Performance Study on Brain Tumor Segmentation Techniques

Abstract

The core purpose of this paper is to compare the efficiency of two methods which are used to segment the brain tumor images. Brain tumor segmentation is an essential procedure for diagnose tumor in earlier stage. Generally, in medical imaging, segmentation of brain tumor images is executed manually in clinical practice. It is a time taking process and so manual brain tumor detection is complicated. To overcome this drawback an automatic brain tumor segmentation method is needed. Among several automatic brain tumor segmentation approaches, this paper investigates two methods and their performances are compared to observe the best method for brain tumor partition. The first method segments the brain tumor images using Local Independent Projection based Classification (LIPC). The second technique uses wavelet and Self Organization Map (SOM). To analyse the performance of these methods, several performance metrics are used. This work utilizes Precision Rate, Recall Rate, F-Measure, Sensitivity and Specificity to examine the efficiency. From the experimental outcomes it is shown that the Wavelet based SOM approach performs superior than the other method.