Diffusion-weighted images superresolution using high-order SVD
Summary: The spatial resolution of diffusion-weighted imaging (DWI) is limited by several physical and clinical considerations, such as practical scanning times. Interpolation methods, which are widely used to enhance resolution, often result in blurred edges. Advanced superresolution scanning acquires images with specific protocols and long acquisition times. In this paper, we propose a novel single image superresolution (SR) method which introduces high-order SVD (HOSVD) to regularize the patch-based SR framework on DWI datasets. The proposed method was implemented on an adaptive basis which ensured a more accurate reconstruction of high-resolution DWI datasets. Meanwhile, the intrinsic dimensional decreasing property of HOSVD is also beneficial for reducing the computational burden. Experimental results from both synthetic and real DWI datasets demonstrate that the proposed method enhances the details in reconstructed high-resolution DWI datasets and outperforms conventional techniques such as interpolation methods and nonlocal upsampling.
- An image super-resolution reconstruction method based on diffusion driven prior
- An improved bilevel optimization approach for image super-resolution based on a fractional diffusion tensor
- A multi-frame super-resolution using diffusion registration and a nonlocal variational image restoration
- Superresolution reconstruction using nonlinear gradient-based regularization
- Image super-resolution reconstruction based on Dirac residual
- Conjugate gradient methods for super-resolution image reconstruction problems
- Superresolution via Sparsity Constraints
- Segmentation of hyperacute cerebral infarcts based on sparse representation of diffusion weighted imaging
- A machine learning approach for specification of spinal cord injuries using fractional anisotropy values obtained from diffusion tensor images
- Second-order regression-based MR image upsampling
- scientific article; zbMATH DE number 2043729 (Why is no real title available?)
This page was built for publication: Diffusion-weighted images superresolution using high-order SVD
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q519828)
