UEPS: Robust and Efficient MRI Reconstruction (Pre-trained Model and Demo Data)

Fuente: Zenodo
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zhou, Xiang, Shang, Hong, Zhan, Zijian, He, Tianyu, Meng, Jintao, Liang, Dong
Format: Recurso digital
Veröffentlicht: Zenodo 2026
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866902014120689664
author Zhou, Xiang
Shang, Hong
Zhan, Zijian
He, Tianyu
Meng, Jintao
Liang, Dong
author_facet Zhou, Xiang
Shang, Hong
Zhan, Zijian
He, Tianyu
Meng, Jintao
Liang, Dong
contents <p>This record contains the pre-trained weights (ckpt_pick.pth), sample MRI data, and visual results for the UEPS framework.</p> <p>UEPS is a novel deep unrolled model (DUM) architecture designed for robust and efficient MRI reconstruction. It features three key innovations: (i) an Unrolled Expanded (UE) design that eliminates coil sensitivity maps (CSM) dependency by expanding multi-coil data to the batch dimension; (ii) progressive resolution, which leverages k-space-to-image mapping for efficient coarse-to-fine refinement; and (iii) sparse attention tailored to MRI's 1D undersampling nature.</p> <p>Files included:<br>* ckpt_pick.pth: Pre-trained model weights.<br>* demo_data.zip: Sample MRI data for quick testing and visualization.<br>* reconstruction_examples.zip: Qualitative visualization examples of reconstructed slices. The image filenames follow the format '{slice_index}_nmse_{value}_psnr_{value}_ssim_{value}.png' (e.g., 140_nmse_0.00663_psnr_42.3608_ssim_0.9784.png).</p> <p>For the official PyTorch implementation, please visit our GitHub repository: https://github.com/HongShangGroup/UEPS</p>
format Recurso digital
id zenodo_https___doi_org_10_5281_zenodo_19494819
institution Zenodo
language
publishDate 2026
publisher Zenodo
record_format zenodo
spellingShingle UEPS: Robust and Efficient MRI Reconstruction (Pre-trained Model and Demo Data)
Zhou, Xiang
Shang, Hong
Zhan, Zijian
He, Tianyu
Meng, Jintao
Liang, Dong
<p>This record contains the pre-trained weights (ckpt_pick.pth), sample MRI data, and visual results for the UEPS framework.</p> <p>UEPS is a novel deep unrolled model (DUM) architecture designed for robust and efficient MRI reconstruction. It features three key innovations: (i) an Unrolled Expanded (UE) design that eliminates coil sensitivity maps (CSM) dependency by expanding multi-coil data to the batch dimension; (ii) progressive resolution, which leverages k-space-to-image mapping for efficient coarse-to-fine refinement; and (iii) sparse attention tailored to MRI's 1D undersampling nature.</p> <p>Files included:<br>* ckpt_pick.pth: Pre-trained model weights.<br>* demo_data.zip: Sample MRI data for quick testing and visualization.<br>* reconstruction_examples.zip: Qualitative visualization examples of reconstructed slices. The image filenames follow the format '{slice_index}_nmse_{value}_psnr_{value}_ssim_{value}.png' (e.g., 140_nmse_0.00663_psnr_42.3608_ssim_0.9784.png).</p> <p>For the official PyTorch implementation, please visit our GitHub repository: https://github.com/HongShangGroup/UEPS</p>
title UEPS: Robust and Efficient MRI Reconstruction (Pre-trained Model and Demo Data)
url https://doi.org/10.5281/zenodo.19494819