Fast Multi-class Dictionaries Learning with Geometrical Directions in MRI Reconstruction
This incremental method addresses the need for faster and higher-quality MRI reconstruction in undersampled imaging, potentially reducing data acquisition time for medical applications.
The authors tackled the problem of improving MRI image reconstruction from undersampled k-space data by introducing a fast multi-class dictionary learning method that classifies image patches by geometrical direction, resulting in better artifact suppression and edge preservation compared to state-of-the-art methods, with significantly faster computation than typical K-SVD dictionary learning.
Objective: Improve the reconstructed image with fast and multi-class dictionaries learning when magnetic resonance imaging is accelerated by undersampling the k-space data. Methods: A fast orthogonal dictionary learning method is introduced into magnetic resonance image reconstruction to providing adaptive sparse representation of images. To enhance the sparsity, image is divided into classified patches according to the same geometrical direction and dictionary is trained within each class. A new sparse reconstruction model with the multi-class dictionaries is proposed and solved using a fast alternating direction method of multipliers. Results: Experiments on phantom and brain imaging data with acceleration factor up to 10 and various undersampling patterns are conducted. The proposed method is compared with state-of-the-art magnetic resonance image reconstruction methods. Conclusion: Artifacts are better suppressed and image edges are better preserved than the compared methods. Besides, the computation of the proposed approach is much faster than the typical K-SVD dictionary learning method in magnetic resonance image reconstruction. Significance: The proposed method can be exploited in undersapmled magnetic resonance imaging to reduce data acquisition time and reconstruct images with better image quality.