Comprehensive Segmentation of Deep Grey Nuclei From Structural MRI Data

There is a lack of tools for comprehensive and complete segmentation of deep grey nuclei using a single software for reproducibility and repeatability. We present a fast, accurate, and robust method for segmentation of deep grey nuclei (thalamic nuclei, basal ganglia, amygdala, claustrum, and red nucleus) from structural T-1 MRI data at conventional field strengths. We leveraged the improved contrast of white-matter-nulled imaging by using the recently proposed Histogram-based Polynomial Synthesis (HIPS) to synthesize white-matter nulled images from standard T-1 and then use a multi-atlas segmentation with joint label fusion to segment deep grey nuclei. The method worked robustly on all field strengths (1.5/3/7T) and Dice coefficients >= 0.7 were achieved for all structures compared against manual segmentation ground truth. In conclusion, this method facilitates careful investigation of deep grey nuclei by enabling the use of conventional T-1 data from large public databases, which has not been possible hitherto due to lack of robust reproducible segmentation tools.