Abstract
Scoliosis is a medical condition where a person’s spine has a sideways curve. The Cobb angle quantifying the degree of spinal curvature is the gold standard for a scoliosis assessment. Recently, the deep learning methods based on segmentation and landmark estimation both achieve high performance for automated Cobb angle measurement on X-rays. However, we notice that these methods utilize segmentation and landmark information separately. In this light, we propose an automated architecture that uses combined segmentation with landmark information to estimate 68 landmarks of 17 vertebrae. In addition, we consider spinal curvature described by 68 landmarks as a constraint to estimate the Cobb angle. Extensive experiment results which test on 240 X-rays demonstrate that our method improves the landmark estimation performance effectively and reduces the Cobb angle error.
Similar content being viewed by others
References
Clark EM, Taylor HJ, Harding I, Hutchinson J, Nelson I, Deanfield JE, Ness AR, Tobias JH (2014) Association between components of body composition and scoliosis: a prospective cohort study reporting differences identifiable before the onset of scoliosis. J Bone Miner Res 29(8):1729. https://doi.org/10.1002/jbmr.2207
Konieczny MR, Senyurt H, Krauspe R (2013) Epidemiology of adolescent idiopathic scoliosis. J Child Orthop 7(1):3. https://doi.org/10.1007/s11832-012-0457-4
Harrison Harrison DD, Cailliet R, Troyanovich SJ, Janik TJ, Holland B (2000) Cobb method or harrison posterior tangent method: which to choose for lateral cervical radiographic analysis. Spine (Phila. Pa. 1976). https://doi.org/10.1097/00007632-200008150-00011
Cobb JR (1917) Outline for the study of bitumens. Sch Sci Math 17(1):31. https://doi.org/10.1111/j.1949-8594.1917.tb01839.x
Sun H, Zhen X, Bailey C, Rasoulinejad P, Yin Y, Li S (2017) Direct estimation of spinal cobb angles by structured multi-output regression. Lect Notes Comput Sci (including Subser Lect Notes Artif Intell Lect Notes Bioinform) 10265:529–540. https://doi.org/10.1007/978-3-319-59050-9_42
Wu H, Bailey C, Rasoulinejad P, Li S (2017) Automatic landmark estimation for adolescent idiopathic scoliosis assessment using BoostNet. Lect Notes Comput Sci (including Subser Lect Notes Artif Intell Lect Notes Bioinform) 10433:127–135. https://doi.org/10.1007/978-3-319-66182-7_15
Wu H, Bailey C, Rasoulinejad P, Li S (2018) Automated comprehensive adolescent Idiopathic Scoliosis assessment using MVC-Net. Med Image Anal 48:1. https://doi.org/10.1016/j.media.2018.05.005
Wang L, Xu Q, Leung S, Chung J, Chen B, Li S (2019) Accurate automated Cobb angles estimation using multi-view extrapolation net. Med Image Anal 58:101542. https://doi.org/10.1016/j.media.2019.101542
Chen B, Xu Q, Wang L, Leung S, Chung J, Li S (2019) An automated and accurate spine curve analysis system. IEEE Access 7:124596. https://doi.org/10.1109/ACCESS.2019.2938402
Okashi OA, Du H, Al-Assam H (2017) Automatic spine curvature estimation from X-ray images of a mouse model. Comput Methods Progr Biomed 140:175. https://doi.org/10.1016/j.cmpb.2016.12.010
Ronneberger O, Fischer P, Brox T (2015) U-net: convolutional networks for biomedical image segmentation. Lect Notes Comput Sci (including Subser Lect Notes Artif Intell Lect Notes Bioinform) 9351:234. https://doi.org/10.1007/978-3-319-24574-4_28
Jegou S, Drozdzal M, Vazquez Romero A, Bengio Y (2017) the one hundred layers tiramisu: fully convolutional densenets for semantic segmentation. IEEE Comput Soc Conf Comput Vis Pattern Recognit Work 2017:1175–1183. https://doi.org/10.1109/CVPRW.2017.156
Zhang Z, Liu Q, Wang Y, Geosci IEEE (2018) Road extraction by deep residual U-Net. Remote Sens Lett 15(5):749. https://doi.org/10.1109/LGRS.2018.2802944
Al Arif SMR, Knapp K, Slabaugh G (2018) Shape-aware deep convolutional neural network for vertebrae segmentation. Lect Notes Comput Sci (including Subser Lect Notes Artif Intell Lect Notes Bioinform) 10734:12–24. https://doi.org/10.1007/978-3-319-74113-0_2
Tu Y, Wang N, Tong F, Chen H (2019) Automatic measurement algorithm of scoliosis Cobb angle based on deep learning. J Phys Conf Ser 1187:42100. https://doi.org/10.1088/1742-6596/1187/4/042100
Horng MH, Kuok CP, Fu MJ, Lin CJ, Sun YN (2019) Cobb angle measurement of spine from x-ray images using convolutional neural network. Comput Math Methods Med. https://doi.org/10.1155/2019/6357171
He K, Gkioxari G, Dollar P, Girshick R (2017) Mask R-CNN. Proc IEEE Int Conf Comput Vis. https://doi.org/10.1109/ICCV.2017.322
Pan Y, Chen Q, Chen T, Wang H, Zhu X, Fang Z, Lu Y (2019) Evaluation of a computer-aided method for measuring the Cobb angle on chest X-rays. Eur Spine J 28(12):3035. https://doi.org/10.1007/s00586-019-06115-w
Cho BH, Kaji D, Cheung ZB, Ye IB, Tang R, Ahn A, Carrillo O, Schwartz JT, Valliani AA, Oermann EK, Arvind V, Ranti D, Sun L, Kim JS, Cho SK (2019) Automated measurement of lumbar lordosis on radiographs using machine learning and computer vision. Glob Spine J. https://doi.org/10.1177/2192568219868190
Zhang K, Xu N, Yang G, Wu J, Fu X (2019) An automated Cobb angle estimation method using convolutional neural network with area limitation. Lect Notes Comput Sci (including Subser Lect Notes Artif Intell Lect Notes Bioinform) 11769:775–783. https://doi.org/10.1007/978-3-030-32226-7_86
Long J, Shelhamer E, Darrell T (2015) Fully convolutional networks for semantic segmentation. Proc IEEE Comput Soc Conf Comput Vis Pattern Recognit. https://doi.org/10.1109/CVPR.2015.7298965
Ioffe S, Szegedy C (2015) Batch normalization: accelerating deep network training by reducing internal covariate shift. In: Proceedings of the 32nd international conference on machine learning ICML, vol 1, p 448
Srivastava N, Hinton G, Krizhevsky A, Sutskever I, Salakhutdinov R (2014) Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res 15(1):1929
Acknowledgements
This study was supported by the National Key Research and Development Program of China (No. 2018Y-FC0116800), by Beijing Municipal Natural Science Foundation (No. L192026), by the Young Scientists Fund of the National Natural Science Foundation of China (No. 2019NSFC81901822) and by the Peking University Fund of Fostering Young Scholars’ Scientific & Technological Innovation (No. BMU2018PYB016).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of Interest
The authors declare that they have no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Fu, X., Yang, G., Zhang, K. et al. An automated estimator for Cobb angle measurement using multi-task networks. Neural Comput & Applic 33, 4755–4761 (2021). https://doi.org/10.1007/s00521-020-05533-y
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-020-05533-y