Breast cancer detection in its early stages with spider monkey optimization using the MIAS dataset
Kanchan Warkar, Sandhya Dhage, Ashish Dandekar, Bhakti Thakre · 2024
Millions of women around the world have a higher chance of survival thanks to early and accurate breast cancer diagnosis. A key component of detection is computer-aided diagnosis, which relieves medical experts of the load of precise detection. A number of machine learning and deep learning algorithms were used in the computer-aided diagnosis of breast cancer. This research suggests a feature extraction and optimization approach for the identification of breast cancer. The suggested methodology used stationary wavelet transform techniques to extract features. An optimization algorithm called spider-monkey was used to extract the features. A dynamic population-based metaheuristic function called “spider-monkey optimization” can improve the feature optimization of medical pictures. We suggested a neural network (NN)-based classifier encoder deep learning for the identification of breast cancer. Breast cancer diagnosis accuracy is increased by the suggested deep learning-based classifier based on a neural network encoder. MATLAB 2018R software was used to simulate the suggested technique. The MIAS dataset was used by the algorithm for the valuation. The effectiveness of the suggested method in comparison to other breast cancer algorithms, including CNN, Ransom-RF, SVM, and NN.