Knowledge-based Segmentation: Using Simultaneous Shape Priori and Histogram Information to Segment Brain Structures

N. Batmanghelich (Iran), H. Soltanian-Zadeh (Iran/USA), and B.N. Araabi (Iran)


Brain Structural segmentation, Histogram information, Shape priori, Medical image analysis, Magnetic resonance imaging (MRI)


In this paper, we propose a new method integrating both a priori shape information and our knowledge about gray levels of the desired structure. We describe an approach inspired from tracking to deal with non-uniform gray levels. We define focus region to consider both interior and exterior of the desired object. We utilize signed distance function to consider shape information. Embedding a priori shape and gray level knowledge in a statistical platform, we use correlation between changes in shape and histogram to improve the results. Our method successfully segments Thalamus and other brain structures.

Important Links:

Go Back