Institution-wide shape analysis of 3D spinal curvature and global alignment parameters

Claudia Iriondo, Sarah Mehany, Rutwik Shah, Upasana Bharadwaj, Emma Bahroos, Cynthia Chin, Mohammad Diab, Valentina Pedoia, Sharmila Majumdar, Claudia Iriondo, Sarah Mehany, Rutwik Shah, Upasana Bharadwaj, Emma Bahroos, Cynthia Chin, Mohammad Diab, Valentina Pedoia, Sharmila Majumdar

Abstract

The spine is an articulated, 3D structure with 6 degrees of translational and rotational freedom. Clinical studies have shown spinal deformities are associated with pain and functional disability in both adult and pediatric populations. Clinical decision making relies on accurate characterization of the spinal deformity and monitoring of its progression over time. However, Cobb angle measurements are time-consuming, are limited by interobserver variability, and represent a simplified 2D view of a 3D structure. Instead, spine deformities can be described by 3D shape parameters, addressing the limitations of current measurement methods. To this end, we develop and validate a deep learning algorithm to automatically extract the vertebral midline (from the upper endplate of S1 to the lower endplate of C7) for frontal and lateral radiographs. Our results demonstrate robust performance across datasets and patient populations. Approximations of 3D spines are reconstructed from the unit normalized midline curves of 20,118 pairs of full spine radiographs belonging to 15,378 patients acquired at our institution between 2008 and 2020. The resulting 3D dataset is used to describe global imbalance parameters in the patient population and to build a statistical shape model to describe global spine shape variations in preoperative deformity patients via eight interpretable shape parameters. The developed method can identify patient subgroups with similar shape characteristics without relying on an existing shape classification system.

Keywords: diagnostic imaging; modeling; scoliosis; spine.

© 2021 Orthopaedic Research Society. Published by Wiley Periodicals LLC.

