An Improved Decision Support System for Detection of Lesions in Mammograms Using Differential Evolution Optimized Wavelet Neural Network

Abstract

In this paper, a computerized scheme for automatic detection of cancerous lesion in mammograms is examined. Breast lesions in mammograms are an area with an abnormality or alteration in the breast tissues. Diagnosis of these lesions at the early stage is a very difficult task as the cancerous lesions are embedded in normal breast tissue structures. This paper proposes a supervised machine learning algorithm - Differential Evolution Optimized Wavelet Neural Network (DEOWNN) for detection of tumor masses in mammograms. Differential Evolution (DE) is a population based optimization algorithm based on the principle of natural evolution, which optimizes real parameters and real valued functions. By utilizing the DE algorithm, the parameters of the Wavelet Neural Network (WNN) are optimized. To increase the detection accuracy a feature extraction methodology is used to extract the texture features of the abnormal breast tissues and normal breast tissues prior to classification. Then DEOWNN classifier is applied at the end to determine whether the given input data is normal or abnormal. The performance of the computerized decision support system is evaluated using a mini database from Mammographic Image Analysis Society (MIAS). The detection performance is evaluated using Receiver Operating Characteristic (ROC) curves. The result shows that the proposed algorithm has a sensitivity of 96.9% and specificity of 92.9%.

Logic Programming and Artificial Neural Networks in Breast Cancer Detection

“…A perusal of Table 3 shows that the sensitivity ranges from 96.6% to 100%, while the specificity ranges from 94.3% to 95.9%. The sensitivity of the proposed model is higher than the reported in literature for medical imaging diagnosis, ranging from 70.21% to 94.17% [13,14,15]. PPV ranges from 80.0% to 84.8%, while NPV ranges from 99.2% to 100%.…”

“…Some general computer-aided diagnostics systems have been presented based on Kohonen's self-organizing map [5], neuro-fuzzy approach [6,7], support vector machines [8], Artificial Neural Networks (ANNs) [9] ANNs combined with techniques for reducing the dimension of initial database like association rules [10], sequential forward selection, sequential backward selection, and principal component analysis [11], or clustering [12]. Other authors have developed computer-aided diagnostics systems combining different methodologies like genetic algorithms and ANNs [13] or swarm intelligence and wavelet neural networks [14,15].…”

Foundation and methodologies in computer-aided diagnosis systems for breast cancer detection

“…A Particle Swarm Optimized Wavelet Neural Network (PSOWNN) method proposed in Dheeba et al (2014[34]) to classification mass on mammogram images. The performance measures compare with Swarm Optimized Neural Network (SONN) (Dheeba and Selvi, 2012[31]) and Differential Evolution Optimized Wavelet Neural Network (DEOWNN) (Dheeba and Selvi, 2012[32]) illustrated that enhanced accuracy, sensitivity and specificity has been achieved by PSOWN method.…”

A hybrid differential evolution algorithm for parameter tuning of evolving spiking neural network

“…The major advantage of using EAs is its ability to adapt itself to a varying environment (Fernandez Caballero et al, 2010). It is very common to use DE optimiser in many classification models like ANN (da Silva et al, 2010;Mineu et al, 2010), wavelet neural network (Dheeba and Selvi, 2012) and support vector machine (SVM) (Zhou et al, 2007). However, DE has not as yet been applied for ESNN to optimise pre-synaptic neurons.…”