Multi‐mask self‐supervised learning for physics‐guided neural networks in highly accelerated magnetic resonance imaging

• Published in: NMR in biomedicine Vol. 35; no. 12; pp. e4798 - n/a
• Main Authors: Yaman, Burhaneddin, Gu, Hongyi, Hosseini, Seyed Amir Hossein, Demirel, Omer Burak, Moeller, Steen, Ellermann, Jutta, Uğurbil, Kâmil, Akçakaya, Mehmet
• Format: Journal Article
• Language: English
• Published: England Wiley Subscription Services, Inc 01.12.2022; John Wiley and Sons Inc
• Subjects: Brain; convolutional neural networks; Data acquisition; data augmentation; Deep learning; Humans; Image Processing, Computer-Assisted - methods; Image reconstruction; Knee; Magnetic resonance imaging; Magnetic Resonance Imaging - methods; Medical imaging; Neural networks; Neural Networks, Computer; Neuroimaging; parallel imaging; Physics; Resonance; Sampled data; Self-supervised learning; Supervised Machine Learning; Training; deep learning; parallel imaging; self-supervised learning; convolutional neural networks; image reconstruction; data augmentation
• ISSN: 0952-3480; 1099-1492
• DOI: 10.1002/nbm.4798

Self‐supervised learning has shown great promise because of its ability to train deep learning (DL) magnetic resonance imaging (MRI) reconstruction methods without fully sampled data. Current self‐supervised learning methods for physics‐guided reconstruction networks split acquired undersampled data into two disjoint sets, where one is used for data consistency (DC) in the unrolled network, while the other is used to define the training loss. In this study, we propose an improved self‐supervised learning strategy that more efficiently uses the acquired data to train a physics‐guided reconstruction network without a database of fully sampled data. The proposed multi‐mask self‐supervised learning via data undersampling (SSDU) applies a holdout masking operation on the acquired measurements to split them into multiple pairs of disjoint sets for each training sample, while using one of these pairs for DC units and the other for defining loss, thereby more efficiently using the undersampled data. Multi‐mask SSDU is applied on fully sampled 3D knee and prospectively undersampled 3D brain MRI datasets, for various acceleration rates and patterns, and compared with the parallel imaging method, CG‐SENSE, and single‐mask SSDU DL‐MRI, as well as supervised DL‐MRI when fully sampled data are available. The results on knee MRI show that the proposed multi‐mask SSDU outperforms SSDU and performs as well as supervised DL‐MRI. A clinical reader study further ranks the multi‐mask SSDU higher than supervised DL‐MRI in terms of signal‐to‐noise ratio and aliasing artifacts. Results on brain MRI show that multi‐mask SSDU achieves better reconstruction quality compared with SSDU. The reader study demonstrates that multi‐mask SSDU at R = 8 significantly improves reconstruction compared with single‐mask SSDU at R = 8, as well as CG‐SENSE at R = 2. The proposed multi‐mask self‐supervised learning via data undersampling applies a holdout masking operation on the acquired measurements to split them into multiple pairs of disjoint sets for each training sample, while using one of these pairs for data consistency units and the other for defining loss, thereby more efficiently using the undersampled data.