Preview

Problems of Endocrinology

Advanced search

Artificial intelligence for diagnosis of vertebral compression fractures using a morphometric analysis model, based on convolutional neural networks

https://doi.org/10.14341/probl12605

Full Text:

Abstract

BACKGROUND: Pathological low-energy (LE) vertebral compression fractures (VFs) are common complications of osteoporosis and predictors of subsequent LE fractures. In 84% of cases, VFs are not reported on chest CT (CCT), which calls for the development of an artificial intelligence-based (AI) assistant that would help radiology specialists to improve the diagnosis of osteoporosis complications and prevent new LE fractures.
AIMS: To develop an AI model for automated diagnosis of compression fractures of the thoracic spine based on chest CT images.
MATERIALS AND METHODS: Between September 2019 and May 2020 the authors performed a retrospective sampling study of ССТ images. The 160 of results were selected and anonymized. The data was labeled by seven readers. Using the morphometric analysis, the investigators received the following metric data: ventral, medial and dorsal dimensions. This was followed by a semiquantitative assessment of VFs degree. The data was used to develop the Comprise-G AI mode based on CNN, which subsequently measured the size of the vertebral bodies and then calculates the compression degree. The model was evaluated with the ROC curve analysis and by calculating sensitivity and specificity values.
RESULTS: Formed data consist of 160 patients (a training group - 100 patients; a test group - 60 patients). The total of 2,066 vertebrae was annotated. When detecting Grade 2 and 3 maximum VFs in patients the Comprise-G model demonstrated sensitivity - 90,7%, specificity - 90,7%, AUC ROC - 0.974 on the 5-FOLD cross-validation data of the training dataset; on the test data - sensitivity - 83,2%, specificity - 90,0%, AUC ROC - 0.956; in vertebrae demonstrated sensitivity - 91,5%, specificity - 95,2%, AUC ROC - 0.981 on the cross-validation data; for the test data sensitivity - 79,3%, specificity - 98,7%, AUC ROC - 0.978.
CONCLUSIONS: The Comprise-G model demonstrated high diagnostic capabilities in detecting the VFs on CCT images and can be recommended for further validation.

About the Authors

A. V. Petraikin
Research and Practical Clinical Center for Diagnostics and Telemedicine Technologies
Russian Federation

Alexey V. Petraikin - PhD, Med., Associate Professor.
24 Petrovka street, 127051 Moscow.
eLibrary SPIN: 6193-1656


Competing Interests:

No conflict



Zh. E. Belaya
Endocrinology Research Centre
Russian Federation

Zhanna E. Belaya - MD, PhD, Professor.
Moscow.
eLibrary SPIN: 4746-7173


Competing Interests:

No conflict



A. N. Kiseleva
Research Center of Neurology
Russian Federation

Anastasia N. Kiseleva.
Moscow.
eLibrary SPIN: 9586-5720


Competing Interests:

No conflict



Z. R. Artyukova
Research and Practical Clinical Center for Diagnostics and Telemedicine Technologies
Russian Federation

Zlata R. Artyukova.
24 Petrovka street, 127051 Moscow.
eLibrary SPIN: 5873-2280


Competing Interests:

No conflict



M. G. Belyaev
Skolkovo Institute of Science and Technology
Russian Federation

Mikhail G. Belyaev – PhD, Senior Lecturer.
Moscow.
eLibrary SPIN: 2406-1772


Competing Interests:

No conflict



V. A. Kondratenko
Skolkovo Institute of Science and Technology
Russian Federation

Vladimir A. Kondratenko.
Moscow.
eLibrary SPIN: 9265-9820


Competing Interests:

No conflict



M. E. Pisov
Skolkovo Institute of Science and Technology; Kharkevich Institute for Information Transmission Problems
Russian Federation

Maxim E. Pisov.
Moscow.
eLibrary SPIN: 7812-9031


Competing Interests:

No conflict



A. V. Solovev
Sklifosovsky Clinical and Research Institute of Emergency Medicine
Russian Federation

Alexander V. Solovev.
Moscow.
eLibrary SPIN: 9654-4005


Competing Interests:

No conflict



A. K. Smorchkova
Central State Medical Academy of the Presidential Administration of the Russian Federation
Russian Federation

Anastasia K. Smorchkova.
Moscow.
eLibrary SPIN: 4345-8568


Competing Interests:

No conflict



L. R. Abuladze
Sechenov University
Russian Federation

Liya R. Abuladze.
Moscow.
eLibrary SPIN: 8640-9989


Competing Interests:

No conflict



I. N. Kieva
Peoples' Friendship University of Russia
Russian Federation

Irina N. Kieva.
Moscow.
eLibrary SPIN:2279-9141


Competing Interests:

No conflict



V. A. Fedanov
Central State Medical Academy of the Presidential Administration of the Russian Federation
Russian Federation

Vladimir A. Fedanov.
Moscow.
eLibrary SPIN:4700-0649


Competing Interests:

