Ischemic Stroke detection using Image processing and ANN

Ischemic stroke is a condition in which brain stops working due to lack of blood supply resulting in death of brain cells. Magnetic Resonance Imaging is widely used to detect Ischemic Strokes in brain. This paper gives an automated algorithm to detect the stroke using Image processing techniques. The algorithm consists of six phases. Data in the form of MRI images is collected in first phase. The preprocessing is performed including filtering on the raw data collected. Midline is traced in third phase for acquiring a symmetrical image. It is followed by bifurcation of image in fourth phase. Finally the image quality matrix is formed for texture analysis in fifth phase and neural network is applied in sixth phase for classification of normal and infected brain. The advantage is that the strokes can be detected in its early stage. The algorithm proposed is simple, efficient and less time consuming. The efficiency is found to be 98%.