HTN: Hybrid Transformer Network for Curvature of Cervical Spine Estimation
Source abstract
Abstract
Many young people have suffered from cervical spondylosis in recent years due to long-term desk work or unhealthy lifestyles. Early diagnosis is crucial for curing cervical spondylosis. The Cobb angle method is the most common method for assessing spinal curvature. However, manually measuring the Cobb angle is time-consuming and heavily dependent on personal experience. In this paper, we propose a fully automatic system for measuring cervical spinal curvature on X-rays using the Cobb angle method, which can reduce the workload of clinicians and provide a reliable basis for surgery. Hybrid transformer network (HTN) blends a self-attention mechanism, self-supervision learning, and feature fusion. In addition, a new cervical spondylosis dataset is proposed to evaluate our method. Our model can achieve a SMAPE of 11.06% and a significant Pearson correlation coefficient of 0.9619 (p < 0.001) on our dataset. The absolute difference between the ground truth and the prediction obtained is less than 2°, implying clinical value. Statistical analysis proves the reliability of our method for Cobb angle estimation. To further prove the validity of our method, the HTN was also trained and evaluated on the public AASCE MICCAI 2019 challenge dataset. The experimental results show that our method can achieve comparable performance to state-of-the-art methods, which means that our method can measure the curvature of the neck and the entire spine.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Medical Imaging and Analysis · Spine and Intervertebral Disc Pathology · Scoliosis diagnosis and treatment
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
International Joint Research Lab of Intelligent Perception and Control, Shanghai University of Engineering Science, No. 333 Longteng Road, Shanghai 201620, China
Division of Computer Science and Engineering, Jeonbuk National University, Jeonju 54896, Republic of Korea
References (30)
Show source-provided references
1. Acupotomy versus acupuncture for cervical spondylotic radiculopathy: Protocol of a systematic review and meta-analysis10.1136/bmjopen-2019-029052 ↗
2. Efficacy and safety of electroacupuncture in treatment of cervical spondylosis: A protocol of randomized controlled trial10.1097/MD.0000000000025570 ↗
3. Reproducibility and repeatability of a new computerized software for sagittal spinopelvic and scoliosis curvature radiologic measurements: Keops®10.1007/s00586-015-3817-1 ↗
4. Validation of a new computer-assisted tool to measure spino-pelvic parameters10.1016/j.spinee.2015.08.067 ↗
5. The reliability of sagittal pelvic parameters: The effect of lumbosacral instrumentation and measurement experience10.1097/BRS.0000000000000720 ↗
6. Khanal, B., Dahal, L., Adhikari, P., and Khanal, B. (2019, January 17). Automatic cobb angle detection using vertebra detector and vertebra corners regression. Proceedings of the International Workshop and Challenge on Computational Methods and Clinical Applications for Spine Imaging, Shenzhen, China.10.1007/978-3-030-39752-4_9 ↗
7. Accurate automated Cobb angles estimation using multi-view extrapolation net10.1016/j.media.2019.101542 ↗
8. An automated and accurate spine curve analysis system10.1109/ACCESS.2019.2938402 ↗
9. Yi, J., Wu, P., Huang, Q., Qu, H., and Metaxas, D.N. (2020, January 4). Vertebra-focused landmark detection for scoliosis assessment. Proceedings of the 2020 IEEE 17th International Symposium on Biomedical Imaging (ISBI), Iowa City, IA, USA.10.1109/ISBI45749.2020.9098675 ↗
10. Cobb angle measurement of spine from X-ray images using convolutional neural network10.1155/2019/6357171 ↗
11. Dubost, F., Collery, B., Renaudier, A., Roc, A., Posocco, N., Niessen, W., and Bruijne, M.D. (2019, January 17). Automated estimation of the spinal curvature via spine centerline extraction with ensembles of cascaded neural networks. Proceedings of the International Workshop and Challenge on Computational Methods and Clinical Applications for Spine Imaging, Shenzhen, China.10.1007/978-3-030-39752-4_10 ↗
12. Lin, Y., Zhou, H.-Y., Ma, K., Yang, X., and Zheng, Y. (2019, January 17). Seg4Reg networks for automated spinal curvature estimation. Proceedings of the International Workshop and Challenge on Computational Methods and Clinical Applications for Spine Imaging, Shenzhen, China.10.1007/978-3-030-39752-4_7 ↗
13. Lin, Y., Liu, L., Ma, K., and Zheng, Y. (October, January 27). Seg4Reg+: Consistency Learning Between Spine Segmentation and Cobb Angle Regression. Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention, Strasbourg, France.
