Deep Learning Classification Method to Detect and Diagnose the Cancer Regions in Oral MRI Images

Abstract

The paper proposes deep learning algorithm used to classify the oral images into either normal or abnormal
images. The cancer regions are segmented using morphological operations. The segmented cancer regions
are further diagnosed into ‘Mild’ or ‘Severe’ using deep learning algorithm. The main advantage of the deep
learning algorithm is that it requires minimum number of oral images for both classification and diagnosis
stages of the proposed work. In this paper, the total number of cancers affected oral images used is about
160 and the proposed oral cancer detection system using CNN classification approach classifies 159 cancer
affected oral images correctly and achieves 99.3% of detection rate.