Development and validation of an artificial intelligence model to accurately predict spinopelvic parameters

Edward S. Harake School of Medicine and Departments of

Search for other papers by Edward S. Harake in
jns
Google Scholar
PubMed
Close
 MM
,
Joseph R. Linzey Neurosurgery,

Search for other papers by Joseph R. Linzey in
jns
Google Scholar
PubMed
Close
 MD, MS
,
Cheng Jiang Computational Medicine and Bioinformatics, and

Search for other papers by Cheng Jiang in
jns
Google Scholar
PubMed
Close
 MSE
,
Rushikesh S. Joshi Neurosurgery,

Search for other papers by Rushikesh S. Joshi in
jns
Google Scholar
PubMed
Close
 MD
,
Mark M. Zaki Neurosurgery,

Search for other papers by Mark M. Zaki in
jns
Google Scholar
PubMed
Close
 MD, MBA
,
Jaes C. Jones Neurosurgery,

Search for other papers by Jaes C. Jones in
jns
Google Scholar
PubMed
Close
 MD, MS
,
Siri Sahib S. Khalsa Department of Neurosurgery, Wexner Medical Center, The Ohio State University, Columbus, Ohio; and

Search for other papers by Siri Sahib S. Khalsa in
jns
Google Scholar
PubMed
Close
 MD
,
John H. Lee School of Medicine and Departments of

Search for other papers by John H. Lee in
jns
Google Scholar
PubMed
Close
 BS
,
Zachary Wilseck Radiology, University of Michigan, Ann Arbor, Michigan;

Search for other papers by Zachary Wilseck in
jns
Google Scholar
PubMed
Close
 MD
,
Jacob R. Joseph Neurosurgery,

Search for other papers by Jacob R. Joseph in
jns
Google Scholar
PubMed
Close
 MD
,
Todd C. Hollon Neurosurgery,

Search for other papers by Todd C. Hollon in
jns
Google Scholar
PubMed
Close
 MD
, and
Paul Park Department of Neurosurgery, Semmes Murphey Neurologic and Spine Institute, University of Tennessee, Memphis, Tennessee

Search for other papers by Paul Park in
jns
Google Scholar
PubMed
Close
 MD
Restricted access

Purchase Now

USD  $45.00

Spine - 1 year subscription bundle (Individuals Only)

USD  $392.00

JNS + Pediatrics + Spine - 1 year subscription bundle (Individuals Only)

USD  $636.00
USD  $45.00
USD  $392.00
USD  $636.00
Print or Print + Online Sign in

OBJECTIVE

Achieving appropriate spinopelvic alignment has been shown to be associated with improved clinical symptoms. However, measurement of spinopelvic radiographic parameters is time-intensive and interobserver reliability is a concern. Automated measurement tools have the promise of rapid and consistent measurements, but existing tools are still limited to some degree by manual user-entry requirements. This study presents a novel artificial intelligence (AI) tool called SpinePose that automatically predicts spinopelvic parameters with high accuracy without the need for manual entry.

METHODS

SpinePose was trained and validated on 761 sagittal whole-spine radiographs to predict the sagittal vertical axis (SVA), pelvic tilt (PT), pelvic incidence (PI), sacral slope (SS), lumbar lordosis (LL), T1 pelvic angle (T1PA), and L1 pelvic angle (L1PA). A separate test set of 40 radiographs was labeled by four reviewers, including fellowship-trained spine surgeons and a fellowship-trained radiologist with neuroradiology subspecialty certification. Median errors relative to the most senior reviewer were calculated to determine model accuracy on test images. Intraclass correlation coefficients (ICCs) were used to assess interrater reliability.

RESULTS

SpinePose exhibited the following median (interquartile range) parameter errors: SVA 2.2 mm (2.3 mm) (p = 0.93), PT 1.3° (1.2°) (p = 0.48), SS 1.7° (2.2°) (p = 0.64), PI 2.2° (2.1°) (p = 0.24), LL 2.6° (4.0°) (p = 0.89), T1PA 1.1° (0.9°) (p = 0.42), and L1PA 1.4° (1.6°) (p = 0.49). Model predictions also exhibited excellent reliability at all parameters (ICC 0.91–1.0).

CONCLUSIONS

SpinePose accurately predicted spinopelvic parameters with excellent reliability comparable to that of fellowship-trained spine surgeons and neuroradiologists. Utilization of predictive AI tools in spinal imaging can substantially aid in patient selection and surgical planning.

ABBREVIATIONS

AI = artificial intelligence; ASD = adult spinal deformity; CNN = convolutional neural network; EMERSE = Electronic Medical Record Search Engine; ICC = intraclass correlation coefficient; IQR = interquartile range; IT = information technology; L1PA = L1 pelvic angle; LL = lumbar lordosis; PCK = percent correct key point; PI = pelvic incidence; PT = pelvic tilt; SS = sacral slope; SVA = sagittal vertical axis; T1PA = T1 pelvic angle.
  • Collapse
  • Expand
  • 1

    Jackson RP, McManus AC. Radiographic analysis of sagittal plane alignment and balance in standing volunteers and patients with low back pain matched for age, sex, and size. A prospective controlled clinical study. Spine (Phila Pa 1976). 1994;19(14):16111618.

    • PubMed
    • Search Google Scholar
    • Export Citation
  • 2

    Le Huec JC, Thompson W, Mohsinaly Y, Barrey C, Faundez A. Sagittal balance of the spine. Eur Spine J. 2019;28(9):18891905.

  • 3

    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(4):559568.

    • PubMed
    • Search Google Scholar
    • Export Citation
  • 4

    Liu Y, Liu Z, Zhu F, et al. Validation and reliability analysis of the new SRS-Schwab classification for adult spinal deformity. Spine (Phila Pa 1976). 2013;38(11):902908.

