Synthetic cranial MRI from 3D optical surface scans using deep learning for radiation therapy treatment planning

• Published in: Australasian physical & engineering sciences in medicine Vol. 46; no. 1; pp. 367 - 375
• Main Authors: Douglass, Michael, Gorayski, Peter, Patel, Sandy, Santos, Alexandre
• Format: Journal Article
• Language: English
• Published: Cham Springer International Publishing 01.03.2023; Springer Nature B.V
• Subjects: Accuracy; Adult; Anatomy; Biological and Medical Physics; Biomedical and Life Sciences; Biomedical Engineering and Bioengineering; Biomedicine; Biophysics; Brachytherapy; Datasets; Deep Learning; Feasibility; Generative adversarial networks; Humans; Image segmentation; Magnetic resonance imaging; Magnetic Resonance Imaging - methods; Medical and Radiation Physics; Medical imaging; Model accuracy; Photogrammetry; Radiation therapy; Radiotherapy Planning, Computer-Assisted - methods; Scanning; Scientific Paper; Three dimensional models; Three dimensional printing; Tomography, X-Ray Computed - methods; Deep learning; Synthetic; GAN; MRI; Radiation oncology; pix2pix; 3D scan; Treatment planning; Photogrammetry
• ISSN: 2662-4729; 0158-9938; 2662-4737; 2662-4737; 1879-5447
• DOI: 10.1007/s13246-023-01229-4

Background Optical scanning technologies are increasingly being utilised to supplement treatment workflows in radiation oncology, such as surface-guided radiotherapy or 3D printing custom bolus. One limitation of optical scanning devices is the absence of internal anatomical information of the patie...