Fine-tuning deep learning model parameters for improved super-resolution of dynamic MRI with prior-knowledge

TL;DR

This paper introduces a prior-knowledge based fine-tuning method for deep learning models to enhance super-resolution in dynamic MRI, significantly improving spatial resolution while reducing scan time.

Contribution

It proposes a novel fine-tuning approach using subject-specific static MRI as prior knowledge to improve dynamic MRI super-resolution performance.

Findings

Higher SSIM scores after fine-tuning indicate better image quality.

Method achieves statistically significant improvements over baseline.

Potential for real-time high-resolution dynamic MRI with high acceleration factors.

Abstract

Dynamic imaging is a beneficial tool for interventions to assess physiological changes. Nonetheless during dynamic MRI, while achieving a high temporal resolution, the spatial resolution is compromised. To overcome this spatio-temporal trade-off, this research presents a super-resolution (SR) MRI reconstruction with prior knowledge based fine-tuning to maximise spatial information while reducing the required scan-time for dynamic MRIs. An U-Net based network with perceptual loss is trained on a benchmark dataset and fine-tuned using one subject-specific static high resolution MRI as prior knowledge to obtain high resolution dynamic images during the inference stage. 3D dynamic data for three subjects were acquired with different parameters to test the generalisation capabilities of the network. The method was tested for different levels of in-plane undersampling for dynamic MRI. The reconstructed dynamic SR results after fine-tuning showed higher similarity with the high resolution ground-truth, while quantitatively achieving statistically significant improvement. The average SSIM of the lowest resolution experimented during this research (6.25~\% of the k-space) before and after fine-tuning were 0.939 $\pm$ 0.008 and 0.957 $\pm$ 0.006 respectively. This could theoretically result in an acceleration factor of 16, which can potentially be acquired in less than half a second. The proposed approach shows that the super-resolution MRI reconstruction with prior-information can alleviate the spatio-temporal trade-off in dynamic MRI, even for high acceleration factors.