| Home

Overview


Original Research

IDENTIFICATION OF OROPHARYNGEAL CANCER USING MACHINE LEARNING MODEL

KUMAR R 1, Dr S PAZHANIRAJAN 2, and Dr S UMAMAHESWARAN 3

Vol 17, No 06 ( 2022 )   |  DOI: 10.5281/zenodo.6637102   |   Author Affiliation: Research Scholar, Department of Computer Science and Engineering, Faculty of Engineering and Technology, Annamalai University, Chidambaram 1; Assistant Professor, Department of Computer Science and Engineering, Faculty of Engineering and Technology, Annamalai University, Chidambaram 2; Professor, Department of Computer Science and Engineering, MVJ College of Engineering, Bangalore 3.   |   Licensing: CC 4.0   |   Pg no: 109-132   |   To cite: KUMAR R, Dr S PAZHANIRAJAN, and Dr S UMAMAHESWARAN. (2022). IDENTIFICATION OF OROPHARYNGEAL CANCER USING MACHINE LEARNING MODEL. 17(06), 109–132. https://doi.org/10.5281/zenodo.6637102   |   Published on: 11-06-2022

Abstract

Oropharyngeal cancer is a main worldwide health problem accounting for 606,520 deaths in 2020 and it is most predominant in middle- and low-income nations. The most important purpose is being carried out this research is to find the Oropharyngeal Cancer Lesions affected region in the tongue images. The combined diagnostic framework with hybrid features selection techniques is utilised in this study to discover the traits that assist the most to the detection of Oropharyngeal cancer, reducing the amount of features obtained from a range of patient information indirectly. Using hybrid feature selection, twenty- five qualities were reduced to 14 features. Support Vector Machine.Following that, four classifiers were employed to forecast the identification of patients with Oropharyngeal cancer: Updatable Multilayer Perceptron, Nave Bayes, and K- Nearest Neighbors Furthermore, after adding feature subset choice with SMOTE during preprocessing stages, the SVM surpasses other machine learning algorithms, according to the findings. Using the initial data gathered in this study, a hybrid classifier algorithm was assessed to detect Oropharyngeal cancer lesions and features like color, texture, and geometry were extracted. Our initial findings establish support vector machine has the probable to challenge this stimulating task.


Keywords

GVF algorithm, Oropharyngeal Cancer Lesions, hybrid classifier algorithm, support vector machine.