Optimized CAD System for Breast Cancer Detection with Tabu Search and RNN

Breast cancer stands as the second leading cause of cancer-related fatalities among women and is the most prevalent form of noncutaneous malignancy worldwide, affecting more than one in ten women globally. Ongoing efforts in the development of novel approaches and strategies are dedicated to enhancing breast cancer prevention, elevating survival rates, and reducing mortality. This study introduces an innovative technique for breast cancer detection and classification known as Tabu Search and Kernel Principal Component Analysis (TKPCA). In implementing TKPCA, a Recurrent Neural Network (RNN) is utilized to construct a classifier named TKPCA-RNN, proficient in distinguishing between benign and malignant tissue within medical images. The Wisconsin Breast Cancer Dataset (WBCD) and Wisconsin Diagnosis Breast Cancer (WDBC) are chosen as fundamental breast cancer databases sourced from the UCI benchmark repository. Notably, experimental findings validate the superiority of our proposed TKPCA method over established classifiers, representing a significant breakthrough in breast cancer research.