A BRIEF REVIEW OF SEGMENTATION METHODS FOR MEDICAL IMAGES

Abstract

For medical diagnosis and laboratory study applicat ions we cannot directly use image that are acquired and detect the disorder because it is not efficient and unrealistic. These images need processing and extracting portions from them that can be used for further study or diagnosis. The main goal of this paper is to give overview about segmentation method s that are used for medical images for detecting the edges and based on this de tection the disease prediction and diagnosis is don e. There are a lot of tools available for this purpose such as STAPLE and FreeS urfer whole brain segmentation tool etc. Some of th ese methods are semiautomatic i.e. they require human intervention for their completion and some of them are automatic. Th e methods are totally divided into four types namely, edge based segmenta tion, region based segmentation, data clustering an d matching. The aim of segmenting medical images is that to detect the ROI and diagnose for a disease based on the detected p art. Segmentation is partitioning a image into meaningful regions based upon a specific application. Generally segmentation can be based on the measurements like gray level, color, texture, motio n, depth or intensity. Segmentation is necessary in two situations, namely, setoff segmentation i.e. when the object to be segment ed is interesting in itself and can be used separat ely for further studies, and secondly concealing segmentation i.e. suppose there are some noise or vision blockers in the image, so this segmentation aims at deleting the disturbing elements in an image. This paper focuses only on the working of different meth ods that are used for segmentation whether they segment well or poor.