Flow-based Deformation Guidance for Unpaired Multi-Contrast MRI Image-to-Image Translation

TL;DR

This paper introduces a flow-based, invertible architecture for unpaired multi-contrast MRI translation that leverages temporal deformation guidance to produce more realistic and consistent synthesized images, improving upon existing methods.

Contribution

The paper presents a novel invertible, flow-based model that incorporates deformation fields for temporal guidance in unpaired MRI translation, ensuring cycle-consistency without extra loss functions.

Findings

Achieves competitive performance on standard MRI datasets.

Maintains realistic and consistent image translation across slices.

Outperforms existing deep learning methods in key metrics.

Abstract

Image synthesis from corrupted contrasts increases the diversity of diagnostic information available for many neurological diseases. Recently the image-to-image translation has experienced significant levels of interest within medical research, beginning with the successful use of the Generative Adversarial Network (GAN) to the introduction of cyclic constraint extended to multiple domains. However, in current approaches, there is no guarantee that the mapping between the two image domains would be unique or one-to-one. In this paper, we introduce a novel approach to unpaired image-to-image translation based on the invertible architecture. The invertible property of the flow-based architecture assures a cycle-consistency of image-to-image translation without additional loss functions. We utilize the temporal information between consecutive slices to provide more constraints to the optimization for transforming one domain to another in unpaired volumetric medical images. To capture temporal structures in the medical images, we explore the displacement between the consecutive slices using a deformation field. In our approach, the deformation field is used as a guidance to keep the translated slides realistic and consistent across the translation. The experimental results have shown that the synthesized images using our proposed approach are able to archive a competitive performance in terms of mean squared error, peak signal-to-noise ratio, and structural similarity index when compared with the existing deep learning-based methods on three standard datasets, i.e. HCP, MRBrainS13, and Brats2019.