Abstract
Purpose
In adolescent idiopathic scoliosis (AIS), non-invasive surgical techniques such as anterior vertebral body tethering (AVBT) enable to treat patients with mild and severe degrees of deformity while maintaining lower lumbar motion by avoiding spinal fusion. However, multiple features and characteristics affect the overall patient outcome, notably the 3D spine geometry and bone maturity, but also from decisions taken intra-operatively such as the selected tethered vertebral levels, which makes it difficult to anticipate the patient response.
Methods
We propose here a forecasting method which can be used during AVBT surgery, exploiting the spatio-temporal features extracted from a dynamic networks. The model learns the corrective effect from the spine’s different segments while taking under account the time differences in the initial diagnosis and between the serial acquisitions taken before and during surgery. Clinical parameters are integrated through an attention-based decoder, allowing to associate geometrical features to patient status. Long-term relationships allow to ensure regularity in geometrical curve prediction, using a manifold-based smoothness term to regularize geometrical outputs, capturing the temporal variations of spine correction.
Results
A dataset of 695 3D spine reconstructions was used to train the network, which was evaluated on a hold-out dataset of 72 scoliosis patients using the baseline 3D reconstruction obtained prior to surgery, yielding an overall reconstruction error of \(1.8 \pm 0.8\)mm based on pre-identified landmarks on vertebral bodies. The model was also tested prospectively on a separate cohort of 15 AIS patients, demonstrating the integration within the OR theatre.
Conclusion
The proposed predictive network allows to intra-operatively anticipate the geometrical response of the spine to AVBT procedures using the dynamic features.
Similar content being viewed by others
References
Bai W, Suzuki H, Qin C, Tarroni G, Oktay O, Matthews PM, Rueckert D (2018) Recurrent neural networks for aortic image sequence segmentation with sparse annotations. In: International conference on medical image computing and computer-assisted intervention, pp 586–594. Springer
Beauséjour M, Roy-Beaudry M, Goulet L, Labelle H (2007) Patient characteristics at the initial visit to a scoliosis clinic: a cross-sectional study in a community without school screening. Spine 32(12):1349–1354
Cheng JC, Castelein RM, Chu WC, Danielsson AJ, Dobbs MB, Grivas TB, Gurnett CA, Luk KD, Moreau A, Newton PO et al (2015) Adolescent idiopathic scoliosis. Nat Rev Disease Primers 1(1):1–21
Cobetto N, Parent S, Aubin CE (2018) 3D correction over 2 years with anterior vertebral body growth modulation: a finite element analysis of screw positioning, cable tensioning and postop functional activities. Clin Biom 51:26–33
Drozdzal M, Chartrand G, Vorontsov E, Shakeri M, Di Jorio L, Tang A, Romero A, Bengio Y, Pal C, Kadoury S (2018) Learning normalized inputs for iterative estimation in medical image segmentation. Med Image Anal 44:1–13
Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9(8):1735–1780
Huang G, Liu Z, Van Der Maaten L, Weinberger KQ (2017) Densely connected convolutional networks. In: Proceedings oFf the IEEE conference on computer vision and pattern recognition, pp 4700–4708
Humbert L, de Guise J, Aubert B, Godbout B, Skalli W (2009) 3D reconstruction of the spine from biplanar X-rays using parametric models based on transversal and longitudinal inferences. Med Eng Phy 31(6):681–87
Kadoury S, Mandel W, Nault Roy-Beaudry ML, ., Parent S (2017) 3-D morphology prediction of progressive spinal deformities from probabilistic modeling of discriminant manifolds. IEEE Trans Med Imag 36(5):1194–1204
Kingma DP, Ba J (2014) Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980
Labelle H, Aubin CE, Jackson R, Lenke L, Newton P, Parent S (2011) Seeing the spine in 3d: how will it change what we do? J Pediatr Orthopaed 31:S37–S45
Luong MT, Pham H, Manning CD (2015) Effective approaches to attention-based neural machine translation. arXiv preprint arXiv:1508.04025
Mandel W, Oulbacha R, Roy-Beaudry M, Parent S, Kadoury S (2020) Image-guided tethering spine surgery with outcome prediction using spatio-temporal dynamic networks. IEEE Trans Med Imaging
Mandel W, Parent S, Kadoury S (2020) Intra-operative forecasting of growth modulation spine surgery outcomes with spatio-temporal dynamic networks. In: International conference on medical image computing and computer-assisted intervention, pp 751–760. Springer