14. Wang, J., Wang, L., and Liu, C. (2019, January 17). A multi-task learning method for direct estimation of spinal curvature. Proceedings of the International Workshop and Challenge on Computational Methods and Clinical Applications for Spine Imaging, Shenzhen, China.10.1007/978-3-030-39752-4_14 ↗
15. Guo, Y., Li, Y., He, W., and Song, H. (2021, January 1–5). Heterogeneous Consistency Loss for Cobb Angle Estimation. Proceedings of the 2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), online.10.1109/EMBC46164.2021.9631102 ↗
16. Guo, Y., Li, Y., Song, H., He, W., and Yuan, K. (2022, January 7–10). Cobb Angle Rectification with Dual-Activated Linformer. Proceedings of the 2022 IEEE International Conference on Mechatronics and Automation (ICMA), Guilin, China.10.1109/ICMA54519.2022.9856345 ↗
17. Bayat, A., Sekuboyina, A., Hofmann, F., Husseini, M.E., Kirschke, J.S., and Menze, B.H. (2019, January 17). Vertebral labelling in radiographs: Learning a coordinate corrector to enforce spinal shape. Proceedings of the International Workshop and Challenge on Computational Methods and Clinical Applications for Spine Imaging, Shenzhen, China.10.1007/978-3-030-39752-4_4 ↗
18. Long, J., Shelhamer, E., and Darrell, T. (2015, January 7–12). Fully convolutional networks for semantic segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA.10.1109/CVPR.2015.7298965 ↗
19. Ronneberger, O., Fischer, P., and Brox, T. (2015, January 5–9). U-net: Convolutional networks for biomedical image segmentation. Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention, Munich, Germany.10.1007/978-3-319-24574-4_28 ↗
20. Wang, H., Xie, S., Lin, L., Iwamoto, Y., Han, X.-H., Chen, Y.-W., and Tong, R. (2022, January 23–27). Mixed transformer u-net for medical image segmentation. Proceedings of the ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Singapore.10.1109/ICASSP43922.2022.9746172 ↗
21. Ds-transunet: Dual swin transformer u-net for medical image segmentation10.1109/TIM.2022.3178991 ↗
22. MATR: Multimodal Medical Image Fusion via Multiscale Adaptive Transformer10.1109/TIP.2022.3193288 ↗
23. Tragakis, A., Kaul, C., Murray-Smith, R., and Husmeier, D. (2022). The Fully Convolutional Transformer for Medical Image Segmentation. arXiv.10.1109/WACV56688.2023.00365 ↗
24. Chen, J., Lu, Y., Yu, Q., Luo, X., Adeli, E., Wang, Y., Lu, L., Yuille, A.L., and Zhou, Y. (2021). Transunet: Transformers make strong encoders for medical image segmentation. arXiv.
25. Wang, W., Chen, C., Ding, M., Yu, H., Zha, S., and Li, J. (October, January 27). Transbts: Multimodal brain tumor segmentation using transformer. Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention, Strasbourg, France.
26. Zhai, X., Oliver, A., Kolesnikov, A., and Beyer, L. (2019, January 27–28). S4l: Self-supervised semi-supervised learning. Proceedings of the IEEE/CVF International Conference on Computer Vision, Seoul, Republic of Korea.10.1109/ICCV.2019.00156 ↗
27. Newell, A., Yang, K., and Deng, J. (2016, January 11–14). Stacked hourglass networks for human pose estimation. Proceedings of the European Conference on Computer Vision, Amsterdam, The Netherlands.10.1007/978-3-319-46484-8_29 ↗
28. Hu, J., Shen, L., and Sun, G. (2018, January 18–22). Squeeze-and-excitation networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00745 ↗
29. He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27–30). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.10.1109/CVPR.2016.90 ↗
30. Uneven illumination correction of digital images: A survey of the state-of-the-art10.1016/j.ijleo.2019.02.118 ↗