Detection and Evaluation of Cervical Cancer by Multiple Instance Learning

Abstract

In terms of frequency, cervical cancer is the fourth most common cause of cancer-related deaths in women worldwide. Early diagnosis of cervical intraepithelial neoplasia (CIN) can significantly improve patient survival chances. This study intends to develop a cutting-edge deep learning architecture to perform accurate CIN recognition. Here, the ResNet50-based Convolution Neural Network (CNN)-based transfer learning technique is used. The cervical cancer dataset, assembled using some images from the internet and some that have been enhanced is trained using CNN. CNN performs well and correctly forecasts whether the disease will be favorable or negative.