Literature DB >> 35596800

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

Danis Alukaev1, Semen Kiselev1, Tamerlan Mustafaev1,2, Ahatov Ainur3, Bulat Ibragimov4,5, Tomaž Vrtovec6.   

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'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.
© 2022. The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

Entities:  

Keywords:  Artificial intelligence; Cobb angle; Computed tomography; Deep learning; Spine; Vertebral morphometry

Mesh:

Year:  2022        PMID: 35596800     DOI: 10.1007/s00586-022-07245-4

Source DB:  PubMed          Journal:  Eur Spine J        ISSN: 0940-6719            Impact factor:   2.721


  21 in total

1.  Three-dimensional morphological and signal intensity features for detection of intervertebral disc degeneration from magnetic resonance images.

Authors:  A Neubert; J Fripp; C Engstrom; D Walker; M-A Weber; R Schwarz; S Crozier
Journal:  J Am Med Inform Assoc       Date:  2013-06-27       Impact factor: 4.497

2.  Holistic multitask regression network for multiapplication shape regression segmentation.

Authors:  Clara M Tam; Dong Zhang; Bo Chen; Terry Peters; Shuo Li
Journal:  Med Image Anal       Date:  2020-07-11       Impact factor: 8.545

3.  Segmentation of Pathological Structures by Landmark-Assisted Deformable Models.

Authors:  Bulat Ibragimov; Robert Korez; Bostjan Likar; Franjo Pernus; Lei Xing; Tomaz Vrtovec
Journal:  IEEE Trans Med Imaging       Date:  2017-02-13       Impact factor: 10.048

4.  Spine Explorer: a deep learning based fully automated program for efficient and reliable quantifications of the vertebrae and discs on sagittal lumbar spine MR images.

Authors:  Jiawei Huang; Haotian Shen; Jialong Wu; Xiaojian Hu; Zhiwei Zhu; Xiaoqiang Lv; Yong Liu; Yue Wang
Journal:  Spine J       Date:  2019-11-20       Impact factor: 4.166

5.  Quantitative vertebral morphometry based on parametric modeling of vertebral bodies in 3D.

Authors:  D Stern; V Njagulj; B Likar; F Pernuš; T Vrtovec
Journal:  Osteoporos Int       Date:  2012-07-24       Impact factor: 4.507

Review 6.  Adolescent idiopathic scoliosis 3D vertebral morphology, progression and nomenclature: a current concepts review.

Authors:  Fraser R Labrom; Maree T Izatt; Andrew P Claus; J Paige Little
Journal:  Eur Spine J       Date:  2021-04-18       Impact factor: 3.134

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

Authors:  Danis Alukaev; Semen Kiselev; Tamerlan Mustafaev; Ahatov Ainur; Bulat Ibragimov; Tomaž Vrtovec
Journal:  Eur Spine J       Date:  2022-05-21       Impact factor: 2.721

8.  The measurement of Cobb angle based on spine X-ray images using multi-scale convolutional neural network.

Authors:  Jun Liu; Chen Yuan; Xiaoxue Sun; Lechan Sun; Hua Dong; Yun Peng
Journal:  Phys Eng Sci Med       Date:  2021-07-12

9.  Automatic vertebrae localization and segmentation in CT with a two-stage Dense-U-Net.

Authors:  Pengfei Cheng; Yusheng Yang; Huiqiang Yu; Yongyi He
Journal:  Sci Rep       Date:  2021-11-12       Impact factor: 4.379

Review 10.  Vertebral morphometry: current methods and recent advances.

Authors:  G Guglielmi; D Diacinti; C van Kuijk; F Aparisi; C Krestan; J E Adams; T M Link
Journal:  Eur Radiol       Date:  2008-03-20       Impact factor: 7.034

View more
  1 in total

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

Authors:  Danis Alukaev; Semen Kiselev; Tamerlan Mustafaev; Ahatov Ainur; Bulat Ibragimov; Tomaž Vrtovec
Journal:  Eur Spine J       Date:  2022-05-21       Impact factor: 2.721

  1 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.