An efficient CEST workflow using joint optimization of sampling, reconstruction and quantification

Motivation: As an exciting ‘label-free' molecular imaging technique, CEST workflow is always time-consuming, because of the seconds-long TR and multiple frequency repetitions in acquisition, the iteration in reconstruction, and the pixel-by-pixel in B0 correction and quantification. Goal(s): To achieve rapid and high-quality sampling, reconstruction and quantification of CEST-MRI. Approach: We constructed a data-driven CEST framework, by joint optimization of k-space sampling, reconstruction and quantification. Results: Retrospective experiments on human brain demonstrated the feasibility of combination with acceleration techniques including parallel imaging, compress sensing or deep learning, allowing 6X under-sampling rate and reconstruction of high-quality contrast maps in one second. Impact: A data-driven CEST framework enabled joint optimization of k-space sampling,reconstruction and quantification. Retrospective experiments demonstrated that the the framework allows 6X under-sampling rate and reconstruction of high-quality contrast maps in one second. This one-stop workflow may facilitate more clinical needs.