TY - JOUR
T1 - Anatomy-Aware Inference of the 3D Standing Spine Posture from 2D Radiographs
AU - Bayat, Amirhossein
AU - Pace, Danielle F.
AU - Sekuboyina, Anjany
AU - Payer, Christian
AU - Stern, Darko
AU - Urschler, Martin
AU - Kirschke, Jan S.
AU - Menze, Bjoern H.
N1 - Funding Information:
Funding: This research was funded by the European Research Council (ERC) under the European Union’s ‘Horizon 2020’ research & innovation programme (GA637164–iBack–ERC–2014–STG).
Funding Information:
Acknowledgments: The authors would like to thank Polina Golland and Justin Solomon. We also acknowledge support of NIH NIBIB NAC P41EB015902 and Philips Inc.
Publisher Copyright:
© 2022 by the authors. Licensee MDPI, Basel, Switzerland.
PY - 2022/2
Y1 - 2022/2
N2 - 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.
AB - 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.
KW - 3D reconstruction
KW - Neural networks
KW - Registration
KW - Shape priors
KW - Template
UR - http://www.scopus.com/inward/record.url?scp=85124754745&partnerID=8YFLogxK
U2 - 10.3390/tomography8010039
DO - 10.3390/tomography8010039
M3 - Article
C2 - 35202204
AN - SCOPUS:85124754745
VL - 8
SP - 479
EP - 496
JO - Tomography
JF - Tomography
SN - 2379-1381
IS - 1
ER -