Page 81 - Read Online

Glaser et al. Art Int Surg. 2025;5:1-15 Artificial
DOI: 10.20517/ais.2024.36
Intelligence Surgery

Meta-Analysis Open Access

Deep learning for automated spinopelvic parameter
measurement from radiographs: a meta-analysis

4
1
1
3
2
Dylan Glaser , Ahmad K. AlMekkawi , James P. Caruso , Candace Y. Chung , Eshal Z. Khan , Hicham M.
3
5
Daadaa , Salah G. Aoun , Carlos A. Bagley 2
1
Department of Neurosurgery, The university of Missouri-Kansas City, School of Medicine, Kansas City, MO 64108, USA.
2
Department of Neurosurgery, Saint Luke’s Hospital, Kansas City, MO 64111, USA.
3
Department of Neurosurgery, The University of Texas Southwestern, Dallas, TX 75235, USA.
4
Department of Neurosurgery , College of Osteopathic Medicine, Kansas City University, Kansas City, MO 64106, USA.
5
Department of Hematology, King’s College Hospital NHS Foundation Trust, London SE5 9RS, UK.
Correspondence to: Dr. Carlos A. Bagley, Saint Luke’s Marion Bloch Neuroscience Institute, Department of Neurosurgery, Saint
Luke’s Hospital, 4401 Wornall Rd., Kansas City, MO 64111, USA. E-mail: cabagley@saint-lukes.org
How to cite this article: Glaser D, AlMekkawi AK, Caruso JP, Chung CY, Khan EZ, Daadaa HM, Aoun SG, Bagley CA. Deep
learning for automated spinopelvic parameter measurement from radiographs: a meta-analysis. Art Int Surg. 2025;5:1-15. https://
dx.doi.org/10.20517/ais.2024.36
Received: 31 May 2024 First Decision: 14 Oct 2024 Revised: 26 Nov 2024 Accepted: 6 Dec 2024 Published: 4 Jan 2025
Academic Editors: Eyad Elyan, Andrew Gumbs Copy Editor: Pei-Yun Wang Production Editor: Pei-Yun Wang

Abstract
Aim: Quantitative measurement of spinopelvic parameters from radiographs is important for assessing spinal
disorders but is limited by the subjectivity and inefficiency of manual techniques. Deep learning may enable
automated measurement with accuracy rivaling human readers.

Methods: PubMed, Embase, Scopus, and Cochrane databases were searched for relevant studies. Eligible studies
were published in English, used deep learning for automated spinopelvic measurement from radiographs, and
reported performance against human raters. Mean absolute errors and correlation coefficients were pooled in a
meta-analysis.

Results: Fifteen studies analyzing over 10,000 radiographs met the inclusion criteria, employing convolutional
neural networks (CNNs) and other deep learning architectures. Pooled mean absolute errors were 4.3° [95%
confidence interval (CI) 3.2-5.4] for Cobb angle, 3.9° (95%CI 2.7-5.1) for thoracic kyphosis, 3.6° (95%CI 2.8-4.4)
for lumbar lordosis, 1.9° (95%CI 1.3-2.5) for pelvic tilt (PT), 4.1° (95%CI 2.7-5.5) for pelvic incidence (PI), and
1.3 cm (95%CI 0.9-1.7) for sagittal vertical axis (SVA). Intraclass correlation coefficients exceeded 0.81, indicating
strong agreement between automated and manual measurements.

© The Author(s) 2025. Open Access This article is licensed under a Creative Commons Attribution 4.0
International License (https://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, sharing,
adaptation, distribution and reproduction in any medium or format, for any purpose, even commercially, as
long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and
indicate if changes were made.

www.oaepublish.com/ais