A novel framework for the segmentationof mrinfant brain images

This paper introduces a novel adaptive atlas-based framework for the automated segmentation of different brain structures from infant magnetic resonance (MR) brain images. The proposed framework provides a more accurate segmentation of different infant brain structures in the isointense age stage (6-12 months) by integrating diffusion tensor imaging (DTI) image features (e.g., fractional anisotropy (FA)) in the segmentation procedure. The input to the proposed system is the medical scans of the infant brain, i.e., 4D diffusion weighted images (DWI). The input brain first undergoes a quality control procedure to remove scan artifacts, and correct motion and eddy current distortions, followed by brain extraction, in which any non-brain tissues are removed. Then, specific DTI features are extracted, and fused to guide the segmentation process to produce the final segmented brain tissues. The high accuracy of the proposed segmentation approach was confirmed by testing it on 10 in-vivo diffusion weighted infant MR brain data sets using three metrics: the Dice coefficient, the 95-percentile modified Hausdorff distance, and the absolute volume difference.