Brain tumor detection from MR images: Image processing, slicing and PCA based reconstruction

In this paper, a novel algorithm is developed to feature out tumor from diseased brain Magnetic Resonance (MR) images. In this work, based on a study of quality parameter comparison of two filters, adaptive median filter is selected for de-noising the images. Image slicing and identification of significant planes are done. Logical operations are applied on selected slices to obtain the processed image showing the tumor region. A novel image reconstruction algorithm is developed based on the application of Principal Components Analysis (PCA). This reconstruction algorithm is applied on original raw images as well as on the processed images. Results of this work confirm the sole efficiency of the developed image processing algorithm to detect brain tumor. For this work randomly chosen 20 normal brain MR images and 20 brain tumor MR images are considered. Also in this work, statistical significance testing is carried out to justify the uniformity of population means of the processed output. Finally normal and processed outputs are compared.