A deep learning framework for vertebral morphometry and Cobb angle measurement with external validation

Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt

Standard

A deep learning framework for vertebral morphometry and Cobb angle measurement with external validation. / Alukaev, Danis; Kiselev, Semen; Mustafaev, Tamerlan; Ainur, Ahatov; Ibragimov, Bulat; Vrtovec, Tomaž.

I: European Spine Journal, Bind 31, 2022, s. 2115–2124.

Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt

Harvard

Alukaev, D, Kiselev, S, Mustafaev, T, Ainur, A, Ibragimov, B & Vrtovec, T 2022, 'A deep learning framework for vertebral morphometry and Cobb angle measurement with external validation', European Spine Journal, bind 31, s. 2115–2124. https://doi.org/10.1007/s00586-022-07245-4

APA

Alukaev, D., Kiselev, S., Mustafaev, T., Ainur, A., Ibragimov, B., & Vrtovec, T. (2022). A deep learning framework for vertebral morphometry and Cobb angle measurement with external validation. European Spine Journal, 31, 2115–2124. https://doi.org/10.1007/s00586-022-07245-4

Vancouver

Alukaev D, Kiselev S, Mustafaev T, Ainur A, Ibragimov B, Vrtovec T. A deep learning framework for vertebral morphometry and Cobb angle measurement with external validation. European Spine Journal. 2022;31:2115–2124. https://doi.org/10.1007/s00586-022-07245-4

Author

Alukaev, Danis ; Kiselev, Semen ; Mustafaev, Tamerlan ; Ainur, Ahatov ; Ibragimov, Bulat ; Vrtovec, Tomaž. / A deep learning framework for vertebral morphometry and Cobb angle measurement with external validation. I: European Spine Journal. 2022 ; Bind 31. s. 2115–2124.

Bibtex

@article{636970909e154eb38a9305229c2d503a,

title = "A deep learning framework for vertebral morphometry and Cobb angle measurement with external validation",

abstract = "Purpose: To propose a fully automated deep learning (DL) framework for the vertebral morphometry and Cobb angle measurement from three-dimensional (3D) computed tomography (CT) images of the spine, and validate the proposed framework on an external database. Methods: The vertebrae were first localized and segmented in each 3D CT image using a DL architecture based on an ensemble of U-Nets, and then automated vertebral morphometry in the form of vertebral body (VB) and intervertebral disk (IVD) heights, and spinal curvature measurements in the form of coronal and sagittal Cobb angles (thoracic kyphosis and lumbar lordosis) were performed using dedicated machine learning techniques. The framework was trained on 1725 vertebrae from 160 CT images and validated on an external database of 157 vertebrae from 15 CT images. Results: The resulting mean absolute errors (± standard deviation) between the obtained DL and corresponding manual measurements were 1.17 ± 0.40 mm for VB heights, 0.54 ± 0.21 mm for IVD heights, and 3.42 ± 1.36° for coronal and sagittal Cobb angles, with respective maximal absolute errors of 2.51 mm, 1.64 mm, and 5.52°. Linear regression revealed excellent agreement, with Pearson{\textquoteright}s correlation coefficient of 0.943, 0.928, and 0.996, respectively. Conclusion: The obtained results are within the range of values, obtained by existing DL approaches without external validation. The results therefore confirm the scalability of the proposed DL framework from the perspective of application to external data, and time and computational resource consumption required for framework training.",

keywords = "Artificial intelligence, Cobb angle, Computed tomography, Deep learning, Spine, Vertebral morphometry",

author = "Danis Alukaev and Semen Kiselev and Tamerlan Mustafaev and Ahatov Ainur and Bulat Ibragimov and Toma{\v z} Vrtovec",

note = "Publisher Copyright: {\textcopyright} 2022, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.",

year = "2022",

doi = "10.1007/s00586-022-07245-4",

language = "English",

volume = "31",

pages = "2115–2124",

journal = "European Spine Journal",

issn = "0940-6719",

publisher = "Springer",

}

RIS

TY - JOUR

T1 - A deep learning framework for vertebral morphometry and Cobb angle measurement with external validation

