Semiautomated intraoperative measurement of Cobb angle and coronal C7 plumb line using deep learning and computer vision for scoliosis correction: a feasibility study

Parth GamiWallace H. Coulter Department of Biomedical Engineering, Georgia Institute of Technology, Atlanta, Georgia; and

Search for other papers by Parth Gami in
jns
Google Scholar
PubMed
Close
 BS
,
Kelly QiuWallace H. Coulter Department of Biomedical Engineering, Georgia Institute of Technology, Atlanta, Georgia; and

Search for other papers by Kelly Qiu in
jns
Google Scholar
PubMed
Close
 BS
,
Sindhu KannappanWallace H. Coulter Department of Biomedical Engineering, Georgia Institute of Technology, Atlanta, Georgia; and

Search for other papers by Sindhu Kannappan in
jns
Google Scholar
PubMed
Close
 BS
,
Yoel AlperinWallace H. Coulter Department of Biomedical Engineering, Georgia Institute of Technology, Atlanta, Georgia; and

Search for other papers by Yoel Alperin in
jns
Google Scholar
PubMed
Close
 BS
,
Gaetano De BiaseDepartment of Neurosurgery, Mayo Clinic, Jacksonville, Florida

Search for other papers by Gaetano De Biase in
jns
Google Scholar
PubMed
Close
 MD
,
Ian A. BuchananDepartment of Neurosurgery, Mayo Clinic, Jacksonville, Florida

Search for other papers by Ian A. Buchanan in
jns
Google Scholar
PubMed
Close
 MD
,
Alfredo Quiñones-HinojosaDepartment of Neurosurgery, Mayo Clinic, Jacksonville, Florida

Search for other papers by Alfredo Quiñones-Hinojosa in
jns
Google Scholar
PubMed
Close
 MD
, and
Kingsley Abode-IyamahDepartment of Neurosurgery, Mayo Clinic, Jacksonville, Florida

Search for other papers by Kingsley Abode-Iyamah in
jns
Google Scholar
PubMed
Close
 MD
Restricted access

Purchase Now

USD  $45.00

Spine - 1 year subscription bundle (Individuals Only)

USD  $384.00

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

USD  $624.00
USD  $45.00
USD  $384.00
USD  $624.00
Print or Print + Online Sign in

OBJECTIVE

Scoliosis is a degenerative disease with a 3D deformity in the alignment of the spinal column. Surgical spinal correction outcomes are heavily dependent on the surgeon’s expertise and use of visual cues because of time requirements, lack of automation, and radiation exposure associated with current intraoperative measurement techniques. In this study, the authors sought to validate a novel, nonradiographic, and semiautomated device that measures spinal alignment intraoperatively using deep learning and computer vision.

METHODS

To obtain spinal alignment metrics intraoperatively, the surgeon placed 3D-printed markers made of acrylonitrile butadiene styrene (ABS) plastic at designated locations in the surgical field. With the high-definition camera of the device, the surgeon can take an image of the markers in the surgical field. Images are processed through a computer vision model that detects the location of the markers and calculates the Cobb angle and coronal plumb line.

The marker detection model was trained on 100 images and tested on 130 images of the ABS markers in various conditions. To verify the Cobb angle calculation, 50 models of angle templates from 0° to 180° in 3.6735° increments were created for testing. To verify the plumb line calculation, 21 models of plumb line measurements from −10 to +10 cm in increments of 1 cm were created for testing. A validation study was performed on a scoliotic cadaver model, and the radiographic calculations for Cobb angle and plumb line were compared with the device’s calculations.

RESULTS

The area under the curve for the marker detection model was 0.979 for Cobb angle white, 0.791 for Cobb angle black, and 1 for the plumb line model. The average absolute difference between expected and measured Cobb angles on the verification models was 1.726° ± 1.259°, within the clinical acceptable error of 5°. The average absolute difference between the expected and measured plumb lines on the verification models was 0.415 ± 0.255 cm. For the cadaver validation study, the differences between the radiographic and device calculations for the Cobb angle and plumb line were 2.78° and 0.29 cm, respectively.

CONCLUSIONS

The authors developed and validated a nonradiographic, semiautomated device that utilizes deep learning and computer vision to measure spinal metrics intraoperatively.

ABBREVIATIONS

ABS = acrylonitrile butadiene styrene; AUC = area under the curve; GUI = graphical user interface; ROC = receiver operating characteristic.

Supplementary Materials

    • Supplementary Figures and Tables (PDF 3,103 KB)
  • Collapse
  • Expand

Images from Gami et al. (pp 713–721).

  • 1

    Aebi M. The adult scoliosis. Eur Spine J. 2005;14(10):925948.

  • 2

    Jackson RP, Simmons EH, Stripinis D. Incidence and severity of back pain in adult idiopathic scoliosis. Spine (Phila Pa 1976). 1983;8(7):749756.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 3

    Janicki JA, Alman B. Scoliosis: review of diagnosis and treatment. Paediatr Child Health. 2007;12(9):771776.

