet neural network approach. J Biomed Inform 49: 45-52.
Gullanar M. Hadi, & Nassir H. Salman, (2016) “Image Segmentation Based on Single Seed Region Growing Algorithm” (2016) ZJPAS (2016) 28(2); s120-126.
Haralick, Robert M., and Karthikeyan Shanmugam. (1973), "Textural features for image classification." IEEE Transactions on systems, man, and cybernetics 6, pp 610-621.
Jalalian A, Mashohor S, Mahmud R, Karasfi B, Saripan MIB, et al. (2017) Foundation and methodologies in computer-aided diagnosis systems for breast cancer detection. Excli 16: 113.
Muramatsu C, Hara T, Endo T, Fujita H (2016) Breast mass classification mammograms using radial local ternary patterns. ComputBiol Med 72: 43-53.
Pereira DC, Ramos RP, Do Nascimento MZ (2014) Segmentation and detection of breast cancer in mammograms combining wavelet analysis and genetic algorithm. Compute Methods Programs Biomed 114: 88-101.
Copyright (c) 2019 Gullanar M Hadi
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
At Zanco Journal, we're dedicated to protecting your rights as an author, and ensuring that any and all legal information and copyright regulations are addressed. Whether an author is published with Zanco Journal or any other publisher, we hold ourselves and our colleagues to the highest standards of ethics, responsibility and legal obligation