    • PubMed
    • Search Google Scholar
    • Export Citation
  • 5

    Schwab FJ, Blondel B, Bess S, et al. Radiographical spinopelvic parameters and disability in the setting of adult spinal deformity: a prospective multicenter analysis. Spine (Phila Pa 1976). 2013;38(13):E803E812.

    • PubMed
    • Search Google Scholar
    • Export Citation
  • 6

    Ha KY, Jang WH, Kim YH, Park DC. Clinical relevance of the SRS-Schwab classification for degenerative lumbar scoliosis. Spine (Phila Pa 1976). 2016;41(5):E282E288.

    • PubMed
    • Search Google Scholar
    • Export Citation
  • 7

    Protopsaltis TS, Soroceanu A, Tishelman JC, et al. Should sagittal spinal alignment targets for adult spinal deformity correction depend on pelvic incidence and age? Spine (Phila Pa 1976). 2020;45(4):250257.

    • PubMed
    • Search Google Scholar
    • Export Citation
  • 8

    Glassman SD, Berven S, Bridwell K, Horton W, Dimar JR. Correlation of radiographic parameters and clinical symptoms in adult scoliosis. Spine (Phila Pa 1976). 2005;30(6):682688.

    • PubMed
    • Search Google Scholar
    • Export Citation
  • 9

    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(18):20242029.

    • PubMed
    • Search Google Scholar
    • Export Citation
  • 10

    Smith JS, Klineberg E, Schwab F, et al. Change in classification grade by the SRS-Schwab adult spinal deformity classification predicts impact on health-related quality of life measures: prospective analysis of operative and nonoperative treatment. Spine (Phila Pa 1976). 2013;38(19):16631671.

    • PubMed
    • Search Google Scholar
    • Export Citation
  • 11

    Diebo BG, Varghese JJ, Lafage R, Schwab FJ, Lafage V. Sagittal alignment of the spine: what do you need to know? Clin Neurol Neurosurg. 2015;139:295301.

  • 12

    Kieser DC, Boissiere L, Cawley DT, et al. Validation of a simplified SRS-Schwab classification using a sagittal modifier. Spine Deform. 2019;7(3):467471.

  • 13

    Bergeron C, Cheriet F, Ronsky J, Zernicke R, Labelle H. Prediction of anterior scoliotic spinal curve from trunk surface using support vector regression. Eng Appl Artif Intell. 2005;18(8):973983.

    • PubMed
    • Search Google Scholar
    • Export Citation
  • 14

    Jaremko JL, Poncet P, Ronsky J, et al. Estimation of spinal deformity in scoliosis from torso surface cross sections. Spine (Phila Pa 1976). 2001;26(14):15831591.

  • 15

    Komeili A, Westover L, Parent EC, El-Rich M, Adeeb S. Monitoring for idiopathic scoliosis curve progression using surface topography asymmetry analysis of the torso in adolescents. Spine J. 2015;15(4):743751.

    • PubMed
    • Search Google Scholar
    • Export Citation
  • 16

    Ramirez L, Durdle NG, Raso VJ, Hill DL. A support vector machines classifier to assess the severity of idiopathic scoliosis from surface topography. IEEE Trans Inf Technol Biomed. 2006;10(1):8491.

    • PubMed
    • Search Google Scholar
    • Export Citation
  • 17

    Watanabe K, Aoki Y, Matsumoto M. An application of artificial intelligence to diagnostic imaging of spine disease: estimating spinal alignment from Moiré images. Neurospine. 2019;16(4):697702.

    • PubMed
    • Search Google Scholar
    • Export Citation
  • 18

    Yang J, Zhang K, Fan H, et al. Development and validation of deep learning algorithms for scoliosis screening using back images. Commun Biol. 2019;2:390.

  • 19

    Schwartz JT, Cho BH, Tang P, et al. Deep learning automates measurement of spinopelvic parameters on lateral lumbar radiographs. Spine (Phila Pa 1976). 2021;46(12):E671E678.

    • PubMed
    • Search Google Scholar
    • Export Citation
  • 20

    Orosz LD, Bhatt FR, Jazini E, et al. Novel artificial intelligence algorithm: an accurate and independent measure of spinopelvic parameters. J Neurosurg Spine. 2022;37(6):893901.

    • PubMed
    • Search Google Scholar
    • Export Citation
  • 21

    Hanauer DA, Mei Q, Law J, Khanna R, Zheng K. Supporting information retrieval from electronic health records: a report of University of Michigan’s nine-year experience in developing and using the Electronic Medical Record Search Engine (EMERSE). J Biomed Inform. 2015;55:290300.

    • PubMed
    • Search Google Scholar
    • Export Citation
  • 22

    Liljequist D, Elfving B, Skavberg Roaldsen K. Intraclass correlation—a discussion and demonstration of basic features. PLoS One. 2019;14(7):e0219854.

  • 23

    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(5):951960.

    • PubMed
    • Search Google Scholar
    • Export Citation
  • 24

    Weng CH, Wang CL, Huang YJ, et al. Artificial intelligence for automatic measurement of sagittal vertical axis using ResUNet framework. J Clin Med. 2019;8(11):1826.

  • 25

    Yeh YC, Weng CH, Huang YJ, Fu CJ, Tsai TT, Yeh CY. Deep learning approach for automatic landmark detection and alignment analysis in whole-spine lateral radiographs. Sci Rep. 2021;11(1):7618.

    • PubMed
    • Search Google Scholar
    • Export Citation

Metrics

All Time Past Year Past 30 Days
Abstract Views 1906 1906 1906
Full Text Views 90 90 90
PDF Downloads 102 102 102
EPUB Downloads 0 0 0