Anatomy Guided Hybrid Deformable Model for Reconstruction of Brain Cortex from MR Image

S. Saha, R.K. Chatterjee, S.K. Das, and A. Kar (India)


Magnetic resonance imaging, Image segmentation,Deformable model, Cortical reconstruction


This paper presents an Anatomy Guided Hybrid Deformable Model (AGHD) for fully automatic reconstruction of outer cortical surface of brain from MR image. Apart from its fully automatic nature, the algorithm requires tuning of the least number of parameters and avoids all kinds of assumption and approximation. This strength of the algorithm is a derivative of rich tissue specific information of the images acquired with signal attenuation from the gray matters. Using signal nulling effect the acquisition protocol has enhanced the intensity difference between white and gray matters in the reconstructed MR image. This leads to the generation of a histogram where pixel values of different anatomical structures are distributed around separate dominant modes. An algorithm for automated multilevel thresholding for partitioning specific modes into initial brain contour has been highlighted. Finally AGHD model has hybridized the essence of traditional “snake” model and the Generalized Gradient Vector Flow deformable contour with precise neuroanatomical guidance for accurate reconstruction of CSF/gray matter interface. The algorithm has been tested on a large dataset with great success and validated by a robust index with highly encouraging outcome.

Important Links:

Go Back