This paper describes a rigorous framework for reconstructing MR images of the heart, acquired continuously over the cardiac and respiratory cycle. The framework generalizes existing techniques, commonly referred to as retrospective gating, and is based on the properties of reproducing kernel Hilbert spaces. The reconstruction problem is formulated as a moment problem in a multidimensional reproducing kernel Hilbert spaces (a two-dimensional space for cardiac and respiratory resolved imaging). Several reproducing kernel Hilbert spaces were tested and compared, including those corresponding to commonly used interpolation techniques (sinc-based and splines kernels) and a more specific kernel allowed by the framework (based on a first-order Sobolev RKHS). The Sobolev reproducing kernel Hilbert spaces was shown to allow improved reconstructions in both simulated and real data from healthy volunteers, acquired in free breathing.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1002/mrm.22170 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Starting from the extension to complex arguments of the ordinary Fourier transform (FT) (due to Paley and Wiener) and from results concerning reproducing kernels in Hilbert spaces, we define a new, to the best of our knowledge, class of partially coherent planar sources presenting a structured degree of coherence. Such sources are shown to be of the Schell-model type as far as one of the transverse coordinates is concerned, while they depend on the average value of the orthogonal coordinate of the two points. Some examples are shown in detail, but the proposed approach can be easily extended to infinitely many other sources.
View Article and Find Full Text PDFNew Properties of Holomorphic Sobolev-Hardy Spaces.
Complex Anal Oper Theory
December 2024
Department of Mathematical Sciences, Purdue University Fort Wayne, Fort Wayne, IN 46805-1499 USA.
We give new characterizations of the optimal data space for the -Neumann boundary value problem for the operator associated to a bounded, Lipschitz domain . We show that the solution space is embedded (as a Banach space) in the Dirichlet space and that for , the solution space is a reproducing kernel Hilbert space.
View Article and Find Full Text PDFLeveraging SO(3)-steerable convolutions for pose-robust semantic segmentation in 3D medical data.
J Mach Learn Biomed Imaging
May 2024
Support Center for Advanced Neuroimaging (SCAN), University Institute of Diagnostic and Interventional Neuroradiology, University of Bern, Inselspital, Bern University Hospital, Bern, Switzerland.
Article Synopsis
- Convolutional neural networks (CNNs) enhance parameter sharing and translational equivariance using convolutional kernels, and adjusting these to be SO(3)-steerable improves their efficacy.
- These rotationally-equivariant convolutional layers offer benefits like increased robustness to unseen poses, reduced network size, and better sample efficiency compared to standard convolutional layers.
- The authors introduce a new family of segmentation networks utilizing equivariant voxel convolutions based on spherical harmonics, achieving improved performance in MRI brain tumor segmentation without needing rotation-based data augmentation.
Application of Bivariate Reproducing Kernel-Based Best Interpolation Method in Electrical Tomography.
Sensors (Basel)
November 2024
School of Building Services Science and Engineering, Xi'an University of Architecture and Technology, Xi'an 710055, China.
Electrical Tomography (ET) technology is widely used in multiphase flow detection due to its advantages of low cost, visualization, fast response, non-radiation, and non-invasiveness. However, ill-posed solutions lead to low image reconstruction resolution, which limits its practical engineering applications. Although existing interpolation approximation algorithms can alleviate the effects of the ill-posed solutions to some extent, the imaging results remain suboptimal due to the limited approximation capability of these methods.
View Article and Find Full Text PDFTowards generalizable face forgery detection via mitigating spurious correlation.
Neural Netw
February 2025
School of Software Engineering, Xi'an Jiaotong University, Xi'an 710048, China. Electronic address:
The continuous advancement of face forgery techniques has caused a series of trust crises, posing a significant menace to information security and personal privacy. In response, deep learning is being employed to develop effective detection methods to identify deepfake images and videos. Currently, most detection methods generally achieve satisfactory performance in intra-domain detection.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!