Multi-orientation U-Net for Super-Resolution of Ultra-Low-Field Paediatric MRI
Purpose: Owing to the high cost of modern MRI systems, their use in clinical care and neurodevelopmental research is limited to hospitals and universities in high income countries. Ultra-low-field systems with significantly lower scanning costs bear the potential for global adoption, however their reduced SNR compared to 1.5 or 3T systems limits their applicability for research and clinical use. Methods: In this paper, we describe a deep-learning based super-resolution approach to generate high-resolution isotropic T2-weighted scans from low-resolution inputs. We train a multi-orientation U-Net, which uses multiple low-resolution anisotropic images acquired in orthogonal orientations to construct a super-resolved output. Results: Our approach exhibits improved quality of outputs compared to current state-of-the-art methods for super-resolution of ultra-low-field scans in paediatric populations. The average correlation value between volume estimates from high-field scans and super-resolved outputs rises to 0.77 using our method, compared to 0.71 using earlier techniques. Conclusion: Our research serves as proof-of-principle of the viability of training deep-learning based super-resolution models for use in neurodevelopmental research and presents the first U-Net trained exclusively on paired ultra-low-field and high-field data from infants.