No conflict



L. R. Iassin
Sechenov University
Russian Federation

Leila R. Iassin.
Moscow.
eLibrary SPIN:3439-6381


Competing Interests:

No conflict



D. S. Semenov
Research and Practical Clinical Center for Diagnostics and Telemedicine Technologies
Russian Federation

Dmitry S. Semenov.
24 Petrovka street, 127051 Moscow.
eLibrary SPIN: 2278-7290


Competing Interests:

No conflict



N. D. Kudryavtsev
Endocrinology Research Centre
Russian Federation

Nikita D.Kudryavtsev.
Moscow.
eLibrary SPIN: 1125-8637


Competing Interests:

No conflict



S. P. Shchelykalina
Pirogov Russian National Research Medical University
Russian Federation

Svetlana P. Shchelykalina - PhD, Med., Associate Professor.
Moscow.
eLibrary SPIN: 9804-0820


Competing Interests:

No conflict



V. V. Zinchenko
Research and Practical Clinical Center for Diagnostics and Telemedicine Technologies
Russian Federation

Victoria V. Zinchenko.
24 Petrovka street, 127051 Moscow.
eLibrary SPIN: 4188-0635


Competing Interests:

No conflict



E. S. Akhmad
Research and Practical Clinical Center for Diagnostics and Telemedicine Technologies

Ekaterina S. Akhmad.
24 Petrovka street, 127051 Moscow.
eLibrary SPIN: 5891-4384


Competing Interests:

No conflict



K. A. Sergunova
Research and Practical Clinical Center for Diagnostics and Telemedicine Technologies
Russian Federation

Kristina A. Sergunova – PhD.
24 Petrovka street, 127051 Moscow.
eLibrary SPIN: 6946-3205


Competing Interests:

No conflict



V. A. Gombolevsky
Research and Practical Clinical Center for Diagnostics and Telemedicine Technologies
Russian Federation

Victor A. Gombolevsky - MD, PhD.
24 Petrovka street, 127051 Moscow.
eLibrary SPIN: 6810-3279


Competing Interests:

Нет конфликта интересов 



L. A. Nisovstova
Research and Practical Clinical Center for Diagnostics and Telemedicine Technologies
Russian Federation

Lyudmila A. Nisovstova - PhD, MD, Professor.
24 Petrovka street, 127051 Moscow.
eLibrary SPIN: 9957-8107


Competing Interests:

No conflict



A. V. Vladzymyrskyy
Research and Practical Clinical Center for Diagnostics and Telemedicine Technologies
Russian Federation

Anton V. Vladzymyrskyy - MD, PhD.
24 Petrovka street, 127051 Moscow.
eLibrary SPIN: 3602-7120


Competing Interests:

No conflict



S. P. Morozov
Research and Practical Clinical Center for Diagnostics and Telemedicine Technologies
Russian Federation

Sergey P. Morozov - MD, PhD, Professor.
24 Petrovka street, 127051 Moscow.
eLibrary SPIN: 8542-1720


Competing Interests:

No conflict



References

1. Mel'nichenko GA, Belaya ZhE, Rozhinskaya LYa, et al. Russian federal clinical guidelines on the diagnostics, treatment, and prevention of osteoporosis. Problemy endocrinologii. 2017;63(6):392-426. (in Russ.). doi: 10.14341/probl2017636392-426

2. Lesnyak OM, Baranova IA, Belova KYu et al. Osteoporosis in Russian Federation: Epidemiology, Socio-Medical and Economical Aspects (Review). Travmatologiya i ortopediya Rossii [Traumatology and orthopedics of Russia]. 2018;24(1):155-168. (in Russ.). doi: 10.21823/2311-2905-2018-24-1-155-168

3. Lesnyak OM. The Eastern European & Central Asian Regional Audit Epidemiology, costs & burden of osteoporosis in 2010. Osteoporosis and bone diseases. 2011;14(2):3-6. (in Russ.). doi: 10.14341/osteo201123-6

4. Kanis JA, McCloskey EV, Johansson H, et al. European guidance for the diagnosis and management of osteoporosis in postmenopausal women. Osteoporosis International. 2013; 24:23-57. doi: 10.1007/s00198-012-2074-y

5. Williams AL, Al-Busaidi A, Sparrow PJ, et al. Underreporting of osteoporotic vertebral fractures on computed tomography. European journal of radiology. 2009;69(1):179-183. doi: 10.1016/j.ejrad.2007.08.028

6. Carberry GA, Pooler BD, Binkley N, et al. Unreported vertebral body compression fractures at abdominal multidetector CT. Radiology. 2013;268(1):120-126. doi: 10.1148/radiol.13121632

7. Black DM, Arden NK, Palermo L, et al. Prevalent vertebral deformities predict hip fractures and new vertebral deformities but not wrist fractures. J. Bone Miner. Res. 1999;14(5): 821-828. doi: 10.1359/jbmr.1999.14.5.821

