Abstract

Abstract: Lung cancer takes more lives every year than the combined numbers of breast, colon, and prostate cancer.Diagnosis in the early stage increases the chance of survival of the patient. CT scan plays an important role in the detectionof lung cancer and improved results than X-ray as CT scan is more powerful and sophisticated X-ray as it gives a 360-degreeview of the organs. Due to this more number of CT scans are done and hence the radiologist has to evaluate all of these andthis hampers the quality of diagnosis. Many SVM models have been used for nodule detection in Chest CT scan images but the accuracy has been more dependent on the preprocessing of the image for better accuracy, which consumes a lot of time. The purpose of this project is to address this aim and implement and train the SVM model to classify lung CT images into the nodule and non-nodule class.Keywords—Medical Image Classification, SVM , Lung Cancer