Establishment and test of intelligent classification method of thoracolumbar fractures based on machine vision_West China Medical Journal

Authors：

YU Zhibin ¹ , LIU Jingxiao ¹ , YANG Yi ² , ZHANG Xiang ² , SHEN Yiwei ² , ZHANG Kerui ² , WANG Xingjin ² ,  MA Litai ²

1. School of Electrical Engineering, Southwest Jiaotong University, Chengdu, Sichuan 611756, P. R. China;
2. Department of Orthopedics, West China Hospital, Sichuan University, Chengdu, Sichuan 610041, P. R. China;

Corresponding author：

MA Litai, Email: ma.litai@163.com

Keywords：

Deep learning; Thoracolumbar fracture; Convolutional neural network; Fracture classification

DOI：

10.7507/1002-0179.202108003

Video：

Export PDF Favorites Scan Get Citation

Abstract Full text Figures/Tables Video References Cited by

Objective To develop a deep learning system for CT images to assist in the diagnosis of thoracolumbar fractures and analyze the feasibility of its clinical application. Methods Collected from West China Hospital of Sichuan University from January 2019 to March 2020, a total of 1256 CT images of thoracolumbar fractures were annotated with a unified standard through the Imaging LabelImg system. All CT images were classified according to the AO Spine thoracolumbar spine injury classification. The deep learning system in diagnosing ABC fracture types was optimized using 1039 CT images for training and validation, of which 1004 were used as the training set and 35 as the validation set; the rest 217 CT images were used as the test set to compare the deep learning system with the clinician’s diagnosis. The deep learning system in subtyping A was optimized using 581 CT images for training and validation, of which 556 were used as the training set and 25 as the validation set; the rest 104 CT images were used as the test set to compare the deep learning system with the clinician’s diagnosis. Results The accuracy and Kappa coefficient of the deep learning system in diagnosing ABC fracture types were 89.4% and 0.849 (P<0.001), respectively. The accuracy and Kappa coefficient of subtyping A were 87.5% and 0.817 (P<0.001), respectively. Conclusions The classification accuracy of the deep learning system for thoracolumbar fractures is high. This approach can be used to assist in the intelligent diagnosis of CT images of thoracolumbar fractures and improve the current manual and complex diagnostic process.

Citation： YU Zhibin, LIU Jingxiao, YANG Yi, ZHANG Xiang, SHEN Yiwei, ZHANG Kerui, WANG Xingjin, MA Litai. Establishment and test of intelligent classification method of thoracolumbar fractures based on machine vision. West China Medical Journal, 2021, 36(10): 1337-1343. doi: 10.7507/1002-0179.202108003 Copy

1.	Havaei M, Davy A, Warde-Farley D, et al. Brain tumor segmentation with deep neural networks. Med Image Anal, 2017, 35: 18-31.
2.	Pereira S, Pinto A, Alves V, et al. Brain tumor segmentation using convolutional neural networks in MRI images. IEEE Trans Med Imaging, 2016, 35(5): 1240-1251.
3.	Menze BH, Jakab A, Bauer S, et al. The multimodal brain tumor image segmentation benchmark (BRATS). IEEE Trans Med Imaging, 2015, 34(10): 1993-2024.
4.	Christ PF, Elshaer MA, Ettlinger F, et al. Automatic liver and lesion segmentation in CT using cascaded fully convolutional neural networks and 3D conditional random fields//International Conference on Medical Image Computing and Computer-Assisted Intervention--MICCAI 2016. Cham: Springer, 2016: 415-423.
5.	Roth HR, Lu L, Farag A, et al. DeepOrgan: multilevel deep convolutional networks for automated pancreas segmentation//International Conference on Medical Image Computing and Computer-Assisted Intervention--MICCAI 2015. Cham: Springer, 2015: 556-564.
6.	Yu L, Yang X, Chen H, et al. Volumetric convNets with mixed residual connections for automated prostate segmentation from 3D MR images//Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence. San Francisco: AAAI Press, 2017: 66-72.
7.	Zhou X, Takayama R, Wang S, et al. Deep learning of the sectional appearances of 3D CT images for anatomical structure segmentation based on an FCN voting method. Med Phys, 2017, 44(10): 5221-5233.
8.	Adams M, Chen W, Holcdorf D, et al. Computer vs human: deep learning versus perceptual training for the detection of neck of femur fractures. J Med Imaging Radiat Oncol, 2019, 63(1): 27-32.
9.	许华权, 庄杰, 章建军, 等. 医学影像学在骨科医学中的应用. 中医药管理杂志, 2016, 24(11): 149-151.
10.	Muehlematter UJ, Mannil M, Becker AS, et al. Vertebral body insufficiency fractures: detection of vertebrae at risk on standard CT images using texture analysis and machine learning. Eur Radiol, 2019, 29(5): 2207-2217.
11.	Li YC, Chen HH, Horng-Shing Lu H, et al. Can a deep-learning model for the automated detection of vertebral fractures approach the performance level of human subspecialists?. Clin Orthop Relat Res, 2021, 479(7): 1598-1612.
12.	余锦娟, 林勇. 基于机器学习的骨质疏松性骨折预测研究. 中国医学物理学杂志, 2018, 35(11): 1329-1333.
13.	Burns JE, Yao J, Summers RM. Vertebral body compression fractures and bone density: automated detection and classification on CT images. Radiology, 2017, 284(3): 788-797.
14.	Lessmann N, van Ginneken B, de Jong PA, et al. Iterative fully convolutional neural networks for automatic vertebra segmentation and identification. Med Image Anal, 2019, 53: 142-155.
15.	Kepler CK, Vaccaro AR, Koerner JD, et al. Reliability analysis of the AOSpine thoracolumbar spine injury classification system by a worldwide group of naïve spinal surgeons. Eur Spine J, 2016, 25(4): 1082-1086.
16.	Suri A, Jones BC, Ng G, et al. A deep learning system for automated, multi-modality 2D segmentation of vertebral bodies and intervertebral discs. Bone, 2021, 149: 115972.
17.	Seo JW, Lim SH, Jeong JG, et al. A deep learning algorithm for automated measurement of vertebral body compression from X-ray images. Sci Rep, 2021, 11(1): 13732.
18.	Li Y, Zhang Y, Zhang EL, et al. Differential diagnosis of benign and malignant vertebral fracture on CT using deep learning. Eur Radiol, 2021(2021): 1-8.
19.	Rehman F, Ali SI, Riaz MN, et al. A region-based deep level set formulation for vertebral bone segmentation of osteoporotic fractures. J Digit Imaging, 2020, 33(1): 191-203.

