Segmentation and compression of 2D brain MRI images for efficient teleradiological applications

Brain tumor is an unusual or abnormal growth of tissue in the brain or central spine that can disrupt proper brain function. Normally, the cells in body age, die, and are replaced by new cells. With cancer and other tumors, this cycle is disrupted. According to research and surveys there will be nearly 70,000 new cases of primary brain tumors will be diagnosed every year. More than 4,600 children between the ages of 0-19 will be diagnosed with a brain tumor every year. There are more than 120 types of brain tumors. So it has become more essential to properly detect and cure these type of tumors and those tumors are usually diagnosed by experts who may reside at different locations. Tele-radiology is the process electronic transmission of radiological images from one place to another for the purpose of interpretation and consultation. Since image transmitted has very precious information usual compression technique cannot be applied. In this paper we propose a new cost effective, simple iterative thresholding technique for the segmentation of brain tumor and to separate it from non region of interest. Non region of interest is compressed using simple enhanced DPCM and Huffman coding and the uncompressed tumor along with compressed non ROI, are sent across network it results in reduced bandwidth and less storage space.