Multi-Contrast Complementary Learning for Accelerated MR Imaging

Thanks to its powerful ability to depict high-resolution anatomical information, magnetic resonance imaging (MRI) has become an essential non-invasive scanning technique in clinical practice. However, excessive acquisition time often leads to the degradation of image quality and psychological discomfort among subjects, hindering its further popularization. Besides reconstructing images from the undersampled protocol itself, multi-contrast MRI protocols bring promising solutions by leveraging additional morphological priors for the target modality. Nevertheless, previous multi-contrast techniques mainly adopt a simple fusion mechanism that inevitably ignores valuable knowledge. In this work, we propose a novel multi-contrast complementary information aggregation network named MCCA, aiming to exploit available complementary representations fully to reconstruct the undersampled modality. Specifically, a multi-scale feature fusion mechanism has been introduced to incorporate complementary-transferable knowledge into the target modality. Moreover, a hybrid convolution transformer block was developed to extract global-local context dependencies simultaneously, which combines the advantages of CNNs while maintaining the merits of Transformers. Compared to existing MRI reconstruction methods, the proposed method has demonstrated its superiority through extensive experiments on different datasets under different acceleration factors and undersampling patterns.

Authors

• Bangjun Li
• Weifeng Hu
• Chun-Mei Feng Institute of High Performance Computing, Singapore, A*STAR
• Yujun Li School of Artifcial Intelligence, Optics and Electronics (iOPEN), Northwestern Polytechnical University, Xi'an 710072, P.R. China
• Zhi Liu Shandong University
• Yong Xu

Keywords

• Magnetic resonance imaging
• Image reconstruction
• Transformers
• Data integration
• Convolutional neural networks
• Convolutional Neural Network
• Reconstruction Method
• Acceleration Factor
• Multi-scale Feature Fusion
• Target Modality
• Transformer Block
• Quantitative Results
• Convolutional Layers
• Local Context
• Convolution Operation
• Global Context
• Inverse Problem
• Magnetic Resonance Imaging Image
• Multimodal Imaging
• Spatial Context
• Image Domain
• Channel Dimension
• Clinical Datasets
• Structural Similarity Index Measure
• Inverse Fourier Transform
• Magnetic Resonance Imaging Sequences
• Convolutional Block
• Vision Transformer
• Reconstruction Performance
• Proton Density
• Reference Mode
• Multiple Modalities
• Deep Learning-based Methods
• Complementary information fusion
• fast reconstruction
• multi-contrast sequence
• Humans
• Electric Power Supplies
• Image Processing, Computer-Assisted
• Knowledge