Enhanced Vertebral Segmentation and Cobb angle Calculation using Advanced Instance Segmentation Techniques
DOI:
https://doi.org/10.21015/vtcs.v14i1.2197Abstract
Scoliosis, a spinal deformity affecting children and adolescents, is quantified using the Cobb angle. Traditional manual measurement by clinicians is time-consuming and subject to variability. This study introduces an automated method using the YOLACT++ instance segmentation model to detect vertebrae and calculate the Cobb angle on the SpineWeb dataset. By identifying the most tilted vertebrae using principal component analysis, our approach achieves a Symmetric Mean Absolute Percentage Error (SMAPE) of 8.11%, outperforming previous segmentation-based methods. This demonstrates improved accuracy and reliability, with potential for clinical decision support. The source code and other details are available at github link. https://github.com/inzamam-ulhaq-collab/Cobb-angle-measurement-code.git
References
C. Du, J. Yu, J. Zhang, J. Jiang, H. Lai, W. Liu, et al., “Relevant areas of functioning in patients with adolescent idiopathic scoliosis on the International Classification of Functioning, Disability and Health: The patients' perspective,” J. Rehabil. Med., vol. 48, no. 9, pp. 806–814, 2016.
T. R. Kuklo, B. K. Potter, T. M. Schroeder, and M. F. O'Brien, “Comparison of manual and digital measurements in adolescent idiopathic scoliosis,” Spine, vol. 31, no. 11, pp. 1240–1246, 2006.
R. T. Morrissy, G. Goldsmith, E. Hall, D. Kehl, and G. Cowie, “Measurement of the Cobb angle on radiographs of patients who have scoliosis: Evaluation of intrinsic error,” J. Bone Joint Surg. Am., vol. 72, no. 3, pp. 320–327, 1990.
S. Langensiepen, O. Semler, R. Sobottke, et al., “Measuring procedures to determine the Cobb angle in idiopathic scoliosis: A systematic review,” Eur. Spine J., vol. 22, no. 11, pp. 2360–2371, 2013.
M. C. Tanure, A. P. Pinheiro, and A. S. Oliveira, “Reliability assessment of Cobb angle measurements using manual and digital methods,” Spine J., vol. 10, no. 9, pp. 769–774, 2010.
M. Gstoettner, K. Sekyra, N. Walochnik, et al., “Inter- and intraobserver reliability assessment of the Cobb angle: Manual versus digital measurement tools,” Eur. Spine J., vol. 16, no. 10, pp. 1587–1592, 2007.
K. Chen, X. Zhai, K. Sun, et al., “A narrative review of machine learning as promising revolution in clinical practice of scoliosis,” Ann. Transl. Med., vol. 9, no. 1, p. 67, 2021.
F. Bao, D. Wang, H. Zhao, and B. Xu, “Application of adaptive threshold image segmentation algorithm in orthopedic CT imaging,” J. Med. Imaging Health Inf., vol. 9, no. 8, pp. 1736–1740, 2019.
J. Mao, K. Wang, Y. Hu, W. Sheng, and Q. Feng, “GrabCut algorithm for dental X-ray images based on full threshold segmentation,” IET Image Process., vol. 12, no. 12, pp. 2330–2335, 2018.
L. Țepelea, L. Gavriluț, and A. Gacsádi, “Edge-based CNN image segmentation methods for medical imaging,” J. Comput. Sci. Control Syst., vol. 3, no. 2, 2010.
Y. M. B. Ali, “Edge-based segmentation using robust evolutionary algorithm applied to medical images,” J. Signal Process. Syst., vol. 54, no. 1, pp. 231–238, 2009.
H. Wu, C. Bailey, P. Rasoulinejad, and S. Li, “Automatic landmark estimation for adolescent idiopathic scoliosis assessment using BoostNet,” in Proc. MICCAI, 2017, pp. 127–135.
G. K. Prabhu, “Automatic quantification of spinal curvature in scoliotic radiograph using image processing,” J. Med. Syst., vol. 36, no. 3, pp. 1943–1951, 2012.
H. Anitha, A. Karunakar, and K. V. N. Dinesh, “Automatic extraction of vertebral endplates from scoliotic radiographs using customized filter,” Biomed. Eng. Lett., vol. 4, no. 2, pp. 158–165, 2014.
