Skip to content
2000
  1. Home
  2. A-Z Publications
  3. Current Medical Imaging
  4. Volume 20, Issue 1
  5. Article
Volume 20, Issue 1
  • ISSN: 1573-4056
  • E-ISSN: 1875-6603
file format pdf download PDF
side by side viewer icon HTML

Abstract

Introduction

A recently developed deep-learning-based automatic evaluation model provides reliable and efficient Cobb angle measurements for scoliosis diagnosis. However, few studies have explored its clinical application, and external validation is lacking. Therefore, this study aimed to explore the value of automated assessment models in clinical practice by comparing deep-learning models with manual measurement methods.

Methods

The 481 spine radiographs from an open-source dataset were divided into training and validation sets, and 119 spine radiographs from a private dataset were used as the test set. The mean Cobb angle values assessed by three physicians in the hospital's PACS system served as the reference standard. The results of Seg4Reg, VFLDN, and manual measurement were statistically analyzed. The intra-class correlation coefficients (ICC) and the Pearson correlation coefficient (PCC) were used to compare their reliability and correlation. The Bland-Altman method was used to compare their agreement. The Kappa statistic was used to compare the consistency of Cobb angles at different severity levels.

Results

The mean Cobb angle values measured were 35.89° ± 9.33° with Seg4Reg, 31.54° ± 9.78° with VFLDN, and 32.23° ± 9.28° with manual measurement. The ICCs for the reliability of Seg4Reg and VFLDN were 0.809 and 0.974, respectively. The PCC and MAD between Seg4Reg and manual measurements were 0.731 (p<0.001) and 6.51°, while those between VFLDN and manual measurements were 0.952 (p<0.001) and 2.36°. The Kappa statistic indicated VFLDN (k= 0.686, p< 0.001) was superior to Seg4Reg and manual measurements for Cobb angle severity classification.

Conclusion

The deep-learning-based automatic scoliosis Cobb angle assessment model is feasible in clinical practice. Specifically, the keypoint-based VFLDN is more valuable in actual clinical work with higher accuracy, transparency, and interpretability.

© 2024 The Author(s). Published by Bentham Science Publisher.
This is an open access article distributed under the terms of the Creative Commons Attribution 4.0 International Public License (CC-BY 4.0), a copy of which is available at: https://creativecommons.org/licenses/by/4.0/legalcode. This license permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
Loading

Article metrics loading...

/content/journals/cmir/10.2174/0115734056278130231218073650
2024-01-01
2025-04-02

  • From This Site

    /content/journals/cmir/10.2174/0115734056278130231218073650
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
The full text of this item is not currently available.

