Flow-based Deformation Guidance for Unpaired Multi-Contrast MRI Image-to-Image Translation
This work addresses the problem of generating diverse diagnostic information for neurological diseases by improving MRI image synthesis, which is relevant for medical researchers and practitioners, offering an incremental improvement over existing methods.
This paper tackles the problem of unpaired multi-contrast MRI image-to-image translation, aiming to synthesize images from corrupted contrasts to increase diagnostic information. The authors introduce a novel invertible flow-based architecture that ensures cycle-consistency without additional loss functions and utilizes temporal information from consecutive slices via a deformation field as guidance. The approach achieved competitive performance in terms of MSE, PSNR, and SSIM on HCP, MRBrainS13, and Brats2019 datasets compared to existing deep learning methods.
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.