DuDoINet: Dual-Domain Implicit Network for Multi-Modality MR Image Arbitrary-scale Super-Resolution
Open Access
- 26 October 2023
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 7335-7344
Abstract
Compared to single-modality magnetic resonance (MR) image super-resolution (SR) methods, multi-modality MR image methods can utilize high-resolution reference modality (e.g., T1 modality) to provide valuable complementary information for low-resolution target modality (e.g., T2 modality) in SR reconstruction, which can further improve the quality of the SR images. Although they have achieved impressive results, these methods still suffer from the following drawbacks: (1) They can only handle fixed integer upsampling factors, such as 2X, 3X, and 4X, and require training and storing corresponding models for each upsampling factor, which is infeasible in clinical practice; (2) They only perform feature extraction and reconstruction in the image domain. However, the aliasing artifacts produced in the image domain are structural and non-local. Therefore, using only the image domain cannot effectively reconstruct high-quality aliasing-free SR images. To address these issues, we develop a brand-new Dual-Domain Implicit Network (DuDoINet) for multi-modality MR image arbitrary-scale SR. Specifically, we propose a dual-domain learning scheme for multi-modality MR image SR, which allows the network to sufficiently exploit the frequency and image domain information in MR images. In addition, we design implicit attention to achieve arbitrary-scale upsampling of MR images, which utilizes a continuously differentiable function that generates pixel values from pixel coordinates. Furthermore, we designed a deformable cross-modality attention mechanism that can adaptively transfer high-frequency details from the T1 to the T2 modality, better integrating valuable complementary information from the T1 modality. Extensive and comprehensive experiments on healthy subjects and patient datasets demonstrate that our DuDoINet outperforms SOTA methods, demonstrating its great potential for clinical practice.Keywords
Funding Information
- National Program of China (2020YFC1523201 6217236519ZDA197)
- Zhejiang Elite Program (2022C01222)
This publication has 29 references indexed in Scilit:
- Subsampled brain MRI reconstruction by generative adversarial neural networksMedical Image Analysis, 2020
- High‐Resolution Breast MRI Reconstruction Using a Deep Convolutional Generative Adversarial NetworkJournal of Magnetic Resonance Imaging, 2020
- Multi-Contrast Super-Resolution MRI Through a Progressive NetworkIEEE Transactions on Medical Imaging, 2020
- MRI Super-Resolution With Ensemble Learning and Complementary PriorsIEEE Transactions on Computational Imaging, 2020
- End-to-End Boundary Aware Networks for Medical Image Segmentation2019
- Brain MRI super resolution using 3D deep densely connected neural networks2018
- A Deep Cascade of Convolutional Neural Networks for Dynamic MR Image ReconstructionIEEE Transactions on Medical Imaging, 2018
- Context-Sensitive Super-Resolution for Fast Fetal Magnetic Resonance Imaging2017
- Multi-input Cardiac Image Super-Resolution Using Convolutional Neural Networks2016
- On Single Image Scale-Up Using Sparse-Representations2012