MRI breast cancer diagnosis hybrid approach using adaptive ant-based segmentation and multilayer perceptron neural networks classifier

• Published in: Applied soft computing Vol. 14; pp. 62 - 71
• Main Authors: Hassanien, Aboul Ella, Moftah, Hossam M., Azar, Ahmad Taher, Shoman, Mahmoud
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.01.2014
• Subjects: Ant Colony Optimization (ACO); Clustering; Magnetic resonance (MR) images; Neural network classifier; Segmentation; Swarm intelligence; Magnetic resonance (MR) images; Swarm intelligence; Ant Colony Optimization (ACO); Segmentation; Clustering; Neural network classifier
• ISSN: 1568-4946; 1872-9681
• DOI: 10.1016/j.asoc.2013.08.011

The proposed MRI breast cancer diagnosis is comprised of the following four fundamental building phases: (1) pre-processing phase: In the first phase of the investigation, a preprocessing algorithm based on fuzzy Type-II is presented. It is adopted and used to improve the quality of the images and to make the segmentation and feature extraction phase more reliable, (2) segmentation phase: in the second phase, a segmentation algorithm using the adaptive ant-based segmentation technique is presented to segment breast MR images. This technique is an improved ant-based clustering algorithm for segmenting breast MR images, (3) feature extraction phase: twenty statistical-based features have been extracted, normalized and represented in a database as vector values, (4) classification phase: the last phase is the classification and prediction of new objects, it is dependent on the multilayer perceptron neural networks classifier. These four phases are described in detail in the following section along with the steps involved and the characteristics feature for each phase and the overall architecture of the introduced approach is described in above this figure. [Display omitted] •Proposed a hybrid algorithm to classify the breast cancer images into two outcomes: Benign or Malignant.•An improved version of the classical ant-based clustering algorithm to segment the region of interest of breast images.•The overall accuracy offered by the employed hybrid technique confirms that the effectiveness and performance of the proposed hybrid system is high. This article introduces a hybrid approach that combines the advantages of fuzzy sets, ant-based clustering and multilayer perceptron neural networks (MLPNN) classifier, in conjunction with statistical-based feature extraction technique. An application of breast cancer MRI imaging has been chosen and hybridization system has been applied to see their ability and accuracy to classify the breast cancer images into two outcomes: Benign or Malignant. The introduced hybrid system starts with an algorithm based on type-II fuzzy sets to enhance the contrast of the input images. This is followed by an improved version of the classical ant-based clustering algorithm, called adaptive ant-based clustering to identify target objects through an optimization methodology that maintains the optimum result during iterations. Then, more than twenty statistical-based features are extracted and normalized. Finally, a MLPNN classifier was employed to evaluate the ability of the lesion descriptors for discrimination of different regions of interest to determine whether the cancer is Benign or Malignant. To evaluate the performance of presented approach, we present tests on different breast MRI images. The experimental results obtained, show that the adaptive ant-based segmentation is superior to the classical ant-based clustering technique and the overall accuracy offered by the employed hybrid technique confirm that the effectiveness and performance of the proposed hybrid system is high.