Anatomical Model-Guided Segmentation of Brain MR Image Sequences

Abstract

This paper presents a method for segmentation of human brain magnetic resonance (MR) image sequences based on a 3D human brain model (triangulated mesh). The brain model is composed of four components, namely, cerebrum, cerebellum, brain stem and pituitary gland. Synthesized image sequences are extracted from the model at regular intervals for sagittal and coronal views as done in MR imaging. To align a series of real MR images with these synthesized cross-sections, an efficient dynamic programming based computational technique has been used that obtains the optimal synthesized cross-section sequence corresponding to the series of MR images. For automatic segmentation of anatomical structures from the MR images, each aligned synthesized cross-section is overlaid on the corresponding physical MR image by carrying out appropriate geometric transformation. This transformation produces model guided boundaries for four segments corresponding to cerebrum, cerebellum, brain stem and pituitary gland. Subsequently, these initial contours are further refined by the method of active contouring, which provides segmentation of 3D MR images into the above mentioned four parts. The proposed method compares well with the recently proposed Charged Fluid Model (CFM) based approach and level set segmentation method in terms of accuracy at a significantly lower computational cost.