INTELLIGENT CLASSIFICATION MODEL FOR BREAST CANCER DIAGNOSIS USING OPTIMIZED FEATURE SELECTION ALGORITHMS

Abstract

Breast cancer is one of the most common fatal diseases affecting women whose incidence rate is increasing worldwide. Early detection is the only approach to increase the survival rate because the stage of cancer at the time of detection determines how successfully it may be treated. Recent technological improvements in early screening techniques have decreased the death rate. Breast cancer is the second most frequent malignant tumor in the world. Early findings of breast cancer can significantly improve treatment effectiveness. Manual methods of breast cancer diagnosis are prone to human fault and inaccuracy, and they take time. A computer-aided diagnosis can assist radiologists in making better choices by overcoming the disadvantages of manual methods. One of the significant steps in the breast cancer diagnosis process is feature selection. In recent decades, many studies have proposed numerous hybrid optimization methods to select the optimal features in the breast cancer detection system. However, many hybrid optimization algorithms are trapped in local optima and have slow convergence speed. Thus, it reduces the classification accuracy. For resolving these issues, this work proposes a hybrid optimization algorithm that combines the grasshopper optimization algorithm and the crow search algorithm for feature selection and classification of the breast mass with multilayer perceptron. The simulation is experimented with using MATLAB 2019a. The efficacy of the proposed hybrid grasshopper optimization-crow search algorithm with multilayer perceptron system is compared to multilayer perceptron-based algorithms of enhanced and adaptive genetic algorithm, teaching learningbased whale optimization algorithm, butterfly optimization algorithm, whale optimization algorithm, and grasshopper optimization algorithm. From the results obtained, the proposed grasshopper optimizationcrow search algorithm with the multilayer perceptron method outperforms the comparative models in terms of classification accuracy (97.1%), sensitivity (98%), and specificity (95.4%) for the mammographic image analysis society dataset.