Enhancing quality and speed in database-free neural network reconstructions of undersampled MRI with SCAMPI

TL;DR

SCAMPI is an untrained deep neural network method that improves MRI reconstruction quality and speed by using a sparsity-enforcing loss, outperforming existing methods without prior dataset training.

Contribution

The paper introduces SCAMPI, a novel untrained neural network for MRI reconstruction that enhances image quality and convergence speed using a multidomain sparsity loss.

Findings

SCAMPI outperforms state-of-the-art compressed sensing methods.

It achieves faster convergence and higher image quality than ConvDecoder.

It effectively reconstructs both multicoil and single coil MRI data without explicit coil sensitivity knowledge.

Abstract

Purpose: We present SCAMPI (Sparsity Constrained Application of deep Magnetic resonance Priors for Image reconstruction), an untrained deep Neural Network for MRI reconstruction without previous training on datasets. It expands the Deep Image Prior approach with a multidomain, sparsity-enforcing loss function to achieve higher image quality at a faster convergence speed than previously reported methods. Methods: Two-dimensional MRI data from the FastMRI dataset with Cartesian undersampling in phase-encoding direction were reconstructed for different acceleration rates for single coil and multicoil data. Results: The performance of our architecture was compared to state-of-the-art Compressed Sensing methods and ConvDecoder, another untrained Neural Network for two-dimensional MRI reconstruction. SCAMPI outperforms these by better reducing undersampling artifacts and yielding lower error metrics in multicoil imaging. In comparison to ConvDecoder, the U-Net architecture combined with an elaborated loss-function allows for much faster convergence at higher image quality. SCAMPI can reconstruct multicoil data without explicit knowledge of coil sensitivity profiles. Moreover, it is a novel tool for reconstructing undersampled single coil k-space data. Conclusion: Our approach avoids overfitting to dataset features, that can occur in Neural Networks trained on databases, because the network parameters are tuned only on the reconstruction data. It allows better results and faster reconstruction than the baseline untrained Neural Network approach.