Classification of normal and abnormal bladder CT images using support vector machine
M. N. Helin, Galuh Ayu Treswari, M R A Gani, Prawito Prajitno, Djarwani Soeharso Soejoko · AIP conference proceedings · 2022
Bladder cancer is the 10th most commonly diagnosed cancer worldwide, and the 13th in Indonesia, according to database providing global cancer statistics and estimates of incidence and mortality (GLOBOCAN 2020). The gold standard in the diagnosis of bladder cancer is computed tomography (CT). However, the CT modality produces multiple images and each image has a different size, shape, and location of bladder cancer. Therefore, to improve early diagnostic accuracy from the image directly for each patient, Computer-Aided Diagnosis (CAD) can be an assistant or a tool for radiologist reinforcement in classifying normal and abnormal images. In this study, the CAD system was developed using the K-Nearest Neighbor (KNN) segmentation method, feature extraction based on Gray Level Co-Occurrence Matrix (GLCM), and normal and abnormal image classification using the Support Vector Machine. The data used in this study are 150 bladder CT images from Dharmais National Cancer Hospital, consisting of 75 normal images and 75 abnormal images. 100 images are used as training data, and 50 images are used as testing data. The results of CAD system performance in this study are in the form of the accuracy of 91% for training data and 88% for testing data.