Attention-gated convolutional neural networks for off-resonance correction of spiral real-time MRI

TL;DR

This paper introduces an attention-gated CNN method for off-resonance correction in spiral real-time MRI, significantly enhancing image quality by addressing blurring and signal loss caused by off-resonance effects.

Contribution

It presents a novel CNN architecture with attention gates that improves off-resonance correction in spiral RT-MRI, outperforming existing methods.

Findings

Enhanced image quality in spiral RT-MRI with attention-gated CNN

Better correction of off-resonance artifacts compared to prior methods

Improved visualization of vocal tract dynamics during speech

Abstract

Spiral acquisitions are preferred in real-time MRI because of their efficiency, which has made it possible to capture vocal tract dynamics during natural speech. A fundamental limitation of spirals is blurring and signal loss due to off-resonance, which degrades image quality at air-tissue boundaries. Here, we present a new CNN-based off-resonance correction method that incorporates an attention-gate mechanism. This leverages spatial and channel relationships of filtered outputs and improves the expressiveness of the networks. We demonstrate improved performance with the attention-gate, on 1.5 Tesla spiral speech RT-MRI, compared to existing off-resonance correction methods.