In a landmark paper 4 , the authors reported an extensive evaluation using multiple neuroimaging datasets analyzed by fourteen different registration tools, including the Symmetric Normalization (SyN) algorithm 5 , and found that “ART, SyN, IRTK, and SPM’s DARTEL Toolbox gave the best results according to overlap and distance measures, with ART and SyN delivering the most consistently high accuracy across subjects and label sets.” Participation in other independent competitions 6 , 7 provided additional evidence of the utility of ANTs registration and other tools 8 , 9 , 10 , Despite the extremely significant potential of deep learning for image registration algorithmic development 11 , ANTs registration tools continue to find application in the various biomedical imaging research communities.
1
—
—