DRMIME: Differentiable Mutual Information and Matrix Exponential for Multi-Resolution Image Registration
Proceedings of the Third Conference on Medical Imaging with Deep Learning, PMLR 121:527-543, 2020.
We present a novel unsupervised image registration algorithm using mutual information (MI). It is differentiable end-to-end and can be used for both multi-modal and mono-modal registration. The novelty here is that rather than using traditional ways of approximating MI which are often histogram based, we use a neural estimator called MINE and supplement it with matrix exponential for transformation matrix computation. The introduction of MINE tackles some of the drawbacks of histogram based MI computation and matrix exponential makes the optimization process smoother. Our use of multi-resolution objective function expedites the optimization process and leads to improved results as compared to the standard algorithms available out-of-the-box in state-of-the-art image registration toolboxes empirically demonstrated on publicly available datasets.