Keywords: Super-resolution, Low-field MRI, Hyperfine, Domain adaptation
TL;DR: We propose a method for super-resolution (SR) of low-field MRI integrating a denoiser, a domain adaptation and a SR module and achieve a good correlation (ρ>0.8) in the output segmented volumes with the clinical high-field MRI data.
Abstract: Portable low-field MRI has the potential to revolutionize neuroimaging, by enabling point-of-care imaging and affordable scanning in underserved areas. The lower resolution and signal-to-noise ratio of these scans preclude image analysis with existing tools. Super-resolution (SR) methods can overcome this limitation, but: (i) training with downsampled high-field scans fails to generalize; and (ii) training with paired low/high-field data is hard due to the lack of perfectly aligned images. Here, we present an architecture that combines denoising, SR and domain adaptation modules to tackle this problem. The denoising and SR components are pretrained in a supervised fashion with large amounts of existing high-resolution data, whereas unsupervised learning is used for domain adaptation and end-to-end finetuning. We present preliminary results on a dataset of 11 low-field scans. The results show that our method enables segmentation with existing tools, which yield ROI volumes that correlate strongly with those derived from high-field scans (ρ > 0.8).
Registration: I acknowledge that acceptance of this work at MIDL requires at least one of the authors to register and present the work during the conference.
Authorship: I confirm that I am the author of this work and that it has not been submitted to another publication before.
Paper Type: novel methodological ideas without extensive validation
Primary Subject Area: Image Synthesis
Secondary Subject Area: Transfer Learning and Domain Adaptation
Confidentiality And Author Instructions: I read the call for papers and author instructions. I acknowledge that exceeding the page limit and/or altering the latex template can result in desk rejection.