Anatomy-Aware Inference of the 3D Standing Spine Posture from 2D Radiographs
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 compl...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-02-01
|
| Series: | Tomography |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2379-139X/8/1/39 |
| _version_ | 1797476329536356352 |
|---|---|
| author | Amirhossein Bayat Danielle F. Pace Anjany Sekuboyina Christian Payer Darko Stern Martin Urschler Jan S. Kirschke Bjoern H. Menze |
| author_facet | Amirhossein Bayat Danielle F. Pace Anjany Sekuboyina Christian Payer Darko Stern Martin Urschler Jan S. Kirschke Bjoern H. Menze |
| author_sort | Amirhossein Bayat |
| collection | DOAJ |
| description | 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 <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>0.95</mn></mrow></semantics></math></inline-formula>, 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. |
| first_indexed | 2024-03-09T20:56:20Z |
| format | Article |
| id | doaj.art-50623fd1f7d54a088041b51bf57551a1 |
| institution | Directory Open Access Journal |
| issn | 2379-1381 2379-139X |
| language | English |
| last_indexed | 2024-03-09T20:56:20Z |
| publishDate | 2022-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Tomography |
| spelling | doaj.art-50623fd1f7d54a088041b51bf57551a12023-11-23T22:19:50ZengMDPI AGTomography2379-13812379-139X2022-02-018147949610.3390/tomography8010039Anatomy-Aware Inference of the 3D Standing Spine Posture from 2D RadiographsAmirhossein Bayat0Danielle F. Pace1Anjany Sekuboyina2Christian Payer3Darko Stern4Martin Urschler5Jan S. Kirschke6Bjoern H. Menze7Department of Computer Science, Technical University of Munich, 85748 Garching, GermanyComputer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA 02139, USADepartment of Computer Science, Technical University of Munich, 85748 Garching, GermanyInstitute of Computer Graphics and Vision, Graz University of Technology, 8010 Graz, AustriaInstitute of Computer Graphics and Vision, Graz University of Technology, 8010 Graz, AustriaSchool of Computer Science, University of Auckland, Auckland 1010, New ZealandDepartment of Neuroradiology, Klinikum rech der Isar, 81675 Munich, GermanyDepartment of Computer Science, Technical University of Munich, 85748 Garching, GermanyAn 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 <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>0.95</mn></mrow></semantics></math></inline-formula>, 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.https://www.mdpi.com/2379-139X/8/1/393D reconstructionshape priorsneural networksregistrationtemplate |
| spellingShingle | Amirhossein Bayat Danielle F. Pace Anjany Sekuboyina Christian Payer Darko Stern Martin Urschler Jan S. Kirschke Bjoern H. Menze Anatomy-Aware Inference of the 3D Standing Spine Posture from 2D Radiographs Tomography 3D reconstruction shape priors neural networks registration template |
| title | Anatomy-Aware Inference of the 3D Standing Spine Posture from 2D Radiographs |
| title_full | Anatomy-Aware Inference of the 3D Standing Spine Posture from 2D Radiographs |
| title_fullStr | Anatomy-Aware Inference of the 3D Standing Spine Posture from 2D Radiographs |
| title_full_unstemmed | Anatomy-Aware Inference of the 3D Standing Spine Posture from 2D Radiographs |
| title_short | Anatomy-Aware Inference of the 3D Standing Spine Posture from 2D Radiographs |
| title_sort | anatomy aware inference of the 3d standing spine posture from 2d radiographs |
| topic | 3D reconstruction shape priors neural networks registration template |
| url | https://www.mdpi.com/2379-139X/8/1/39 |
| work_keys_str_mv | AT amirhosseinbayat anatomyawareinferenceofthe3dstandingspineposturefrom2dradiographs AT daniellefpace anatomyawareinferenceofthe3dstandingspineposturefrom2dradiographs AT anjanysekuboyina anatomyawareinferenceofthe3dstandingspineposturefrom2dradiographs AT christianpayer anatomyawareinferenceofthe3dstandingspineposturefrom2dradiographs AT darkostern anatomyawareinferenceofthe3dstandingspineposturefrom2dradiographs AT martinurschler anatomyawareinferenceofthe3dstandingspineposturefrom2dradiographs AT janskirschke anatomyawareinferenceofthe3dstandingspineposturefrom2dradiographs AT bjoernhmenze anatomyawareinferenceofthe3dstandingspineposturefrom2dradiographs |