Mandel W, Turcot O, Knez D, Parent S, Kadoury S (2018) Spatiotemporal manifold prediction model for anterior vertebral body growth modulation surgery in idiopathic scoliosis. In: International conference on medical image computing and computer-assisted intervention, pp 206–213. Springer
Mandel W, Turcot O, Knez D, Parent S, Kadoury S (2019) Prediction outcomes for anterior vertebral body growth modulation surgery from discriminant spatiotemporal manifolds. Int J Comput Assist Radiol Surg 14(9):1565–1575
Nault ML, Mac-Thiong JM, Roy-Beaudry M, Turgeon I, Parent S (2014) Three-dimensional spinal morphology can differentiate between progressive and nonprogressive patients with adolescent idiopathic scoliosis at the initial presentation: a prospective study. Spine 39(10):E601
Newton PO, Bartley CE, Bastrom TP, Kluck DG, Saito W, Yaszay B (2020) Anterior spinal growth modulation in skeletally immature patients with idiopathic scoliosis: a comparison with posterior spinal fusion at 2 to 5 years postoperatively. JBJS 102(9):769–777
Newton PO, Kluck DG, Saito W, Yaszay B, Bartley CE, Bastrom TP (2018) Anterior spinal growth tethering for skeletally immature patients with scoliosis: a retrospective look two to four years postoperatively. JBJS 100(19):1691–1697
Parent S, Newton P, Wenger D (2005) Adolescent idiopathic scoliosis: etiology, anatomy, natural history, and bracing. Instr Course Lect 54:529–536
Park M, Jitkrittum W, Qamar A, Szabó Z, Buesing L, Sahani M (2015) Bayesian manifold learning: the locally linear latent variable model (ll-lvm). In: Advances in neural information processing systems, pp 154–162
Samdani AF, Ames RJ, Kimball JS, Pahys JM, Grewal H, Pelletier GJ, Betz RR (2014) Anterior vertebral body tethering for idiopathic scoliosis: two-year results. Spine 39(20):1688–1693
Samdani AF, Ames RJ, Kimball JS, Pahys JM, Grewal H, Pelletier GJ, Betz RR (2015) Anterior vertebral body tethering for immature adolescent idiopathic scoliosis: one-year results on the first 32 patients. Eur Spine J 24(7):1533–1539
Szegedy C, Ioffe S, Vanhoucke V, Alemi AA (2017) Inception-v4, inception-resnet and the impact of residual connections on learning. In: Thirty-First AAAI conference on artificial intelligence
Thong W, Parent S, Wu J, Aubin CE, Labelle H, Kadoury S (2016) Three-dimensional morphology study of surgical adolescent idiopathic scoliosis patient from encoded geometric models. Eur Spine J 25(10):3104–13
Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser L, Polosukhin I (2017) Attention is all you need. arXiv preprint arXiv:1706.03762
Wong HK, Ruiz JNM, Newton PO, Liu KPG (2019) Non-fusion surgical correction of thoracic idiopathic scoliosis using a novel, braided vertebral body tethering device: minimum follow-up of 4 years. JBJS Open Access 4(4)
Yao H, Tang X, Wei H, Zheng G, Li Z (2019) Revisiting spatial-temporal similarity: a deep learning framework for traffic prediction. Proc AAAI Conf Artif Intell 33:5668–5675
Zhang J, Zheng Y, Qi D (2017) Deep spatio-temporal residual networks for citywide crowd flows prediction. In: Thirty-first AAAI conference on artificial intelligence
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Funding
This study funded by the Canada Research Chairs (950-228359) and the National Science and Engineering Research Council (NSERC) of Canada.
Conflict of interest
The authors declare that they have no conflict of interests.
Ethical approval
All procedures performed in studies involving human participants were in accordance with the ethical standards of the institutional and/or national research committee and with the 1964 Helsinki Declaration and its later amendments or comparable ethical standards. All applicable international, national and/or institutional guidelines for the care and use of animals were followed. All procedures performed in studies involving animals were in accordance with the ethical standards of the institution or practice at which the studies were conducted.
Informed consent
For this type of study formal consent was not required.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Mandel, W., Parent, S. & Kadoury, S. Intra-operative forecasting of growth modulation spine surgery outcomes with spatio-temporal dynamic networks. Int J CARS 16, 1641–1651 (2021). https://doi.org/10.1007/s11548-021-02461-7
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11548-021-02461-7