Synthesized 7T MRI from 3T MRI via deep learning in spatial and wavelet domains

•We introduce a novel method for 7T image synthesis by leveraging complementary information of both spatial and wavelet domains.•We provide an efficient way to incorporate image priors in deep learning to achieve superior image synthesis performance.•We present a flexible and parameter-efficient WAT...

Full description

Saved in:
Bibliographic Details
Published in:Medical image analysis 2020-05, Vol.62, p.101663-101663, Article 101663
Main Authors: Qu, Liangqiong, Zhang, Yongqin, Wang, Shuai, Yap, Pew-Thian, Shen, Dinggang
Format: Article
Language:English
Subjects:
Affine transformations
Deep Learning
Domains
Feature maps
Humans
Image contrast
Image quality
Image synthesis
Machine learning
Magnetic Resonance Imaging
Magnetic resonance imaging (MRI)
Scanners
Spatial and wavelet domains
Spatial discrimination learning
Synthesis
Wavelet transforms
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:•We introduce a novel method for 7T image synthesis by leveraging complementary information of both spatial and wavelet domains.•We provide an efficient way to incorporate image priors in deep learning to achieve superior image synthesis performance.•We present a flexible and parameter-efficient WAT layer that can be embedded into a neural network to facilitate effective reconstruction with consideration of multiple frequency components. [Display omitted] Ultra-high field 7T MRI scanners, while producing images with exceptional anatomical details, are cost prohibitive and hence highly inaccessible. In this paper, we introduce a novel deep learning network that fuses complementary information from spatial and wavelet domains to synthesize 7T T1-weighted images from their 3T counterparts. Our deep learning network leverages wavelet transformation to facilitate effective multi-scale reconstruction, taking into account both low-frequency tissue contrast and high-frequency anatomical details. Our network utilizes a novel wavelet-based affine transformation (WAT) layer, which modulates feature maps from the spatial domain with information from the wavelet domain. Extensive experimental results demonstrate the capability of the proposed method in synthesizing high-quality 7T images with better tissue contrast and greater details, outperforming state-of-the-art methods.
ISSN:1361-8415
1361-8423
DOI:10.1016/j.media.2020.101663