Abstract
This paper introduces a new computational imaging technique called image quality transfer (IQT). IQT uses machine learning to transfer the rich information available from one-off experimental medical imaging devices to the abundant but lower-quality data from routine acquisitions. The procedure uses matched pairs to learn mappings from low-quality to corresponding high-quality images. Once learned, these mappings then augment unseen low quality images, for example by enhancing image resolution or information content. Here, we demonstrate IQT using a simple patch-regression implementation and the uniquely rich diffusion MRI data set from the human connectome project (HCP). Results highlight potential benefits of IQT in both brain connectivity mapping and microstructure imaging. In brain connectivity mapping, IQT reveals, from standard data sets, thin connection pathways that tractography normally requires specialised data to reconstruct. In microstructure imaging, IQT shows potential in estimating, from standard “single-shell” data (one non-zero b-value), maps of microstructural parameters that normally require specialised multi-shell data. Further experiments show strong generalisability, highlighting IQT's benefits even when the training set does not directly represent the application domain. The concept extends naturally to many other imaging modalities and reconstruction problems.
Highlights
Bespoke MRI scanners and imaging protocols can produce very high quality data uniquely informative on anatomy and physiology
neurite orientation dispersion and density imaging (NODDI) maps indices of neurite density and their geometric configuration; spherical mean technique (SMT) (Kaden et al, 2016) maps the per-axon microscopic diffusion tensor independent of intra-voxel orientation distribution, as well as orientation dispersion. Both exemplify the microstructure-imaging paradigm (Assaf et al, 2013), but require non-standard multi-shell acquisitions with multiple non-zero b-values and fail given single-shell data sets, which are routinely acquired for diffusion tensor imaging (DTI) (Basser et al, 1994)
We demonstrate image quality transfer (IQT) parameter mapping by reconstructing NODDI and SMT maps from single-shell DTI maps
Summary
Bespoke MRI scanners and imaging protocols can produce very high quality data uniquely informative on anatomy and physiology. The mapping may operate directly on low-quality images to estimate the corresponding high-quality images, or serve as a prior in an otherwise ill-posed imagereconstruction routine Such a procedure has the potential to enhance or enable a wide range of desirable imaging or image analysis operations. NODDI maps indices of neurite (axons and dendrites) density and their geometric configuration (orientation dispersion); SMT (Kaden et al, 2016) maps the per-axon microscopic diffusion tensor independent of intra-voxel orientation distribution, as well as orientation dispersion Both exemplify the microstructure-imaging paradigm (Assaf et al, 2013), but require non-standard multi-shell acquisitions with multiple non-zero b-values and fail given single-shell data sets, which are routinely acquired for diffusion tensor imaging (DTI) (Basser et al, 1994). The data sets in Golkov et al (2016) are still multishell so the parameter-estimation problem remains well posed
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
