Learning to Decode 7T-like MR Image Reconstruction from 3T MR Images

TL;DR

This paper introduces a novel autoencoder-based framework that reconstructs high-quality 7T-like MR images from low-quality 3T MR scans, aiming to improve diagnostic accuracy without high-cost equipment.

Contribution

It presents a unique merged convolutional autoencoder architecture with multiple decoders and a novel training strategy for enhanced MR image super-resolution.

Findings

Outperforms existing methods in reconstruction quality

Reduces processing time compared to related approaches

Effective in generating high-field MR images from low-field scans

Abstract

Increasing demand for high field magnetic resonance (MR) scanner indicates the need for high-quality MR images for accurate medical diagnosis. However, cost constraints, instead, motivate a need for algorithms to enhance images from low field scanners. We propose an approach to process the given low field (3T) MR image slices to reconstruct the corresponding high field (7T-like) slices. Our framework involves a novel architecture of a merged convolutional autoencoder with a single encoder and multiple decoders. Specifically, we employ three decoders with random initializations, and the proposed training approach involves selection of a particular decoder in each weight-update iteration for back propagation. We demonstrate that the proposed algorithm outperforms some related contemporary methods in terms of performance and reconstruction time.