Hello Elmira, this is Suresh, from my knowledge i would like to give you few points on Segmentation and Classification which will be helpful to you i think so, please go through these,

• Segmentation means to divide up the image into a patchwork of regions, each of which is “homogeneous”, that is, the “same” in some sense

– Intensity, texture, colour, …

• Classification means to assign to each point in the image a tissue class, where the classes are agreed in advance

– Grey matter (GM), White matter (WM), cerebrospinal fluid (CSF), air, … in the case of the brain

• Note that the problems are inter-linked: a classifier implicitly segments an image, and a segmentation implies a classification

Classification of brain MRI images

• The “labels” we wish to assign to objects are typically few and known in advance

– e.g. WM, GM, CSF and air for brain MRI

• objects of interest usually form coherent continuous shapes

– If a pixel has label c, then its neighbours are also likely to have label c

– Boundaries between regions labelled c, d are continuous

• Image noise means that the label to be assigned initially at any pixel is probabilistic, not certain

One way to accommodate these considerations is Hidden Markov Random Fields