Design of A Decision Support System for Detection of Oral Cancer using Matlab
N. Kripa, R. Vasuki1, Prasath Alias Surendhar2

1Research Scholar, Professor, Research Scholar, Department of Biomedical Engineering, Bharath Institute of Higher Education and Research Chennai (Tamil Nadu), India.
2Prasath Alias Surendhar, Research Scholar, Department of Biomedical Engineering, Bharath Institute of Higher Education and Research Chennai  (Tamil Nadu), India.

Manuscript received on 18 June 2019 | Revised Manuscript received on 25 June 2019 | Manuscript published on 30 June 2019 | PP: 795-792 | Volume-8 Issue-5, June 2019 | Retrieval Number: E7243068519/19©BEIESP
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: Oral squamous cell carcinoma (OSCC) represents the predominant neoplasm of the neck and head region, particularly featuring aggressive nature with unfavorable prognosis which is associated along with it. In this research the support system detects and classifies the oral squamous cell carcinoma [1]. The algorithms GLCM and Feed Forward Neural Network (FNN) are utilized to predict the occurrence of oral cancer through the analysis using MATLAB. We try to systematically study and analyze the basis of oral cancer evolvement by the image processing technique using neural network toolbox in Matlab.Images of normal and abnormal images were collected and the feature extraction for all these images was carried out using GLCM. These features extracted were compared and selected accordingly for the classification. The images were initially classified based on thresholding according to variations shown in the images. Later a Feed Forward Network (FNN) was developed and trained to predict the occurrence of oral squamous cell carcinoma [2]. The values of the features selected were given as input to train based on this training the classifier gives the output as cancer or normal image. The Results were obtained as our initial goal and it was observed that the accuracy in the results is better when we use FNN classifier than thresholding.
Keywords: Oral Squamous Cell Carcinoma (OSSC), Feed forward Neural Network, MATLAB, Gray-Level Co-Occurrence Matrix (GLCM), Oral Cancer, Feature Extraction.

Scope of the Article: Computer Network