Accurate quantitative parameter maps reconstruction method for tsDESPOT using Low Rank approximated Unet ADMM
Yuuzo Kamiguchi1, Sadanori Tomiha2, and Masao Yui3
1Advanced Technology Reserch Dept. Reserch and Development Center, Canon Medical Systems Corporation, Kawasaki, Japan, 2Advanced Technology Reserch Dept. Reserch and Development Center, Canon Medical Systems Corporation, Otawara, Japan, 3Reserch and Development Center, Canon Medical Systems Corporation, Otawara, Japan
From the data
acquired by DESPOT like sequence, full sampled low rank approximated images were estimated using ADMM method which optimize Unet estimation
and data consistency, then accurate quantitative maps were obtained by dense
neural network.
Figure 4. Representative T1, T2, B1 and PD maps of
numerical and real NIST system phantom obtained using three reconstruction
methods.
Figure 5. Mean estimated value of T1, T2, and their relative
errors in each region of numerical and real NIST system phantoms as function of
their true and nominal value each other.