1. Havaei M, Davy A, Warde-Farley D, et al. Brain tumor segmentation with deep neural networks. Med Image Anal, 2017, 35: 18-31.
2. Pereira S, Pinto A, Alves V, et al. Brain tumor segmentation using convolutional neural networks in MRI images. IEEE Trans Med Imaging, 2016, 35(5): 1240-1251.
3. Menze BH, Jakab A, Bauer S, et al. The multimodal brain tumor image segmentation benchmark (BRATS). IEEE Trans Med Imaging, 2015, 34(10): 1993-2024.
4. Christ PF, Elshaer MA, Ettlinger F, et al. Automatic liver and lesion segmentation in CT using cascaded fully convolutional neural networks and 3D conditional random fields//International Conference on Medical Image Computing and Computer-Assisted Intervention--MICCAI 2016. Cham: Springer, 2016: 415-423.
5. Roth HR, Lu L, Farag A, et al. DeepOrgan: multilevel deep convolutional networks for automated pancreas segmentation//International Conference on Medical Image Computing and Computer-Assisted Intervention--MICCAI 2015. Cham: Springer, 2015: 556-564.
6. Yu L, Yang X, Chen H, et al. Volumetric convNets with mixed residual connections for automated prostate segmentation from 3D MR images//Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence. San Francisco: AAAI Press, 2017: 66-72.
7. Zhou X, Takayama R, Wang S, et al. Deep learning of the sectional appearances of 3D CT images for anatomical structure segmentation based on an FCN voting method. Med Phys, 2017, 44(10): 5221-5233.
8. Adams M, Chen W, Holcdorf D, et al. Computer vs human: deep learning versus perceptual training for the detection of neck of femur fractures. J Med Imaging Radiat Oncol, 2019, 63(1): 27-32.
9. 许华权, 庄杰, 章建军, 等. 医学影像学在骨科医学中的应用. 中医药管理杂志, 2016, 24(11): 149-151.
10. Muehlematter UJ, Mannil M, Becker AS, et al. Vertebral body insufficiency fractures: detection of vertebrae at risk on standard CT images using texture analysis and machine learning. Eur Radiol, 2019, 29(5): 2207-2217.
11. Li YC, Chen HH, Horng-Shing Lu H, et al. Can a deep-learning model for the automated detection of vertebral fractures approach the performance level of human subspecialists?. Clin Orthop Relat Res, 2021, 479(7): 1598-1612.
12. 余锦娟, 林勇. 基于机器学习的骨质疏松性骨折预测研究. 中国医学物理学杂志, 2018, 35(11): 1329-1333.
13. Burns JE, Yao J, Summers RM. Vertebral body compression fractures and bone density: automated detection and classification on CT images. Radiology, 2017, 284(3): 788-797.
14. Lessmann N, van Ginneken B, de Jong PA, et al. Iterative fully convolutional neural networks for automatic vertebra segmentation and identification. Med Image Anal, 2019, 53: 142-155.
15. Kepler CK, Vaccaro AR, Koerner JD, et al. Reliability analysis of the AOSpine thoracolumbar spine injury classification system by a worldwide group of naïve spinal surgeons. Eur Spine J, 2016, 25(4): 1082-1086.
16. Suri A, Jones BC, Ng G, et al. A deep learning system for automated, multi-modality 2D segmentation of vertebral bodies and intervertebral discs. Bone, 2021, 149: 115972.
17. Seo JW, Lim SH, Jeong JG, et al. A deep learning algorithm for automated measurement of vertebral body compression from X-ray images. Sci Rep, 2021, 11(1): 13732.
18. Li Y, Zhang Y, Zhang EL, et al. Differential diagnosis of benign and malignant vertebral fracture on CT using deep learning. Eur Radiol, 2021(2021): 1-8.
19. Rehman F, Ali SI, Riaz MN, et al. A region-based deep level set formulation for vertebral bone segmentation of osteoporotic fractures. J Digit Imaging, 2020, 33(1): 191-203.

West China Medical Journal

Establishment and test of intelligent classification method of thoracolumbar fractures based on machine vision

Abstract Full text Figures/Tables Video References Cited by

Previous Article

Next Article

Format

Content