Skip to main content
. 2018 Aug 24;5(3):034001. doi: 10.1117/1.JMI.5.3.034001

Algorithm 1.

Pseudo CT prediction using anatomic signature and joint dictionary learning.

1. For each training MR image patch IMR, extract the multiscale and multilevel 3-D RILBP feature fMR.
2. Use fuzzy C-means to segment each corresponding CT ICT into three labels that represent the CT values in the range of bone, soft-tissue and air.
3. For the coupled training MRI features and corresponding CT labels, apply LASSO logistic regression Eq. (1) to select the informative features as an anatomic signature.
4. Use Fisher’s score47 to measure the discriminant power of the anatomic signature to separate bone, air and soft-tissue, and normalize to ω such that ωi=1.
5. For each new arrival MRI image patch IiMR, select its similar patches IijMR from the training patches by computing the weight wij from Eq. (2), and sorting the K-nearest patches by Eq. (3).
6. For the anatomic features fijMR of IijMR and corresponding CT voxels yijCT, initialize the coupled dictionaries: D^MR={fijMR|jNkx×ky×kz(i)\{i}} and D^CT={yijCT|jNkx×ky×kz(i)\{i}}.
7. Use joint dictionary learning [Eq. (4)] to train the coupled dictionary (DMR,DCT).
8. For each new arrival MRI patch, use Eq. (5) to obtain the sparse representation of learned dictionary DMR, and then use Eq. (6) to reconstruct the pseudo CT intensity.