Anatomy-Aware Inference of the 3D Standing Spine Posture from 2D Radiographs
Name
tomography-08-00039.pdf
Size
4.18 MB
Format
Adobe PDF
Checksum (MD5)
b49a874749fd12f99d88d6d40c26cb3e
Author(s)
Bayat, Amirhossein
Pace, Danielle F.
Sekuboyina, Anjany
Payer, Christian
Stern, Darko
Urschler, Martin
Kirschke, Jan S.
Menze, Bjoern H.
Date Issued
February 11, 2022
Journal
Tomography
Publisher
Multidisciplinary Digital Publishing Institute
Citation
Bayat, A.; Pace, D.F.; Sekuboyina, A.; Payer, C.; Stern, D.; Urschler, M.; Kirschke, J.S.; Menze, B.H. Anatomy-Aware Inference of the 3D Standing Spine Posture from 2D Radiographs. Tomography 8 (1): 479-496 (2022)
Version
Final published version
Abstract
An important factor for the development of spinal degeneration, pain and the outcome of spinal surgery is known to be the balance of the spine. It must be analyzed in an upright, standing position to ensure physiological loading conditions and visualize load-dependent deformations. Despite the complex 3D shape of the spine, this analysis is currently performed using 2D radiographs, as all frequently used 3D imaging techniques require the patient to be scanned in a prone position. To overcome this limitation, we propose a deep neural network to reconstruct the 3D spinal pose in an upright standing position, loaded naturally. Specifically, we propose a novel neural network architecture, which takes orthogonal 2D radiographs and infers the spine’s 3D posture using vertebral shape priors. In this work, we define vertebral shape priors using an atlas and a spine shape prior, incorporating both into our proposed network architecture. We validate our architecture on digitally reconstructed radiographs, achieving a 3D reconstruction Dice of 0.95, indicating an almost perfect 2D-to-3D domain translation. Validating the reconstruction accuracy of a 3D standing spine on real data is infeasible due to the lack of a valid ground truth. Hence, we design a novel experiment for this purpose, using an orientation invariant distance metric, to evaluate our model’s ability to synthesize full-3D, upright, and patient-specific spine models. We compare the synthesized spine shapes from clinical upright standing radiographs to the same patient’s 3D spinal posture in the prone position from CT.
MIT Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Terms of Use
Creative Commons Attribution
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.3390/tomography8010039
