. The released CMRxRecon2024 dataset is currently the largest and most protocol-diverse publicly available k-space dataset including multi-modality and multi-view cardiac MRI data from 330 healthy volunteers, and each one covers standardized and commonly used clinical protocols. ©RSNA, 2025.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1148/ryai.240443 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
CMRxRecon2024: A Multimodality, Multiview k-Space Dataset Boosting Universal Machine Learning for Accelerated Cardiac MRI.
Radiol Artif Intell
January 2025
Human Phenome Institute and Shanghai Pudong Hospital, Fudan University, Shanghai, China.
. The released CMRxRecon2024 dataset is currently the largest and most protocol-diverse publicly available k-space dataset including multi-modality and multi-view cardiac MRI data from 330 healthy volunteers, and each one covers standardized and commonly used clinical protocols. ©RSNA, 2025.
View Article and Find Full Text PDFAttention incorporated network for sharing low-rank, image and k-space information during MR image reconstruction to achieve single breath-hold cardiac Cine imaging.
Comput Med Imaging Graph
December 2024
Medical Image and Data Analysis (MIDAS.lab), Department of Diagnostic and Interventional Radiology, University of Tuebingen, Tuebingen, Germany.
Cardiac Cine Magnetic Resonance Imaging (MRI) provides an accurate assessment of heart morphology and function in clinical practice. However, MRI requires long acquisition times, with recent deep learning-based methods showing great promise to accelerate imaging and enhance reconstruction quality. Existing networks exhibit some common limitations that constrain further acceleration possibilities, including single-domain learning, reliance on a single regularization term, and equal feature contribution.
View Article and Find Full Text PDFData on full stationary wave-field measurement of a suspended steel plate punctually loaded.
Data Brief
February 2025
Institut Camille Jordan, UMR-CNRS 5208, École Centrale de Lyon, 36 Avenue Guy de Collongue, 69134, Écully, France.
The dataset presented contains the experimental structural response, in the frequency domain, of a suspended steel plate to a point force excitation. The plate is excited by a mechanical point force generated by a Brüel & kJær shaker with a white noise signal input from 3.125 Hz to 2000 Hz.
View Article and Find Full Text PDFFastMRI Breast: A Publicly Available Radial k-Space Dataset of Breast Dynamic Contrast-enhanced MRI.
Radiol Artif Intell
January 2025
From the Department of Radiology, Weill Cornell Medical College, Cornell University, MRI Research Institute, 407 E 61st St, New York, NY 10065 (E.S., S.G.K.); Center for Advanced Imaging Innovation and Research (CAI2R), Department of Radiology, New York University Grossman School of Medicine, New York, NY (E.S., P.M.J., R.T., Y.W.L., F.K., L.M., S.G.K., L.H.); and Department Artificial Intelligence in Biomedical Engineering, University Erlangen-Nuremberg, Erlangen, Germany (Z.T., F.K.).
Clean Self-Supervised MRI Reconstruction from Noisy, Sub-Sampled Training Data with Robust SSDU.
Bioengineering (Basel)
December 2024
Department of Medical Biophysics, University of Toronto, Toronto, ON M4N 3M5, Canada.
Most existing methods for magnetic resonance imaging (MRI) reconstruction with deep learning use fully supervised training, which assumes that a fully sampled dataset with a high signal-to-noise ratio (SNR) is available for training. In many circumstances, however, such a dataset is highly impractical or even technically infeasible to acquire. Recently, a number of self-supervised methods for MRI reconstruction have been proposed, which use sub-sampled data only.
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!