Coyote–Wolf optimization-based deep neural network for cancer classification using gene expression profiles

Abstract

Cancer is a deadly disease that affects millions of people all over the world, which stimulates unrestricted segmentation of the cell in the affected tissue. The prior determination of cancerous cells renders on-time healthcare service to the affected persons, which promotes easier life-saving. Hence, there is a need for automatic cancer classification methods. Though there are so many conventional classification methods to determine the cancer cells, these methods fail due to their training issues. In this research, a classification model is developed, named as Coyote–Wolf Optimization-based Deep Neural Network (CoWo-DNN), for the classification of cancerous cell from the normal tissues. The proposed CoWo-DNN for the classification of cancer cell utilizes gene expression data, which is log-transformed for effective processing. The comparative evaluation of the proposed CoWo-DNN with the conventional methods demonstrates the supremacy of the proposed method in terms of the performance parameters such as precision rate, accuracy, recall, [Formula: see text]-measure and TRP. The proposed CoWo-DNN achieves the maximum accuracy of 91.8%, precision of 93.7%, recall of 89.2% and [Formula: see text]-measure of 86.4% in the case of breast cancer, and the accuracy of 96.2%, precision of 93.33%, recall of 97.8% and [Formula: see text]-measure of 98.8% in the case of colon cancer.