k-t CLAIR: Self-Consistency Guided Multi-Prior Learning for Dynamic Parallel MR Image Reconstruction
Lab of AI in Radiology (CLAIR), Department of Imaging and Interventional Radiology, The Chinese University of Hong Kong, Hong Kong
This repository is the official PyTorch implementation of "k-t CLAIR: Self-Consistency Guided Multi-Prior Learning for Dynamic Parallel MR Image Reconstruction" (arxiv, supp, pretrained models, visual results, oral presentation). k-t CLAIR achieves state-of-the-art performance in
- accelerated Cine reconstruction
- accelerated T1/T2 mapping
- [2023/10/12] 🥉 We secured 3rd place in accelerated Cine reconstruction task in CMRxRecon Challenge during MICCAI 2023!
- [2023/10/12] 🥉 We secured 3rd place in accelerated T1/T2 Mapping task in CMRxRecon Challenge during MICCAI 2023!
- [2023/10/12] 🔥 Invited talk for CMRxRecon Challenge, Statistical Atlases and Computational Modeling of the Heart (STACOM) Workshop, MICCAI 2023 (Vancouver, Canada)!
@misc{zhang2023kt,
title={$k$-$t$ CLAIR: Self-Consistency Guided Multi-Prior Learning for Dynamic Parallel MR Image Reconstruction},
author={Liping Zhang and Weitian Chen},
year={2023},
eprint={2310.11050},
archivePrefix={arXiv},
primaryClass={eess.IV}
}This project is released under the MIT license. The codes are based on fastMRI and CMRxRecon. Please also follow their licenses. Thanks for their awesome works.
