Adaptive Local Neighborhood-based Neural Networks for MR Image Reconstruction from Undersampled Data

TL;DR

This paper introduces LONDN-MRI, a local neighborhood-based neural network approach that adaptively reconstructs MR images from undersampled data by fitting models on similar data neighborhoods, improving quality and adaptability.

Contribution

The paper presents a novel adaptive local neural network method for MR image reconstruction that fits models on similar data neighborhoods at test time, enhancing flexibility and quality.

Findings

Outperforms global trained models in image quality

Effective at high undersampling rates

Handles diverse scan settings

Abstract

Recent medical image reconstruction techniques focus on generating high-quality medical images suitable for clinical use at the lowest possible cost and with the fewest possible adverse effects on patients. Recent works have shown significant promise for reconstructing MR images from sparsely sampled k-space data using deep learning. In this work, we propose a technique that rapidly estimates deep neural networks directly at reconstruction time by fitting them on small adaptively estimated neighborhoods of a training set. In brief, our algorithm alternates between searching for neighbors in a data set that are similar to the test reconstruction, and training a local network on these neighbors followed by updating the test reconstruction. Because our reconstruction model is learned on a dataset that is in some sense similar to the image being reconstructed rather than being fit on a large, diverse training set, it is more adaptive to new scans. It can also handle changes in training sets and flexible scan settings, while being relatively fast. Our approach, dubbed LONDN-MRI, was validated on multiple data sets using deep unrolled reconstruction networks. Reconstructions were performed at four fold and eight fold undersampling of k-space with 1D variable-density random phase-encode undersampling masks. Our results demonstrate that our proposed locally-trained method produces higher-quality reconstructions compared to models trained globally on larger datasets as well as other scan-adaptive methods.