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

02/14/2021
by   Yongwan Lim, et al.
11

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.

READ FULL TEXT

page 4

page 6

research
03/09/2022

An error correction scheme for improved air-tissue boundary in real-time MRI video for speech production

The best performance in Air-tissue boundary (ATB) segmentation of real-t...
research
04/23/2021

Reconstructing Speech from Real-Time Articulatory MRI Using Neural Vocoders

Several approaches exist for the recording of articulatory movements, su...
research
02/16/2021

A multispeaker dataset of raw and reconstructed speech production real-time MRI video and 3D volumetric images

Real-time magnetic resonance imaging (RT-MRI) of human speech production...
research
10/19/2019

Attention Guided Metal Artifact Correction in MRI using Deep Neural Networks

An attention guided scheme for metal artifact correction in MRI using de...
research
06/07/2023

Cross-attention learning enables real-time nonuniform rotational distortion correction in OCT

Nonuniform rotational distortion (NURD) correction is vital for endoscop...
research
08/03/2020

Speaker dependent articulatory-to-acoustic mapping using real-time MRI of the vocal tract

Articulatory-to-acoustic (forward) mapping is a technique to predict spe...
research
01/21/2023

Dynamic MLP for MRI Reconstruction

As convolutional neural networks (CNN) become the most successful recons...

Please sign up or login with your details

Forgot password? Click here to reset