A CAD System for Automatic Classification Of Brain Strokes in CT Images

Brain stroke is one of the most important brain damages that if don’t diagnose in first hours after happening, may lead to death of patient. There are different modalities for brain imaging but Computed Tomography(CT) is the most common, due to its less cost, less imaging time, more availability, stroke early detection and etc. According to current advances in technology of CT scanners, many images are produced per each patient and hence the radiologist detection error rate has been raised. In these conditions, Computer-Aided Diagnosis (CAD) systems can help radiologists to diagnose brain strokes rapidly and precisely. In this paper, we present a CAD system to classify brain CT images into hemorrhagic, ischemic and normal. The proposed CAD system applies Wavelet Packet Transform (WPT) to decompose input image into sub-images and then extracts texture features from sub-images using GLCM. The proposed method is evaluated on a dataset of 90 brain CT images and resulted in classification accuracy of 90%.

کلیدواژه ها:

Brain stroke ، Discrete Wavelet Transform ، Texture feature extraction ، Wavelet Packet Transform