VAN-ICC trains invertible network by finding an invertible and bijective function, which can map the original image to the compression image.
The main feature of our work is utilizing dummy variable technology to expand the channel in both the image and k-space domains.
Specifically, during model optimization, two subsets are constructed by randomly selecting part of k-space data from the undersampled data and then fed into two parallel reconstruction networks to perform information recovery.
In contrast to other generative models for reconstruction, the proposed method utilizes deep energy-based information as the image prior in reconstruction to improve the quality of image.
As an effective way to integrate the information contained in multiple medical images under different modalities, medical image synthesis and fusion have emerged in various clinical applications such as disease diagnosis and treatment planning.
This work presents an unsupervised deep learning scheme that exploiting high-dimensional assisted score-based generative model for color image restoration tasks.
Furthermore, the joint intensity-gradient constraint in data-fidelity term is proposed to limit the degree of freedom within generative model at the iterative colorization stage, and it is conducive to edge-preserving.
Magnetic resonance imaging is a powerful imaging modality that can provide versatile information but it has a bottleneck problem "slow imaging speed".
Dose reduction in computed tomography (CT) is essential for decreasing radiation risk in clinical applications.
Deep learning, particularly the generative model, has demonstrated tremendous potential to significantly speed up image reconstruction with reduced measurements recently.
Ill-posed inverse problems in imaging remain an active research topic in several decades, with new approaches constantly emerging.
To improve the compressive sensing MRI (CS-MRI) approaches in terms of fine structure loss under high acceleration factors, we have proposed an iterative feature refinement model (IFR-CS), equipped with fixed transforms, to restore the meaningful structures and details.
At the stage of prior learning, transformed feature images obtained by undecimated wavelet transform are stacked as an input of denoising autoencoder network (DAE).
In comparison with state-of-the-art methods, extensive experiments show that our method achieves consistent better reconstruction performance on the MRI reconstruction in terms of three quantitative metrics (PSNR, SSIM and HFEN) under different undersamling patterns and acceleration factors.
Three main contributions have been made: a de-aliasing reconstruction model was proposed to accelerate parallel MR imaging with deep learning exploring both spatial redundancy and multi-coil correlations; a split Bregman iteration algorithm was developed to solve the model efficiently; and unlike most existing parallel imaging methods which rely on the accuracy of the estimated multi-coil sensitivity, the proposed method can perform parallel reconstruction from undersampled data without explicit sensitivity calculation.
Recently, approaches based on deep learning and methods for contextual information extraction have served in many image segmentation tasks.
Usually, acquiring less data is a direct but important strategy to address these issues.
In this work, we propose cascaded residual dense networks for dynamic MR imaging with edge-enhance loss constraint, dubbed as CRDN.
For texture-preserving denoising of each cluster, considering that the variations in texture are captured and wrapped in not only the between-dimension energy variations but also the within-dimension variations of PCA transform coefficients, we further propose a PCA-transform-domain variation adaptive filtering method to preserve the local variations in textures.