ABSTRACT
Oral Cancer is a primary disease which affects the middle age and elderly age group people. When healthy cells undergo mutations, they develop gradually into a mass known as cancer. Cancer can be divided into two types: malignant and benign. The cells in malignant tumors multiply and spread to other parts of the body, whereas benign tumors do not spread. Oral Squamous Cell Carcinoma (OSCC) is a highly prevalent oral cancer that affects more than 90% of the head and neck areas, than other parts of the body. At present, the pathologist finds it difficult to identify the histopathological variants of OSCC. To address this problem, the Computer Aided Diagnosis (CAD) paradigm was developed to assist pathologists in making decisions. However, early detection and prevention of oral cancer is vital, but it is a time-consuming task in medical image processing. Therefore, it is essential to find an effective diagnostic procedure for detecting cancer at the earlier stage. The proposed work aims at developing an effective deep learning model to identify the histopathological variants of OSCC. In the proposed work, convolutional layers and filters size have been altered to attain the accuracy. 2To evaluate the performance of the proposed models, a real time dataset is used which shows a highest accuracy of 93.65% to 96.83% compared to other models.
