Iterative Data Refinement for Self-Supervised Learning MR Image Reconstruction

Xue Liu, Juan Zou, Tao Sun, Ruoyou Wu, Xiawu Zheng, Cheng Li, Shanshan Wang

Abstract

Magnetic Resonance Imaging (MRI) is an important technique in the clinic. Fast MRI based on k-space undersampling and high-quality image reconstruction has been widely utilized, and many deep learning-based methods have been developed in recent years. Although promising results have been achieved, most existing methods require fully-sampled reference data. Unfortunately, fully-sampled MRI data are difficult to obtain in real-world applications. To address this issue, we propose a data refinement framework for self-supervised MR image reconstruction. Specifically, we first analyze the reason of the performance gap between self-supervised and supervised methods and identify that the bias in the training datasets is one major factor. Then, we design an effective self-supervised data refinement learning framework to reduce this data bias. With the data refinement, an enhanced self-supervised MR image reconstruction method is developed to prompt fast MR imaging. We evaluate our method on an in-vivo MRI dataset. Experimental results show that without utilizing any fully sampled MRI data, our self-supervised learning framework possesses strong capabilities in capturing image details and structures at high acceleration factors.
BibTeX
@inproceedings{liu2023iterative,
  author = {Xue Liu and Juan Zou and Tao Sun and Ruoyou Wu and Xiawu Zheng and Cheng Li and Shanshan Wang},
  title = {{Iterative Data Refinement for Self-Supervised Learning MR Image Reconstruction}},
  booktitle = {ISBI},
  year = {2023},
  doi = {10.1109/isbi53787.2023.10230703},
}

Loading related content...

Figure