References

  1. NegriniS. DonzelliS. AulisaA.G. CzaprowskiD. SchreiberS. de MauroyJ.C. DiersH. GrivasT.B. KnottP. KotwickiT. LebelA. MartiC. MaruyamaT. O’BrienJ. PriceN. ParentE. RigoM. RomanoM. StikeleatherL. WynneJ. ZainaF. 2016 SOSORT guidelines: Orthopaedic and rehabilitation treatment of idiopathic scoliosis during growth.Scoliosis Spinal Disord.2018131310.1186/s13013‑017‑0145‑829435499
     [Google Scholar]
  2. MohamedM. TrivediJ. DavidsonN. MunigangaiahS. Adolescent idiopathic scoliosis: A review of current concepts.Paediatr. Child Health202232411912610.1016/j.paed.2022.01.002
     [Google Scholar]
  3. CobbJ. Outline for the study of scoliosis.J. Bone Jt. Surg.19485261275
     [Google Scholar]
  4. GstoettnerM. SekyraK. WalochnikN. WinterP. WachterR. BachC.M. Inter- and intraobserver reliability assessment of the Cobb angle: Manual versus digital measurement tools.Eur. Spine J.200716101587159210.1007/s00586‑007‑0401‑317549526
     [Google Scholar]
  5. ChockalingamN. DangerfieldP.H. GiakasG. CochraneT. DorganJ.C. Computer-assisted Cobb measurement of scoliosis.Eur. Spine J.200211435335710.1007/s00586‑002‑0386‑x12193997
     [Google Scholar]
  6. AS. HP. AZ. BP. A semi-automatic algorithm for estimating cobb angle.J. Biomed. Phys. Eng.20199331732610.31661/jbpe.v9i3Jun.73031341877
     [Google Scholar]
  7. LinY. ZhouH.Y. MaK. Seg4Reg networks for automated spinal curvature estimation.International Workshop and Challenge on Computational Methods and Clinical Applications for Spine Imaging2020697410.1007/978‑3‑030‑39752‑4_7
     [Google Scholar]
  8. HuoL. CaiB. LiangP. Joint spinal centerline extraction and curvature estimation with row-wise classification and curve graph network.International Conference on Medical Image Computing and Computer-Assisted InterventionSpringer202137738610.1007/978‑3‑030‑87240‑3_36
     [Google Scholar]
  9. WangS. HuangS. WangL. Spinal curve guide network (SCG-Net) for accurate automated spinal curvature estimation.Computational Methods and Clinical Applications for Spine Imaging202010711210.1007/978‑3‑030‑39752‑4_13
     [Google Scholar]
  10. YiJ. WuP. HuangQ. QuH. MetaxasD.N. Vertebra-focused landmark detection for scoliosis assessment.2020 IEEE 17th International Symposium on Biomedical Imaging (ISBI)03-07 April 2020Iowa City, IA, USA2020
     [Google Scholar]
  11. KhanalB. DahalL. AdhikariP. Automatic cobb angle detection using vertebra detector and vertebra corners regression.Computational Methods and Clinical Applications for Spine Imaging: 6th International Workshop and Challenge, CSI 2019Shenzhen, ChinaOctober 17, 20192020818710.1007/978‑3‑030‑39752‑4_9
     [Google Scholar]
  12. GuoY. LiY. HeW. Heterogeneous consistency loss for cobb angle estimation.2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC)01-05 November 2021Mexico2021
     [Google Scholar]
  13. ChenK. PengC. LiY. Accurate automated keypoint detections for spinal curvature estimation.Computational Methods and Clinical Applications for Spine Imaging: 6th International Workshop and Challenge, CSI 2019Shenzhen, ChinaOctober 17, 20192020636810.1007/978‑3‑030‑39752‑4_6
     [Google Scholar]
  14. WuH. BaileyC. RasoulinejadP. Automatic landmark estimation for adolescent idiopathic scoliosis assessment using BoostNet.MICCAI 2017: 20th International ConferenceQuebec City, QC, CanadaSeptember 11-13, 2017201712713510.1007/978‑3‑319‑66182‑7_15
     [Google Scholar]
  15. HeK. ZhangX. RenS. Deep residual learning for image recognition.2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)27-30 June 2016Las Vegas, NV, USA20166368
     [Google Scholar]
  16. ZhaoH. ShiJ. QiX. Pyramid scene parsing network.2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)21-26 July 2017Honolulu, HI, USA2017
     [Google Scholar]
  17. HuangG. LiuZ. Van Der MaatenL. Densely connected convolutional networks.2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)21-26 July 2017Honolulu, HI, USA2017
     [Google Scholar]
  18. KooT.K. LiM.Y. A guideline of selecting and reporting intraclass correlation coefficients for reliability research.J. Chiropr. Med.201615215516310.1016/j.jcm.2016.02.01227330520
     [Google Scholar]
  19. SvanholmH. StarklintH. GundersenH.J.G. FabriciusJ. BarleboH. OlsenS. Reproducibility of histomorphologic diagnoses with special reference to the kappa statistic.Acta Pathol. Microbiol. Scand. Suppl.1989977-1268969810.1111/j.1699‑0463.1989.tb00464.x2669853
     [Google Scholar]
  20. KaravidasN. TzatzaliarisD. Brace and physiotherapeutic scoliosis specific exercises (PSSE) for Adolescent Idiopathic Scoliosis (AIS) treatment: A prospective study following Scoliosis Research Society (SRS) criteria.Arch. Physiother.20221212210.1186/s40945‑022‑00150‑536316760
     [Google Scholar]
  21. WangJ. WangL. LiuC. A multi-task learning method for direct estimation of spinal curvature.Computational Methods and Clinical Applications for Spine ImagingSpringer International Publishing202011311810.1007/978‑3‑030‑39752‑4_14
     [Google Scholar]
/content/journals/cmir/10.2174/0115734056278130231218073650
Loading
Clinical Application of Automatic Assessment of Scoliosis Cobb Angle Based on Deep Learning
Curr. Med. Imaging 20, e15734056278130 (2024); https://doi.org/10.2174/0115734056278130231218073650
/content/journals/cmir/10.2174/0115734056278130231218073650
/content/journals/cmir/10.2174/0115734056278130231218073650
Loading

Data & Media loading...


  • Article Type:     Research Article
Keyword(s): Adolescent idiopathic scoliosis; Automatic measurement; Cobb angle; Deep learning; ICC; PCC

Most Cited Most Cited RSS feed

This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error
Please enter a valid_number test