The Optimized Classification of Mammograms Based on the Antlion Technique

The Optimized Classification of Mammograms Based on the Antlion Technique

Ashish Negi (Govind Ballabh Pant Engineering College, India) and Saurabh Sharma (Uttarakhand Technical University, India)
Copyright: © 2020 |Pages: 23
DOI: 10.4018/IJGHPC.2020040104

Abstract

Breast cancer is one of the main health issues for women. This disease can be cured only if detected at early stages. Digital mammography is used to detect the malignant cells at an early stage. This article designs a methodology to detect the malignant tumors. The methodology is comprised of preprocessing feature extraction by Gabor and Law's feature extraction, and feature reduction by ant-lion optimization as well as a classification step using a SVM classifier which is implemented on the live dataset prepared through the Rajindra Hospital Patiala along with MIAS and DDSM datasets. The results of proposed techniques have been compared with three states of art techniques SVM based classification without feature reduction, PSOWNN i.e. PSO based reduction with a neural network as a classifier and binary gray wolf-based feature reduction with SVM classifier. The performance analysis proves the significance of the technique.
Article Preview
Top

Introduction

Breast Cancer can be treated easily in the starting stages whereas it becomes almost impossible to cure when cancer reaches in their highly developed stages. A biopsy is used to confirm whether abnormal tissue or the breast lump is cancer or not. In a biopsy, diagnosis is made by a pathologist in which a needle biopsy or surgical excision remove a suspicious tissue and examining it with a microscope (Zhang et al., 2012). Imaging techniques are therefore vital for effective treatment of a patient with breast cancer since cancer can be detected in early stages and the suspicious lesion present in the breast may be localized for a biopsy. Several imaging techniques may be used for imaging breast such as ultrasound imaging, MRI imaging and digital mammography (Wei et al., 2005). The radiograph of the breast tissue is called a mammogram which is an effective non-invasive technique to examine the breast for the presence of breast cancer. Mammography is the most widely used today throughout the world for the detection and diagnosis of breast cancer malignancies. The composition of breast tissue is inhomogeneous and anisotropic and shows a variation as the age progresses and hormone levels in a woman change. Reading mammograms is a challenge for radiologists because of the nature of the soft tissue within the breast, its inherent non-rigid body behavior, temporal changes of the breast tissue and variation in imaging condition (Salem et al., 2013; Hadjiiski et al., 2006). Digital mammography in which the electronic breast image is taken and directly stored on a computer is a fairly new technology has increased the breast cancer detection by using the Computer Aided Diagnosis (CAD). The CAD has removed the human error which gets introduced due to the interception of the mammograms by the radiologist (Wei et al., 2007; Pisano et al., 2005; Sahiner et al., 2001). The accuracy of diagnosis mammography has shown a significant increase with the integration of computer models which in turn help radiologists to make a decision. In CAD diagnostic image processing, artificial intelligence and pattern recognition (Giger, 2000; Wei et al., 2005) can be integrated and the output of these systems can be used as a “second opinion” in detecting malignancy and making decisions. In the past several years, both research scientists and radiologists have paid much attention to CAD systems because of the challenges and various clinical applications. Commercial CAD systems based on FFDM and screen-film mammography have been reported to have similar performance (Pisano et al., 2005; Manjusha et al., 2011).

The breast cancer detection is a process of classification which is used to classify the whether the tumor is benign or malignant. The digital mammogram stores the image of the breast which is processed by the computer-aided tools. The overall process to detect the breast cancer is shown in Figure 1 (Dheeba et al., 2014).

Figure 1.

Steps to detect breast cancer

IJGHPC.2020040104.f01

Complete Article List

Search this Journal:
Reset
Open Access Articles: Forthcoming
Volume 13: 4 Issues (2021): Forthcoming, Available for Pre-Order
Volume 12: 4 Issues (2020)
Volume 11: 4 Issues (2019)
Volume 10: 4 Issues (2018)
Volume 9: 4 Issues (2017)
Volume 8: 4 Issues (2016)
Volume 7: 4 Issues (2015)
Volume 6: 4 Issues (2014)
Volume 5: 4 Issues (2013)
Volume 4: 4 Issues (2012)
Volume 3: 4 Issues (2011)
Volume 2: 4 Issues (2010)
Volume 1: 4 Issues (2009)
View Complete Journal Contents Listing