MR-Contrast-Aware Image-to-Image Translations with Generative Adversarial Networks

TL;DR

This paper introduces a GAN-based method conditioned on MRI acquisition parameters to synthesize MR images with adjustable contrast, improving over existing methods and aiding in diagnosis and data augmentation.

Contribution

We propose a novel contrast-aware image-to-image translation GAN conditioned on acquisition parameters, enabling fine-tuned MRI contrast synthesis.

Findings

Outperforms pix2pix in contrast translation quality

Achieves higher peak signal-to-noise ratio and structural similarity

Enables synthesis of missing or augmented MRI contrasts

Abstract

Purpose A Magnetic Resonance Imaging (MRI) exam typically consists of several sequences that yield different image contrasts. Each sequence is parameterized through multiple acquisition parameters that influence image contrast, signal-to-noise ratio, acquisition time, and/or resolution. Depending on the clinical indication, different contrasts are required by the radiologist to make a diagnosis. As MR sequence acquisition is time consuming and acquired images may be corrupted due to motion, a method to synthesize MR images with adjustable contrast properties is required. Methods Therefore, we trained an image-to-image generative adversarial network conditioned on the MR acquisition parameters repetition time and echo time. Our approach is motivated by style transfer networks, whereas the "style" for an image is explicitly given in our case, as it is determined by the MR acquisition parameters our network is conditioned on. Results This enables us to synthesize MR images with adjustable image contrast. We evaluated our approach on the fastMRI dataset, a large set of publicly available MR knee images, and show that our method outperforms a benchmark pix2pix approach in the translation of non-fat-saturated MR images to fat-saturated images. Our approach yields a peak signal-to-noise ratio and structural similarity of 24.48 and 0.66, surpassing the pix2pix benchmark model significantly. Conclusion Our model is the first that enables fine-tuned contrast synthesis, which can be used to synthesize missing MR contrasts or as a data augmentation technique for AI training in MRI.