Oral Cancer Detection Using Deep Learning

Abstract

Oral cancer is a very serious, complex, and common type of cancer. Oral cancer ranks eighth globally in terms of cancer incidence in India, with 130,000 deaths reported annually. The tumor affects the tonsils, salivary glands, neck, face, and mouth. Numerous methods, including screening procedures and biopsies—which entail taking a small sample of body tissue and analyzing it under a microscope—can be used to identify oral cancer. The disadvantage of cancer cells is that they are hard to identify and quantify. For this reason, digital processing technology will be employed in this study to identify and classify cancer cells that have affected the oral cavity. State-of-the-art technology and an in-depth learning algorithm can be employed for early detection and categorization. This work employs the Zernike Moment, wavelet features, and the bag histogram of directed gradients as three techniques for character extraction. After the characteristics are obtained, the best texture characteristic is chosen using the fuzzy particle swarm optimization technique (FPSO). In the end, these features were classified using the Faster Region-based Convolution Neural Network (faster RCNN) classifier. to evaluate the efficiency, error, recall rate, precision rate, and classification accuracy of the recommended approach.