Flow-based Visual Quality Enhancer for Super-resolution Magnetic Resonance Spectroscopic Imaging

TL;DR

This paper introduces a flow-based model to enhance the visual quality of super-resolution MRSI images, incorporating anatomical information and providing adjustable quality and uncertainty estimation, outperforming previous GAN-based methods.

Contribution

The paper presents a novel flow-based enhancer network for super-resolution MRSI that integrates anatomical data and offers improved stability, interpretability, and image quality.

Findings

Outperforms adversarial networks and baseline flow-based methods in visual quality.

Enables visual quality adjustment and uncertainty estimation.

Effective on a dataset from 25 glioma patients.

Abstract

Magnetic Resonance Spectroscopic Imaging (MRSI) is an essential tool for quantifying metabolites in the body, but the low spatial resolution limits its clinical applications. Deep learning-based super-resolution methods provided promising results for improving the spatial resolution of MRSI, but the super-resolved images are often blurry compared to the experimentally-acquired high-resolution images. Attempts have been made with the generative adversarial networks to improve the image visual quality. In this work, we consider another type of generative model, the flow-based model, of which the training is more stable and interpretable compared to the adversarial networks. Specifically, we propose a flow-based enhancer network to improve the visual quality of super-resolution MRSI. Different from previous flow-based models, our enhancer network incorporates anatomical information from additional image modalities (MRI) and uses a learnable base distribution. In addition, we impose a guide loss and a data-consistency loss to encourage the network to generate images with high visual quality while maintaining high fidelity. Experiments on a 1H-MRSI dataset acquired from 25 high-grade glioma patients indicate that our enhancer network outperforms the adversarial networks and the baseline flow-based methods. Our method also allows visual quality adjustment and uncertainty estimation.