Abstract: This paper deals with detection of Ischemic stroke which happens because of blockage in arteries of human brain. The obtained input MRI images are pre-processed and enhanced using filters and image processing techniques. The line of symmetry of brain is traced using an algorithm after applying watershed transform. Based on this, the image features for the brain’s right and left side are calculated by means of the Gray Level Co-occurrence Matrix. Wavelet transform is applied for the enhanced image. The image features from the GLCM and the significant coefficients of wavelet transform are given as the input vector to the neural network to classify the MRI images into abnormal and normal. The lesion regions from the abnormal images are segmented using the intensity difference of the image and the lesion region. It was observed that the neural network has an efficiency of 90%.Finally; the neural network is implemented on Field Programmable Gate Array Spartan3E using system generator and Xilinx design suite14.3.
Keyword: Ischemic stroke, Gray Level Co-occurrence Matrix (GLCM), Artificial Neural network (ANN), Filed Programmable Gate Array (FPGA).
Title: EFFICIENT DETECTION OF ISCHEMIC STROKE FROM MRI IMAGES USING WAVELET TRANSFORM
Author: Dr. Menaka R, Rohini. S
International Journal of Computer Science and Information Technology Research
ISSN 2348-120X (online), ISSN 2348-1196 (print)
Research Publish Journals
