MRI Disadvantages

potentially overlapping parts such as WM, GM and CSF.MRI is one of the common ways to visualize brain structure. Automatic segmentation of MR images is very useful for research and clinical study of much neurological pathology. The MRI scan is more reliable than CT scan for diagnosis because it does not affect the human body as it does not use any kind of radiation. MRI shares a common advantage with CT of high spatial resolution images but without ionizing radiation exposure. It possesses good contrast resolution for different tissues.

A huge literature is devoted to brain segmentation from 3D MRI data. Indeed segmentation methods can deal with a large number of purposes:

→ Extraction of one or several, specific or small structures.

→ Extraction

The large balloon force causes the contour to pass through the weak edges of the object. If, however, the balloon force is not large enough, the contour cannot pass through the narrow part of the object. The disadvantage of the edge-based model is the failure to detect the boundaries when the initial contour is far from the desired object boundary.There are several advantages of using Region-based models over the edge-based models. For example in Region-based models, each ROI is identified using a certain region descriptor to guide the motion of the active contour. These models utilize the statistical information inside and outside the contour to handle the evolution of the curve, and are independent of edge information. Therefore, these models have better performance over the images that have weak edge boundaries, and it is also less sensitive to the initial position of the contours. The popular region-based method active contour models [27] depend on the intensity homogeneity in each of the regions to be