A Comparative Study of Deep Learning Based Deformable Image Registration Techniques

ISMRM 2021 presentation - May 2021

Full abstract is available here:

Synopsis:
Deep learning algorithms have been used extensively in tackling medical image registration issues. However, these methods have not thoroughly evaluated on datasets representing real clinic scenarios. Hence in this survey, three state-of-the-art methods were compared against the gold standards ANTs and FSL, for performing deformable image registrations on publicly available IXI dataset, which resembles clinical data. The comparisons were performed for inter-modality and intramodality registration tasks; though in all the respective papers, only the inter-modality registrations were exhibited. The experiments have shown that for intramodality tasks, all the methods performed reasonably well and for inter-modality tasks the methods faced difficulties.

Twitter: soumick1993