Machine Learning Method for Pancreatic Cancer Detection using Naïve Bayes and Decision Tree Algorithm

Abstract

Machine Learning is the study of algorithms and application of artificial intelligence. Artificial Intelligence is said to be the superset of machine learning. It aims to develop those programs which can learn and improves it upon increasing experience. It is designed to learn by itself. The aim is to detect pancreatic cancer using machine learning approach. Pancreas is responsible for secreting insulin which helps to control the blood glucose level in the human body. The paper aims to detect pancreatic cancer with the help of machine learning. The tumor is detected using image processing and is to be detected at the premature stage so that proper medication and treatment can be provided to increase the survival rate of the patient. The MRI image of pancreas obtained after MRI scan will be preprocessed and its noise is removed. The segmentation of MRI images will be performed using FCM algorithm. The tumor present in the image will be detected with the help of morphological process and multi clustering model. After Segmentation the image will be divided into various regions. With the help of the hybrid technique the primary and secondary regions are compressed and are used for telemedicine application. DWT is used for DE noising the image. GLCM features are extracted. The image then compared with the database images of pancreatic tumors and is classified as abnormal and normal with the help of BPN based classifier. The image is classified into abnormal and normal. The malignant image is considered as abnormal. The abnormal image is then segmented using SFCM and tumor part is clustered. After clustering the tumor part validation about the presence of pancreatic cancer is given.