Females are affected by BC (Breast Cancer) more than any other type of cancer. BC has caused more deaths than any other diseases such as tuberculosis or malaria according to WHO (World Health Organization). The mortality rates due to BC in women are high making it a candidate for early detection for prevention and cure. Diagnosing BC is a complex task as it is interleaved with normal breast tissues. Image processing methods have been proposed for detecting BC, yet better segmentation methods are required. Fuzzy based approaches provide optimal results in segmenting BC images. Hence, this work uses Fuzzy approach combined with ResCNN (Recurrent Residual Convolution Neural Network) which is the optimized by a modified GA (Genetic Algorithm). The proposed ERResCNN classifying results in detecting BC from images is accurate and efficient in comparison to other methods.

Additive White Gaussian Noise (AWGN), Fuzzy Clustering by Local Approximation of Membership (FLAME), Enhanced Recurrent Residual Convolution Neural Network (ERResCNN), Hybrid Genetic Grey Wolf Algorithm (HGGWA), Mammographic Image Analysis Society (MIAS)