Publications by authors named "Junxian Jin"
Purpose: To develop a deep learning-based approach to reduce the scan time of multipool CEST MRI for Parkinson's disease (PD) while maintaining sufficient prediction accuracy.
Method: A deep learning approach based on a modified one-dimensional U-Net, termed Z-spectral compressed sensing (CS), was proposed to recover dense Z-spectra from sparse ones. The neural network was trained using simulated Z-spectra generated by the Bloch equation with various parameter settings.
Article Synopsis
- T and T* mapping are important for assessing tissue characteristics in MRI, but traditional methods face challenges like image quality issues due to long echo trains.
- A new single-shot method using spatiotemporally encoded MRI and an efficient spiral acquisition technique has been developed to achieve T and T* mapping with a shorter echo train length.
- This method produced accurate mapping results with minimal differences from reference maps, showing promise for use in dynamic imaging situations such as monitoring free-breathing subjects.