Attention Guided Metal Artifact Correction in MRI using Deep Neural Networks

10/19/2019

∙

An attention guided scheme for metal artifact correction in MRI using deep neural network is proposed in this paper. The inputs of the networks are two distorted images obtained with dual-polarity readout gradients. With MR image generation module and the additional data consistency loss to the previous work [1], the network is trained to estimate the frequency-shift map, off-resonance map, and attention map. The attention map helps to produce better distortion-corrected images by weighting on more relevant distortion-corrected images where two distortion-corrected images are produced with half of the frequency-shift maps. In this paper, we observed that in a real MRI environment, two distorted images obtained with opposite polarities of readout gradient showed artifacts in a different region. Therefore, we proved that using the attention map was important in that it reduced the residual ripple and pile-up artifacts near metallic implants.

READ FULL TEXT

Attention Guided Metal Artifact Correction in MRI using Deep Neural Networks

Blind Geometric Distortion Correction on Images Through Deep Learning

Joint Correction of Attenuation and Scatter Using Deep Convolutional Neural Networks (DCNN) for Time-of-Flight PET

Review: Noise and artifact reduction for MRI using deep learning

Respiratory Motion Correction in Abdominal MRI using a Densely Connected U-Net with GAN-guided Training

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

Orientation recognition and correction of Cardiac MRI with deep neural network

Fingerprint Distortion Rectification using Deep Convolutional Neural Networks

Attention Guided Metal Artifact Correction in MRI using Deep Neural Networks

Related Research

Blind Geometric Distortion Correction on Images Through Deep Learning

Joint Correction of Attenuation and Scatter Using Deep Convolutional Neural Networks (DCNN) for Time-of-Flight PET

Review: Noise and artifact reduction for MRI using deep learning

Respiratory Motion Correction in Abdominal MRI using a Densely Connected U-Net with GAN-guided Training

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

Orientation recognition and correction of Cardiac MRI with deep neural network

Fingerprint Distortion Rectification using Deep Convolutional Neural Networks