EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Deep learning automates Cobb angle measurement compared with multi-expert observers

Keyu Li, Hanxue Gu iD, Roy Colglazier, Robert Lark, Elizabeth Hubbard, Robert French, Denise Smith, Jikai Zhang, Erin McCrum, Anthony Catanzano, Joseph Cao, Leah Waldman und 2 weitere

BJR|Artificial Intelligence · 2025

DOI: 10.1093/bjrai/ubaf009 ↗

Kurz gefasst

Fachartikel in der Zeitschrift BJR|Artificial Intelligence, 2025. Verfasst von Keyu Li und 13 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electrical and Computer Engineering, Duke University, Durham, NC 27705, United States. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 31 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Department of Orthopaedic Surgery, Duke University.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objectives

Scoliosis, a prevalent condition characterized by abnormal spinal curvature leading to deformity, requires precise assessment methods for effective diagnosis and management. The Cobb angle is a widely used scoliosis quantification method that measures the degree of curvature between the tilted vertebrae. Yet, manual measuring of Cobb angles is time-consuming and labour-intensive, fraught with significant interobserver and intraobserver variability. To address these challenges and the lack of interpretability found in certain existing automated methods, we have created fully automated software that not only precisely measures the Cobb angle but also provides clear visualizations of these measurements.

Methods

This software integrates a deep neural network-based spine region detection and segmentation, spine centreline identification, pinpointing the most significantly tilted vertebrae, and direct visualization of Cobb angles on the original images.

Results

Upon comparison with the assessments of 7 expert readers, our algorithm exhibited a mean deviation in Cobb angle measurements of 4.17 degrees, notably surpassing the manual approach’s average intra-reader discrepancy of 5.16 degrees. The algorithm also achieved intraclass correlation coefficients (ICC) exceeding 0.96 and Pearson correlation coefficients above 0.944, reflecting robust agreement with expert assessments and superior measurement reliability.

Conclusions

Through the comprehensive reader study and statistical analysis, we believe this algorithm not only ensures a higher consensus with expert readers but also enhances interpretability and reproducibility during assessments. It holds significant promise for clinical application, potentially helping physicians assess and diagnose scoliosis more accurately, thus improving patient care. Advances in knowledge A fully automated Cobb angle measurement algorithm was compared with a comprehensive multi-expert study and demonstrated superior performance relative to human observers. The code is publicly available at GitHub.

Schlagwörter

Stichwörter der Autor:innen

Cobb angle measurementdeep learningmulti-reader studyscoliosis

Autor:innen und Institutionen

  • Department of Electrical and Computer Engineering, Duke University, Durham, NC 27705, United States.
  • Department of Radiology, Duke University, Durham, NC 27705, United States.
  • Department of Orthopaedics, Duke University, Durham, NC 27705, United States.
  • Department of Pediatric Radiology, Duke University, Durham, NC 27705, United States.
  • Department of Computer Science, Duke University, Durham, NC 27705, United States.

ORCID-Profile: Hanxue Gu

Förderung

  • Department of Orthopaedic Surgery, Duke University

Zitieren

APA

Li, K., Gu, H., Colglazier, R., Lark, R., Hubbard, E., French, R., Smith, D., Zhang, J., McCrum, E., Catanzano, A., Cao, J., Waldman, L., Mazurowski, M. A., & Alman, B. (2025). Deep learning automates Cobb angle measurement compared with multi-expert observers. BJR|Artificial Intelligence. https://doi.org/10.1093/bjrai/ubaf009

Vancouver

Li K, Gu H, Colglazier R, Lark R, Hubbard E, French R, et al. Deep learning automates Cobb angle measurement compared with multi-expert observers. BJR|Artificial Intelligence. 2025. doi:10.1093/bjrai/ubaf009

BibTeX
@article{Li2025,
  author = {Li, Keyu and Gu, Hanxue and Colglazier, Roy and Lark, Robert and Hubbard, Elizabeth and French, Robert and Smith, Denise and Zhang, Jikai and McCrum, Erin and Catanzano, Anthony and Cao, Joseph and Waldman, Leah and Mazurowski, Maciej A and Alman, Benjamin},
  title = {Deep learning automates Cobb angle measurement compared with multi-expert observers},
  journal = {BJR|Artificial Intelligence},
  year = {2025},
  doi = {10.1093/bjrai/ubaf009}
}
Kostenlos starten →