IREM: High-Resolution Magnetic Resonance (MR) Image Reconstruction via Implicit Neural Representation

TL;DR

IREM introduces an implicit neural representation approach for high-resolution MR image reconstruction, enabling arbitrary up-sampling from multiple low-resolution images while reducing scan time and preserving image detail.

Contribution

The paper presents a novel neural network method that models MR images as continuous functions, allowing flexible super-resolution from sparse low-res data.

Findings

Successfully reconstructs high-resolution MR images with high fidelity.

Reduces scan time while maintaining image quality.

Effectively captures high-frequency image features.

Abstract

For collecting high-quality high-resolution (HR) MR image, we propose a novel image reconstruction network named IREM, which is trained on multiple low-resolution (LR) MR images and achieve an arbitrary up-sampling rate for HR image reconstruction. In this work, we suppose the desired HR image as an implicit continuous function of the 3D image spatial coordinate and the thick-slice LR images as several sparse discrete samplings of this function. Then the super-resolution (SR) task is to learn the continuous volumetric function from a limited observations using an fully-connected neural network combined with Fourier feature positional encoding. By simply minimizing the error between the network prediction and the acquired LR image intensity across each imaging plane, IREM is trained to represent a continuous model of the observed tissue anatomy. Experimental results indicate that IREM succeeds in representing high frequency image feature, and in real scene data collection, IREM reduces scan time and achieves high-quality high-resolution MR imaging in terms of SNR and local image detail.