Deep learning (DL) has emerged as a tool for improving accelerated MRI reconstruction. A common strategy among DL methods is the physics-based approach, where a regularized iterative algorithm alternating between data consistency and a regularizer is unrolled for a finite number of iterations. This unrolled network is then trained end-to-end in a supervised manner, using fully-sampled data as ground truth for the network output. However, in a number of scenarios, it is difficult to obtain fully-sampled datasets, due to physiological constraints such as organ motion or physical constraints such as signal decay. In this work, we tackle this issue and propose a self-supervised learning strategy that enables physics-based DL reconstruction without fully-sampled data. Our approach is to divide the acquired sub-sampled points for each scan into two sets, one of which is used to enforce data consistency in the unrolled network and the other to define the loss for training. Results show that the proposed self-supervised learning method successfully reconstructs images without fully-sampled data, performing similarly to the supervised approach that is trained with fully-sampled references. This has implications for physics-based inverse problem approaches for other settings, where fully-sampled data is not available or possible to acquire.
|Original language||English (US)|
|Title of host publication||ISBI 2020 - 2020 IEEE International Symposium on Biomedical Imaging|
|Publisher||IEEE Computer Society|
|Number of pages||5|
|State||Published - Apr 2020|
|Event||17th IEEE International Symposium on Biomedical Imaging, ISBI 2020 - Iowa City, United States|
Duration: Apr 3 2020 → Apr 7 2020
|Name||Proceedings - International Symposium on Biomedical Imaging|
|Conference||17th IEEE International Symposium on Biomedical Imaging, ISBI 2020|
|Period||4/3/20 → 4/7/20|
Bibliographical noteFunding Information:
This work was partially supported by NIH R00HL111410, NIH P41EB027061, NIH U01EB025144, NSF CAREER CCF-1651825. Knee MRI data were obtained from the NYU fastMRI initiative database . NYU fastMRI database was acquired with the relevant institutional review board approvals as detailed in . NYU fastMRI investigators provided data but did not participate in analysis or writing of this report. A listing of NYU fastMRI investigators, subject to updates, can be found at fastmri.med.nyu.edu.
© 2020 IEEE.
- Self-supervised learning
- accelerated imaging
- compressed sensing
- deep learning
- neural networks
- parallel imaging
- supervised learning