A comparative analysis of MRI and CT brain images for stroke diagnosis

Abstract

The advances in medical imaging have led to new multi dimensional imaging modalities that have become important clinical tools in diagnostic radiology. The two modalities capable of producing multidimensional images for radiological applications are Computed Tomography (CT) and Magnetic Resonance Imaging (MRI). Normally the first radiologic examination in suspicion of stroke is brain CT imaging. But MRI provides high resolution images with excellent soft tissue characterization capabilities. A comparative analysis for the diagnosis of stroke on CT and MRI images is presented in this paper. The algorithm proposes the use of Digital Image processing tools for the identification of infarct and Hemorrhage in human brain. Preprocessing of medical images is done by median filtering. Segmentation is done by Gabor filtering and seeded region growing algorithm. The method is demonstrated on the CT and MRI brain images having different types of infarcts. The results of the method are evaluated visually. The proposed method is promising for detection of stroke and also establishes that MRI imaging is superior to CT imaging in stroke detection.