Detection of Cervical Cancer Using Machine Learning Techniques

Abstract

Accurate and efficient detection of cervical cancer at an early stage can be crucial for the survival of a patient. Manual intervention in the process results in costly and time consuming procedures and introduces the risk of manual errors. An effective solution to these drawbacks is automation of the process using machine learning techniques to train neural networks. In this paper, we have presented a survey of the research conducted in the area. The use of convolutional neural networks (CNN) can be frequently observed as they are proven to be effective for images. These networks are based on transfer learning models which have given good results. Other than these, the use of support vector machines (SVM) can frequently be observed. Various pre-processing methods like segmentation and feature extraction plays an important role in all of the papers surveyed.