T. A. Sardjono, M. H. F. Wilkinson, A. G. Veldhuizen, et al., “Automatic Cobb angle determination from radiographic images,” Spine, vol. 38, no. 20, pp. E1256–E1262, 2013.
M. Sánchez-Fernández, M. de-Prado-Cumplido, J. Arenas-García, and F. Pérez-Cruz, “SVM multiregression for nonlinear channel estimation in multiple-input multiple-output systems,” IEEE Trans. Signal Process., vol. 52, no. 8, pp. 2298–2307, 2004.
X. Zhen, Z. Wang, A. Islam, et al., “Multi-scale deep networks and regression forests for direct bi-ventricular volume estimation,” Med. Image Anal., vol. 30, pp. 120–129, 2016.
T. Kooi, G. Litjens, B. van Ginneken, et al., “Large scale deep learning for computer aided detection of mammographic lesions,” Med. Image Anal., vol. 35, pp. 303–312, 2017.
P. F. Christ, M. E. A. Elshaer, F. Ettlinger, et al., “Automatic liver and lesion segmentation in CT using cascaded fully convolutional neural networks and 3D conditional random fields,” in Proc. MICCAI, 2016, pp. 415–423.
S. Jan, F. A. Khalil, S. B. S. Abid, I. Ullah, I. Ullah, and I. U. Haq, “Optimization of feature selection using Firework algorithm for machine learning algorithm,” VAWKUM Trans. Comput. Sci., vol. 13, no. 2, pp. 250–262, 2025.
E. Acuña and C. Rodriguez, “On detection of outliers and their effect in supervised classification,” Univ. Puerto Rico Mayaguez, Tech. Rep., vol. 15, 2004.
H. Sun, X. Zhen, C. Bailey, et al., “Direct estimation of spinal Cobb angles by structured multi-output regression,” in Proc. IPMI, 2017, pp. 529–540.
M. Horng, C. Kuok, M. Fu, et al., “Cobb angle measurement of spine from X-ray images using convolutional neural network,” Comput. Math. Methods Med., vol. 2019, Art. no. 6357171, 2019.
Y. Pan, Q. Chen, T. Chen, et al., “Evaluation of a computer-aided method for measuring the Cobb angle on chest X-rays,” Eur. Spine J., vol. 28, no. 12, pp. 3035–3043, 2019.
Z. Peng, Z. Wang, M. Sun, et al., “Graph convolutional networks for 3D skeleton-based scoliosis screening using gait sequences,” Vis. Comput., pp. 1–13, 2025.
Q. Liu, Z. Lu, R. Gao, X. Bu, and N. Hanajima, “SimpleMask: Parameter link and efficient instance segmentation,” Vis. Comput., vol. 41, no. 3, pp. 1573–1589, 2025.
B. Khanal, L. Dahal, P. Adhikari, and B. Khanal, “Automatic Cobb angle detection using vertebra detector and vertebra corners regression,” in Proc. Spine Imaging Workshop, 2019, pp. 81–87.
J. Yi, P. Wu, Q. Huang, H. Qu, and D. N. Metaxas, “Vertebra-focused landmark detection for scoliosis assessment,” in Proc. IEEE ISBI, 2020, pp. 736–740.
C. Chen, K. Namdar, Y. Wu, et al., “Automating Cobb angle measurement for adolescent idiopathic scoliosis using instance segmentation,” in Proc. IEEE EMBC, 2024, pp. 1–5.
D. Bolya, C. Zhou, F. Xiao, and Y. J. Lee, “YOLACT: Real-time instance segmentation,” in Proc. IEEE/CVF ICCV, 2019, pp. 9157–9166.
C. Zhou, YOLACT++: Better Real-Time Instance Segmentation, Davis, CA, USA: Univ. California, 2020.
J. Kim, T. Kim, T. Kim, et al., “Morphology-aware interactive keypoint estimation,” in Proc. MICCAI, 2022, pp. 675–685.
V. Kukreja et al., “Segmentation and contour detection for handwritten mathematical expressions using OpenCV,” in Proc. IEEE DASA, 2022, pp. 305–310.
Downloads
Published
How to Cite
Issue
Section
License
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License (CC-By) that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
This work is licensed under a Creative Commons Attribution License CC BY