AU - Alukaev, Danis

AU - Kiselev, Semen

AU - Mustafaev, Tamerlan

AU - Ainur, Ahatov

AU - Ibragimov, Bulat

AU - Vrtovec, Tomaž

PY - 2022

Y1 - 2022

N2 - Purpose: To propose a fully automated deep learning (DL) framework for the vertebral morphometry and Cobb angle measurement from three-dimensional (3D) computed tomography (CT) images of the spine, and validate the proposed framework on an external database. Methods: The vertebrae were first localized and segmented in each 3D CT image using a DL architecture based on an ensemble of U-Nets, and then automated vertebral morphometry in the form of vertebral body (VB) and intervertebral disk (IVD) heights, and spinal curvature measurements in the form of coronal and sagittal Cobb angles (thoracic kyphosis and lumbar lordosis) were performed using dedicated machine learning techniques. The framework was trained on 1725 vertebrae from 160 CT images and validated on an external database of 157 vertebrae from 15 CT images. Results: The resulting mean absolute errors (± standard deviation) between the obtained DL and corresponding manual measurements were 1.17 ± 0.40 mm for VB heights, 0.54 ± 0.21 mm for IVD heights, and 3.42 ± 1.36° for coronal and sagittal Cobb angles, with respective maximal absolute errors of 2.51 mm, 1.64 mm, and 5.52°. Linear regression revealed excellent agreement, with Pearson’s correlation coefficient of 0.943, 0.928, and 0.996, respectively. Conclusion: The obtained results are within the range of values, obtained by existing DL approaches without external validation. The results therefore confirm the scalability of the proposed DL framework from the perspective of application to external data, and time and computational resource consumption required for framework training.

AB - Purpose: To propose a fully automated deep learning (DL) framework for the vertebral morphometry and Cobb angle measurement from three-dimensional (3D) computed tomography (CT) images of the spine, and validate the proposed framework on an external database. Methods: The vertebrae were first localized and segmented in each 3D CT image using a DL architecture based on an ensemble of U-Nets, and then automated vertebral morphometry in the form of vertebral body (VB) and intervertebral disk (IVD) heights, and spinal curvature measurements in the form of coronal and sagittal Cobb angles (thoracic kyphosis and lumbar lordosis) were performed using dedicated machine learning techniques. The framework was trained on 1725 vertebrae from 160 CT images and validated on an external database of 157 vertebrae from 15 CT images. Results: The resulting mean absolute errors (± standard deviation) between the obtained DL and corresponding manual measurements were 1.17 ± 0.40 mm for VB heights, 0.54 ± 0.21 mm for IVD heights, and 3.42 ± 1.36° for coronal and sagittal Cobb angles, with respective maximal absolute errors of 2.51 mm, 1.64 mm, and 5.52°. Linear regression revealed excellent agreement, with Pearson’s correlation coefficient of 0.943, 0.928, and 0.996, respectively. Conclusion: The obtained results are within the range of values, obtained by existing DL approaches without external validation. The results therefore confirm the scalability of the proposed DL framework from the perspective of application to external data, and time and computational resource consumption required for framework training.

KW - Artificial intelligence

KW - Cobb angle

KW - Computed tomography

KW - Deep learning

KW - Spine

KW - Vertebral morphometry

UR - http://www.scopus.com/inward/record.url?scp=85130228618&partnerID=8YFLogxK

U2 - 10.1007/s00586-022-07245-4

DO - 10.1007/s00586-022-07245-4

M3 - Journal article

C2 - 35596800

AN - SCOPUS:85130228618

VL - 31

SP - 2115

EP - 2124

JO - European Spine Journal

JF - European Spine Journal

SN - 0940-6719

ER -

ID: 309123826