Zero-shot self-supervised learning of single breath-hold magnetic resonance cholangiopancreatography (MRCP) reconstruction
This addresses the challenge of reducing patient discomfort and improving clinical workflow efficiency in medical imaging, though it is incremental as it builds on existing zero-shot and compressed sensing methods.
The study tackled the problem of long breath-hold times in magnetic resonance cholangiopancreatography (MRCP) by applying zero-shot self-supervised learning reconstruction, achieving a breath-hold duration of 14 seconds and training time reduction from 271 to 11 minutes while maintaining image quality comparable to respiratory-triggered acquisitions.
Purpose: To investigate the feasibility of applying zero-shot self-supervised learning reconstruction to reduce breath-hold times in magnetic resonance cholangiopancreatography (MRCP). Methods: Breath-hold MRCP was acquired from 11 healthy volunteers on a 3T scanner using an incoherent k-space sampling pattern leading to a breath-hold duration of 14s. We evaluated zero-shot reconstruction of breath-hold MRCP against parallel imaging of respiratory-triggered MRCP acquired in 338s on average and compressed sensing reconstruction of breath-hold MRCP. To address the long computation times of zero-shot trainings, we used a training approach that leverages a pretrained network to reduce backpropagation depth during training. Results: Zero-shot learning reconstruction significantly improved visual image quality compared to compressed sensing reconstruction, particularly in terms of signal-to-noise ratio and ductal delineation, and reached a level of quality comparable to that of successful respiratory-triggered acquisitions with regular breathing patterns. Shallow training provided nearly equivalent reconstruction performance with a training time of 11 minutes in comparison to 271 minutes for a conventional zero-shot training. Conclusion: Zero-shot learning delivers high-fidelity MRCP reconstructions with reduced breath-hold times, and shallow training offers a practical solution for translation to time-constrained clinical workflows.