Abstract
Adolescent idiopathic scoliosis is a three-dimensional spinal disorder, where the spine is characterized by lateral curvature and axial vertebral rotation (AVR). Measurement of AVR is not as common as the lateral curvature due to its time-consuming nature. However, AVR measurements are useful for predicting curve progression and planning surgeries, which could both result in improved treatment outcomes. To improve accessibility to AVR measurements, this study reported on a convolutional neural network-based method that automatically measured the AVR on posteroanterior (PA) radiographs based on Stokes’ method. The proposed method was tested on 26 PA radiographs (338 vertebrae). The method resulted in 84% of automatic measurements within the clinically accepted error of 5° and achieved a circular mean absolute error of 3.1° ± 3.5° when compared with manual measurements. This high accuracy, coupled with quick computation time (1.7 s per vertebra) and highly interpretable outputs, demonstrates the clinical feasibility of employing the proposed automatic method. This is the first method that automatically measures AVR accurately on PA radiographs taken by both the conventional and EOS x-ray imaging systems.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Weinstein, S., Dolan, L., Cheng, J., Danielsson, A., Morcuende, J.: Adolescent idiopathic scoliosis. The Lancet. 371, 1527–1537 (2008). https://doi.org/https://doi.org/10.1016/S0140-6736(08)60658-3.
Lam, G., Hill, D., Le, L., Raso, J., Lou, E.: Vertebral rotation measurement: a summary and comparison of common radiographic and CT methods. Scoliosis. 3, 16 (2008). https://doi.org/https://doi.org/10.1186/1748-7161-3-16.
Stokes, I., Bigalow, L., Moreland, M.: Measurement of Axial Rotation of Vertebrae in Scoliosis. Spine. 11, 213–218 (1986). https://doi.org/https://doi.org/10.1097/00007632-198604000-00006.
Vrtovec, T., Pernus, F., Likar, B.: A review of methods for quantitative evaluation of axial vertebral rotation. European Spine Journal. 18, 1079–1090 (2009). https://doi.org/https://doi.org/10.1007/s00586-009-0914-z.
Zhang, J., Lou, E., Hill, D., Raso, J., Wang, Y., Le, L., Shi, X.: Computer-aided assessment of scoliosis on posteroanterior radiographs. Med Biol Eng Comput. 48, 185–195 (2010). https://doi.org/https://doi.org/10.1007/s11517-009-0556-7.
Ebrahimi, S., Gajny, L., Vergari, C., Angelini, E., Skalli, W.: Vertebral rotation estimation from frontal X-rays using a quasi-automated pedicle detection method. Eur Spine J. 28, 3026–3034 (2019). https://doi.org/https://doi.org/10.1007/s00586-019-06158-z.
Logithasan, V., Wong, J., Reformat, M., Lou, E.: Using machine learning to automatically measure axial vertebral rotation on radiographs in adolescents with idiopathic scoliosis. Medical Engineering & Physics. 107, 103848 (2022). https://doi.org/https://doi.org/10.1016/j.medengphy.2022.103848.
Xu, B., Wang, N., Chen, T., Li, M.: Empirical Evaluation of Rectified Activations in Convolutional Network, http://arxiv.org/abs/1505.00853, (2015).
Du, S., Zheng, N., Ying, S., You, Q., Wu, Y.: An Extension of the ICP Algorithm Considering Scale Factor. In: 2007 IEEE International Conference on Image Processing. pp. 193–196 (2007). https://doi.org/10.1109/ICIP.2007.4379798.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Wong, J., Reformat, M., Lou, E. (2023). Fully Automatic Axial Vertebral Rotation Measurement of Children with Scoliosis Using Convolutional Neural Networks. In: Su, R., Zhang, Y., Liu, H., F Frangi, A. (eds) Medical Imaging and Computer-Aided Diagnosis. MICAD 2022. Lecture Notes in Electrical Engineering, vol 810. Springer, Singapore. https://doi.org/10.1007/978-981-16-6775-6_22
Download citation
DOI: https://doi.org/10.1007/978-981-16-6775-6_22
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-6774-9
Online ISBN: 978-981-16-6775-6
eBook Packages: MedicineMedicine (R0)