Plug-and-Play Priors for Reconstruction-based Placental Image Registration

TL;DR

This paper introduces a flexible deformable registration framework using plug-and-play priors with denoising functions, significantly improving alignment accuracy in noisy placental MRI images with large transformations.

Contribution

It develops a novel registration method integrating denoising-based priors, enhancing robustness to noise and large deformations in placental image registration.

Findings

Improved spatial alignment accuracy in low SNR 3D MRI images.

Demonstrated robustness across various denoising models.

Significant performance gains over existing registration methods.

Abstract

This paper presents a novel deformable registration framework, leveraging an image prior specified through a denoising function, for severely noise-corrupted placental images. Recent work on plug-and-play (PnP) priors has shown the state-of-the-art performance of reconstruction algorithms under such priors in a range of imaging applications. Integration of powerful image denoisers into advanced registration methods provides our model with a flexibility to accommodate datasets that have low signal-to-noise ratios (SNRs). We demonstrate the performance of our method under a wide variety of denoising models in the context of diffeomorphic image registration. Experimental results show that our model substantially improves the accuracy of spatial alignment in applications of 3D in-utero diffusion-weighted MR images (DW-MRI) that suffer from low SNR and large spatial transformations.