CT-based generation of synthetic-pseudo MR images with different weightings for human knee

• Published in: Computers in biology and medicine Vol. 169; p. 107842
• Main Authors: Masad, Ihssan S., Abu-Qasmieh, Isam F., Al-Quran, Hiam H., Alawneh, Khaled Z., Abdalla, Khalid M., Al-Qudah, Ali M.
• Format: Journal Article
• Language: English
• Published: United States Elsevier Ltd 01.02.2024; Elsevier Limited
• Subjects: Bone and Bones; Computed tomography; Confined spaces; Deep learning; Feasibility studies; Femur; Human knee; Human subjects; Humans; Image acquisition; Image contrast; Image processing; Image Processing, Computer-Assisted - methods; Image reconstruction; In vivo methods and tests; Internal Medicine; Knee; Knee Joint; Magnetic resonance imaging; Magnetic Resonance Imaging - methods; Medical imaging; Other; Parameters; Proton density (concentration); Radiation; Registration; Soft tissues; Spin echo; Synthetic MRI; Tomography; Tomography, X-Ray Computed; United States > US; Chicago Illinois; Spin echo; Human knee; Computed tomography; Synthetic MRI
• ISSN: 0010-4825; 1879-0534; 1879-0534
• DOI: 10.1016/j.compbiomed.2023.107842

Synthetic MR images are generated for their high soft-tissue contrast avoiding the discomfort by the long acquisition time and placing claustrophobic patients in the MR scanner's confined space. The aim of this study is to generate synthetic pseudo-MR images from a real CT image for the knee region in vivo. 19 healthy subjects were scanned for model training, while 13 other healthy subjects were imaged for testing. The approach used in this work is novel such that the registration was performed between the MR and CT images, and the femur bone, patella, and the surrounding soft tissue were segmented on the CT image. The tissue type was mapped to its corresponding mean and standard deviation values of the CT# of a window moving on each pixel in the reconstructed CT images, which enabled the remapping of the tissue to its MRI intrinsic parameters: T1, T2, and proton density (ρ). To generate the synthetic MR image of a knee slice, a classic spin-echo sequence was simulated using proper intrinsic and contrast parameters. Results showed that the synthetic MR images were comparable to the real images acquired with the same TE and TR values, and the average slope between them (for all knee segments) was 0.98, while the average percentage root mean square difference (PRD) was 25.7%. In conclusion, this study has shown the feasibility and validity of accurately generating synthetic MR images of the knee region in vivo with different weightings from a single real CT image. •Different weighted synthetic MR images were generated from real CT for human knee.•CT#‘s mean & SD in CT image mapped to the corresponding T1, T2 &ρ from MR images.•Synthetic MRIs were generated by simulating SE sequence using T1, T2 &ρ and TE &TR.•Generated MRIs were comparable to the corresponding acquired images with same TE & TR.