Automatic Detection of Brain Tumor using NSR Filter and K-means Clustering

The motive of this work is to come up with an automatic detection of brain tumor from Magnetic Resonance Imaging (MRI) using computer-aided segmentation method. Pre-processing of the image is done using Noise to signal ratio (NSR) Filter. Wavelet filtering is used for decomposing the image. The image is decomposed into four bands, and the one with the HH band eliminated is selected for the segmentation process. Segmentation of the pre-processed image is done using K-means clustering. The result of the clustering shows two images, one with the tumor areas, and the other without the tumor. The automatic segmentation makes detection of the tumor much easier and more accurate. Also, the area of the major portion of the tumor is calculated.