Using High-Pass Filter to Enhance Scan Specific Learning for MRI Reconstruction without Any Extra Training Data

• Published in: NeuroImage (Orlando, Fla.) Vol. 303; p. 120926
• Main Authors: Jin, Zhaoyang, Cao, Jiuwen, Zhang, Mei, Xiang, Qing-San
• Format: Journal Article
• Language: English
• Published: United States Elsevier Inc 01.12.2024; Elsevier Limited; Elsevier
• Subjects: Algorithms; Brain - diagnostic imaging; convolutional neural network; Deep learning; fast MRI; Fourier transforms; high-pass filter; HP-RAKI; Humans; Image Processing, Computer-Assisted - methods; Interpolation; Magnetic resonance imaging; Magnetic Resonance Imaging - methods; Methods; Neural networks; Neural Networks, Computer; RAKI; Sparsity; Wavelet transforms; deep learning; RAKI; high-pass filter; fast MRI; convolutional neural network; HP-RAKI
• ISSN: 1053-8119; 1095-9572; 1095-9572
• DOI: 10.1016/j.neuroimage.2024.120926

•Accelerated MRI reconstruction was improved by using an HP-RAKI algorithm.•A high-pass (HP) filter reduced image support to facilitate linear prediction.•Normal contrast was restored by using an inverse HP filtering.•HP-RAKI method was extended to corresponding residual structure.•High quality reconstruction was achieved without any extra training data. In accelerated MRI, the robust artificial-neural-network for k-space interpolation (RAKI) method is an attractive learning-based reconstruction that does not require additional training data. This study was focused on obtaining high quality MR images from regular under-sampled multi-coil k-space data using a high-pass filtered RAKI (HP-RAKI) reconstruction without any extra training data. MRI scan from human subjects was under-sampled with a regular pattern using skipped phase encoding and a fully sampled k-space center. A high-pass (HP) filter was applied in k-space to reduce image support to facilitate linear prediction. The HP filtered k-space center was used to train the RAKI network without any extra training data. The unacquired k-space data can be predicted from a trained RAKI network with optimized parameters. Final reconstruction was obtained after performing an inverse HP filtering for the predicted k-space data. This HP-RAKI method can be extended to corresponding residual structure (HP-rRAKI). HP-RAKI was compared with GRAPPA, HP-GRAPPA, RAKI and MW-RAKI algorithms, and HP-rRAKI was compared with corresponding residual extensions, including rRAKI and MW-rRAKI, all qualitatively and quantitatively using visual inspection and such metrics as SSIM and PSNR. HP-RAKI and HP-rRAKI were found to be effective in reconstructing MR images even at high acceleration factors. HP-RAKI and HP-rRAKI compared favorably with other algorithms. Using high-pass filtered central k-space data for training, HP-RAKI offers higher reconstruction quality for regularly under-sampled multi-coil k-space data without any extra training data. It has shown promising capabilities for fast MRI applications, especially those lacking fully sampled training data.