  • 4

    Trobisch P, Suess O, Schwab F. Idiopathic scoliosis. Dtsch Arztebl Int. 2010;107(49):875884.

  • 5

    De Biase G, Gruenbaum SE, Quiñones-Hinojosa A, Abode-Iyamah KO. Spine surgery under spinal vs general anesthesia: prospective analysis of quality of life, fatigue, and cognition. Neurosurgery. 2022;90(2):186191.

    • Crossref
    • PubMed
    • Search Google Scholar
    • Export Citation
  • 6

    Kim H, Kim HS, Moon ES, et al. Scoliosis imaging: what radiologists should know. Radiographics. 2010;30(7):18231842.

  • 7

    Maruyama T, Takeshita K. Surgical treatment of scoliosis: a review of techniques currently applied. Scoliosis. 2008;3:6.

  • 8

    Evaniew N, Devji T, Drew B, Peterson D, Ghert M, Bhandari M. The surgical management of scoliosis: a scoping review of the literature. Scoliosis. 2015;10(1):1.

    • Crossref
    • PubMed
    • Search Google Scholar
    • Export Citation
  • 9

    Zuckerman SL, Lai C, Shen Y, et al. P99. Postoperative coronal malalignment after adult spinal deformity surgery: incidence, risk factors, and impact on 2-year outcomes. Spine J. 2021;21(9):S188S189.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 10

    Chen J, Yang C, Ran B, et al. Correction of Lenke 5 adolescent idiopathic scoliosis using pedicle screw instrumentation: does implant density influence the correction?. Spine (Phila Pa 1976). 2013;38(15):E946E951.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 11

    Kim YJ, Lenke LG, Cho SK, Bridwell KH, Sides B, Blanke K. Comparative analysis of pedicle screw versus hook instrumentation in posterior spinal fusion of adolescent idiopathic scoliosis. Spine (Phila Pa 1976). 2004;29(18):20402048.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 12

    Boddapati V, Lombardi JM, Urakawa H, Lehman RA. Intraoperative image guidance for the surgical treatment of adult spinal deformity. Ann Transl Med. 2021;9(1):91.

  • 13

    Lehman RA Jr, Lenke LG, Helgeson MD, Eckel TT, Keeler KA. Do intraoperative radiographs in scoliosis surgery reflect radiographic result?. Clin Orthop Relat Res. 2010;468(3):679686.

    • Crossref
    • PubMed
    • Search Google Scholar
    • Export Citation
  • 14

    Macario A. What does one minute of operating room time cost?. J Clin Anesth. 2010;22(4):233236.

  • 15

    De Biase G, Gassie K, Garcia D, et al. Perioperative comparison of robotic-assisted versus fluoroscopy-guided minimally invasive transforaminal lumbar interbody fusion (TLIF). World Neurosurg. 2021;149:e570e575.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 16

    Garcia D, Sousa-Pinto B, de Biase G, et al. Minimally invasive transforaminal lumbar interbody fusion: cost of a surgeon’s learning curve. World Neurosurg. Published online November 14, 2021.doi: 10.1016/j.wneu.2021.11.039

    • Search Google Scholar
    • Export Citation
  • 17

    West JL, De Biase G, Bydon M, et al. What is the learning curve for lumbar spine surgery under spinal anesthesia? World Neurosurg. 2022;158:e310e316.

  • 18

    De Biase G, Bechtle P, Leone B, Quinones-Hinojosa A, Abode-Iyamah K. Awake minimally invasive transforaminal lumbar interbody fusion with a pedicle-based retraction system. Clin Neurol Neurosurg. 2021;200:106313.

    • Crossref
    • PubMed
    • Search Google Scholar
    • Export Citation
  • 19

    De Biase G, Chen S, Akinduro O, Quinones-Hinojosa A, Abode-Iyamah K. Awake robotic minimally-invasive L4-5 transforaminal lumbar: interbody fusion (TLIF). World Neurosurg. 2021;148:93.

    • Crossref
    • PubMed
    • Search Google Scholar
    • Export Citation
  • 20

    Wu W, Liang J, Du Y, et al. Reliability and reproducibility analysis of the Cobb angle and assessing sagittal plane by computer-assisted and manual measurement tools. BMC Musculoskelet Disord. 2014;15(1):33.

    • Crossref
    • PubMed
    • Search Google Scholar
    • Export Citation
  • 21

    Redmon J, Farhadi A. YOLOv3: an incremental improvement. ArXiv. Preprint posted online April 8, 2018.doi: 10.48550/arxiv.1804.02767

  • 22

    Wills BPD, Auerbach JD, Zhu X, et al. Comparison of Cobb angle measurement of scoliosis radiographs with preselected end vertebrae: traditional versus digital acquisition. Spine (Phila Pa 1976). 2007;32(1):98105.

    • Crossref
    • Search Google Scholar
    • Export Citation

Metrics

All Time Past Year Past 30 Days
Abstract Views 1132 1132 446
Full Text Views 230 230 100
PDF Downloads 211 211 65
EPUB Downloads 0 0 0