Health alert system to detect oral cancer

Abstract

Cancer is a deadly disease in which body's cells start dividing enormously and are able to spread in to other tissues. Oral cancer is a kind of cancer, where some abnormal lesions or patches will appear in the oral cavity. Since it is difficult to identify it in the initial stages, it has one of the worst survival rates. The proposed health alert system can help the patients in identifying the disease in the initial stage itself. It accepts the Computerized Tomography (CT) scanned images of the cancer affected region and can detect the presence of malignancy. The obtained CT image is preprocessed using Adaptive Median Filter and the features such as Texture, Shape, Water Content, Linear Binary Pattern (LBP), Histogram of Oriented Gradients (HOG) and Gray Level Co-occurrence Matrix (GLCM) are extracted from preprocessed images. The redundant features are omitted using features election process and Support Vector Machine (SVM) classification algorithm is used to classify it as benign or malignant. Proposed Health Alert system has an accuracy of 97%.