References

REFERENCES

    1. Aebi M. The adult scoliosis. Eur Spine J. 2005;14:925-948.
    1. Veldhuizen AG, Wever DJ, Webb PJ. The aetiology of idiopathic scoliosis: biomechanical and neuromuscular factors. Eur Spine J. 2000;9:178-184.
    1. Konieczny MR, Senyurt H, Krauspe R. Epidemiology of adolescent idiopathic scoliosis. J Child Orthop. 2013;7:3-9.
    1. Carter OD, Haynes SG. Prevalence rates for scoliosis in United-States adults-results from the 1st National-Health and Nutrition Examination Survey. Int J Epidemiol. 1987;16:537-544.
    1. Schwab F, Dubey A, Gamez L, et al. Adult scoliosis: prevalence, SF-36, and nutritional parameters in an elderly volunteer population. Spine. 2005;30:1082-1085.
    1. Théroux J, Le May S, Hebert JJ, Labelle H. Back pain prevalence is associated with curve-type and severity in adolescents with idiopathic scoliosis: a cross-sectional study. Spine (Phila Pa 1976). 2017;42(42):E914-E919.
    1. Mac-Thiong JM, Transfeldt EE, Mehbod AA, et al. Can c7 plumbline and gravity line predict health related quality of life in adult scoliosis? Spine (Phila Pa 1976). 2009;34:E519-E527.
    1. Terran J, Schwab F, Shaffrey CI, et al. The SRS-Schwab adult spinal deformity classification: assessment and clinical correlations based on a prospective operative and nonoperative cohort. Neurosurgery. 2013;73:559-568.
    1. Glassman SD, Bridwell K, Dimar JR, Horton W, Berven S, Schwab F. The impact of positive sagittal balance in adult spinal deformity. Spine (Phila Pa 1976). 2005;30:2024-2029.
    1. Tan KJ, Moe MM, Vaithinathan R, Wong HK. Curve progression in idiopathic scoliosis follow-up study to skeletal maturity. Spine. 2009;34:697-700.
    1. Ascani E, Bartolozzi P, Logroscino CA, et al. Natural-history of untreated idiopathic scoliosis after skeletal maturity. Spine. 1986;11:784-789.
    1. Cobb J Outline for the study of scoliosis. In: Edwards JW, ed, Instructional Course Lectures, The American Academy Orthopaedic Surgeons. 5, 1948:261-275.
    1. Ferguson A. The study and treatment of scoliosis. South Med J. 1930;23:116-120.
    1. Diab KM, Sevastik JA, Hedlund R, Suliman IA. Accuracy and applicability of measurement of the scoliotic angle at the frontal plane by Cobb's method, by Ferguson's method and by a new method. Eur Spine J. 1995;4:291-295.
    1. Morrissy RT, Goldsmith GS, Hall EC, Kehl D, Cowie GH. Measurement of the Cobb angle on radiographs of patients who have scoliosis. Evaluation of intrinsic error. J Bone Joint Surg Am. 1990;72:320-327.
    1. Prabhu GK. HA. Automatic quantification of spinal curvature in scoliotic radiograph using image processing. J Med Syst. 2012;36:1943-1951.
    1. Pan Y, Chen Q, Chen T, et al. Evaluation of a computer-aided method for measuring the Cobb angle on chest X-rays. Eur Spine J. 2019;28:3035-3043.
    1. Zhang T, Li Y, Cheung JPY, Dokos S, Wong KYK. Learning-based coronal spine alignment prediction using smartphone-acquired scoliosis radiograph images. IEEE Access. 2021;9:38287-38295.
    1. Wu H, Bailey C, Rasoulinejad P, Li S. Automated comprehensive Adolescent Idiopathic Scoliosis assessment using MVC-Net. Med Image Anal. 2018;48:1-11.
    1. Galbusera F, Niemeyer F, Wilke HJ, et al. Fully automated radiological analysis of spinal disorders and deformities: a deep learning approach. Eur Spine J. 2019;28:951-960.
    1. Thong W, Parent S, Wu J, Aubin CE, Labelle H, Kadoury S. Three-dimensional morphology study of surgical adolescent idiopathic scoliosis patient from encoded geometric models. Eur Spine J. 2016;25:3104-3113.
    1. Paszke A, Gross S, Massa F, et al. Pytorch: an imperative style, high-performance deep learning library. Adv Neural Inf Process Syst. 2019;32:8026-8037.
    1. Nibali A, He Z, Morgan S, et al. Numerical coordinate regression with convolutional neural networks. arXiv preprint arXiv. 2018;1801:07372.
    1. Huang G, Liu Z, van der Maaten L, Weinberger KQ. Densely connected convolutional networks. 30th Ieee Conference on Computer Vision and Pattern Recognition (Cvpr 2017). 2017:2261-2269.
    1. Yu F, Koltun V, Funkhouser T. Dilated Residual Networks. 30th Ieee Conference on Computer Vision and Pattern Recognition (Cvpr 2017). 2017:636-644.
    1. Bonanni PG. Contour and angle-function based scoliosis monitoring: relaxing the requirement on image quality in the measurement of spinal curvature. Int J Spine Surg. 2017;11:11.
    1. Wu HBC, Rasoulinejad P, Li S. Automatic landmark estimation for adolescent idiopathic scoliosis assessment using BoostNet. Medical image computing and computer assisted intervention-MICCAI 2017. Lect Notes Comput Sci. 2017;10433:127-135.
    1. Pasha S, Flynn J. Data-driven classification of the 3D spinal curve in adolescent idiopathic scoliosis with an applications in surgical outcome prediction. Sci Rep. 2018;8:16296.
    1. Menon KV, Kumar VPD, Thomas T. Experiments with a novel content-based image retrieval software: can we eliminate classification systems in adolescent idiopathic scoliosis? Glob Spine J. 2014;4:13-20.
    1. Nault ML, Mac-Thiong JM, Roy-Beaudry M, et al. Three-dimensional spinal morphology can differentiate between progressive and nonprogressive patients with adolescent idiopathic scoliosis at the initial presentation. Spine. 2014;39:E601-E606.
    1. Donzelli S, Poma S, Balzarini L, et al. State of the art of current 3-D scoliosis classifications: a systematic review from a clinical perspective. J Neuroeng Rehabil. 2015;12:12.
    1. QuinoneroCandela J, Sugiyama M, Schwaighofer A, et al. Dataset shift in machine learning. Neural Inf Process S. 2009:​1-229.
    1. Kadoury S, Cheriet F, Labelle H. Self-calibration of biplanar radiographic images through geometric spine shape descriptors. Ieee T Bio-Med Eng. 2010;57:1663-1675.
    1. Gajny L, Ebrahimi S, Vergari C, Angelini E, Skalli W. Quasi-automatic 3D reconstruction of the full spine from low-dose biplanar X-rays based on statistical inferences and image analysis. Eur Spine J. 2019;28:658-664.
    1. Humbert L, De Guise JA, Aubert B, Godbout B, Skalli W. 3D reconstruction of the spine from biplanar X-rays using parametric models based on transversal and longitudinal inferences. Med Eng Phys. 2009;31:681-687.
    1. Deschênes S, Charron G, Beaudoin G, et al. Diagnostic imaging of spinal deformities reducing patients radiation dose with a new slot-scanning X-ray Imager. Spine. 2010;35:989-994.
    1. Somoskeöy S, Tunyogi-Csapó M, Bogyó C, Illés T. Accuracy and reliability of coronal and sagittal spinal curvature data based on patient-specific three-dimensional models created by the EOS 2D/3D imaging system. Spine Journal. 2012;12:1052-1059.
    1. Gardner A, Archer J, Berryman F, Pynsent P. The resting coronal and sagittal stance position of the torso in adolescents with and without spinal deformity. Sci Rep. 2021;11:2354.
    1. Ilharreborde B, Steffen JS, Nectoux E, et al. Angle measurement reproducibility using EOS three-dimensional reconstructions in adolescent idiopathic scoliosis treated by posterior instrumentation. Spine (Phila Pa 1976). 2011;36:E1306-E1313.
    1. Chen K, Zhai X, Sun KQ, et al. A narrative review of machine learning as promising revolution in clinical practice of scoliosis. Ann Transl Med. 2021:9(1):67-83.

Source: PubMed

Sponsors et collaborateurs

Les conditions médicales

Interventions en matière de drogue

3
S'abonner