A Comparative Analysis of Machine and Deep Learning Models for Cervical Cancer Classification

Abstract

Machine learning and deep learning algorithms have made significant contributions to healthcare industry. These algorithms aid in improving the accuracy and reliability of diagnosis of various diseases. Moreover they also assist medical practitioners in prognosis thus reducing the time and complexity of work. But on the other hand we also have certain diseases for which there is very less awareness among people. One such deadly disease is cervical cancer. It is a life threatening disease but it can be prevented by early prognosis and treatment. However most of the countries have no effective screening techniques for this type of cancer. In this study we incorporate various deep learning and machine learning models for classification of normal and cancerous cervical cells as well as their types and a comparative analysis of performance measures such as accuracy, sensitivity, specificity and F1 score is made.