Improved breast cancer detection using fusion of bimodal sonographic features through binary firefly algorithm

Abstract

ABSTRACT Breast cancer is a major health issue and causes a larger number of deaths in women. As per GLOBOCAN statistics, breast cancer has surpassed lung cancer in 2020 with 2.3 million anticipated new cases which is 11.7% of total cancer cases. Sonography is used in addition to mammography to detect, describe and locate breast lesions effectively. Elastography and Echography are widely used sonographic techniques as they provide different and distinctive information for identifying breast diseases. To obtain improved detection performance, this work focuses on the fusion of Local Binary Pattern (LBP) texture features from ultrasound elastogram and echogram images followed by feature selection using Binary Firefly Algorithm (BFA) with Optimum Path Forest (OPF) classifier accuracy as a fitness function for feature selection. This method produces 97.3% accuracy, 96.2% sensitivity, 98.2% specificity, 97.3% precision, 96.2% F1 score, 94.71% Balanced Classification Rate, and Mathews Correlation Coefficient of 0.884 outperforming existing works.