Enhancement of MRI Images Using Optimal Filter Topology

Now a day, the medical images play a vital role in detection and diagnosis of diseases. Magnetic Resonance Imaging is considered as the safest tool and hence it is commonly employed for diagnosis of brain related problems. However, the images obtained from MRI scans are affected by different type of noises like Salt and pepper noise, Gaussian noise and Speckle noise. These noises will deteriorate the quality of the images. Image denoising is the only solution to this problem. In this regard, this work formulated a new filtering topology to denoise the noises present in MRI brain images and also compared its performance with existing three filters namely Median, Lee and Frost filters over the brain images. Hence, to determine the efficiency of these filters, Error Sensitivity Measure parameters like Mean Squared Error, Peak Signal to Noise Ratio and Structural Similarity Index are calculated. The experiments have been performed over three datasets of brain images. From the analysis, it is proven that for the all kinds of noises, the proposed algorithm exhibits higher performance metric than the other filters. This algorithm can be used for images obtained from various smart electronic devices.