8. Ahmed N, Mandel R, Fain MJ. Frailty: An Emerging Geriatric Syndrome. The American Journal of Medicine. 2007;120(9):748-753. doi: 10.1016/j.amjmed.2006.10.018

9. Antonio CB, Bautista LGC, Labao AB et al. Vertebra fracture classification from 3D CT lumbar spine segmentation masks using a convolutional neural network. 10th Asian Conference on Intelligent Information and Database Systems, ACIIDS 2018. 2018 March 19-21. Dong Hoi City, Vietnam;449-458. doi: 10.1007/978-3-319-75420-8_43

10. Valentinitsch A, Trebeschi S, Kaesmacher J, et al. Opportunistic osteoporosis screening in multi-detector ct images via local classification of textures. Osteoporosis international. 2019;30(6):1275-1285. doi: 10.1007/s00198-019-04910-1

11. Nicolaes J, Raeymaeckers S, Robben D, et al. Detection of vertebral fractures in CT using 3D Convolutional Neural Networks. Computational Methods and Clinical Applications for Spine Imaging. 2019:3-14. doi: 10.1007/978-3-030-39752-4_1

12. 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. doi: 10.1148/radiol.2017162100

13. Roth HR, Wang Y, Yao J, et al. Deep convolutional networks for automated detection of posterior-element fractures on spine CT. Medical Imaging 2016: Computer-Aided Diagnosis. 2016. doi: 10.1117/12.2217146

14. Bar A, Wolf L, Amitai OB, et al. Compression fractures detection on CT. Medical Imaging 2017: Computer-Aided Diagnosis. 2017. doi:10.1117/12.2249635

15. Tomita N, Cheung YY, Hassanpour S. Deep neural networks for automatic detection of osteoporotic vertebral fractures on CT scans. Computers in biology and medicine. 2018;(98);8-15. doi: 10.1016/j.compbiomed.2018.05.011

16. Genant HK, Wu CY, Van KC, et al. Vertebral fracture assessment using a semiquantitative technique. Journal of bone and mineral research. 1993;8(9):1137-1148. doi: 10.1002/jbmr.5650080915

17. Decree of the President of Russian Federation N490 of 10 October 2019. O razvitii iskusstvennogo intellekta v Rossiiskoi Federatsii». (In Russ.). Доступно по: http://www.kremlin.ru/acts/bank/44731. Ссылка активна на 03.09.2020.

18. Adams JE, Lenchik L, Roux C, Genant HK. Vertebral Fracture Initiative. Part II. Radiological Assessment of Vertebral Fracture. [Internet]. [cited 2020 Aug 5]; 49 p. Available from: https://www.iofbonehealth.org/sites/default/files/PDFs/Vertebral%20Fracture%20Initiative/IOF_VFI-Part_II-Manuscript.pdf

19. Alqahtani FF, Offiah AC. Diagnosis of osteoporotic vertebral fractures in children. Pediatric Radiology. 2019;49(3);283-296. doi: 10.1007/s00247-018-4279-5

20. Ronneberger O, Fischer P, Brox T. U-net: Convolutional networks for biomedical image segmentation. Medical Image Computing and Computer-Assisted Intervention — MICCAI 2015. 2015 October 4-9. Munich, Germany; 234-241. doi: 10.1007/978-3-319-24574-4_28

21. Kingma DP, Ba JL. Adam: A method for stochastic optimization. 3rd International Conference on Learning Representations, ICLR 2015 — Conference Track Proceedings [Internet]. 2015 May 7-9. San Diego, USA. Available from: https://arxiv.org/pdf/1412.6980.pdf

22. Redmon J, Farhadi A. Yolov3: An incremental improvement. [Internet]. [cited 2020 Jul 20]; 6 p. Available from: https://arxiv.org/pdf/1804.02767.pdf

23. Pisov M, Kondratenko V, Zakharov A et al. Keypoints localization for joint vertebra detection and fracture severity quantification. [Internet]. [cited 2020 Jul 20]; 13 p. Available from: https://arxiv.org/pdf/2005.11960.pdf

24. Derkatch S, Kirby C, Kimelman D, Jozani MJ, et al. Identification of Vertebral Fractures by Convolutional Neural Networks to Predict Nonvertebral and Hip Fractures: A Registry-based Cohort Study of Dual X-ray Absorptiometry. Radiology. 2019;293(2):190-201. doi: 10.1148/radiol.2019190201

25. Kim DH, MacKinnon T. Artificial intelligence in fracture detection: transfer learning from deep convolutional neural networks. Clinical Radiology. 2018;73(5):439-445. doi: 10.1016/j.crad.2017.11.015

26. Pickhardt PJ, Pooler BD, Lauder T, et al. Opportunistic Screening for Osteoporosis Using Abdominal Computed Tomography Scans Obtained for Other Indications. Annals of Internal Medicine. 2013;158(8):588-595. doi: 10.7326/0003-4819-158-8-201304160-00003.

27. Alacreu E, Moratal D, Arana E. Opportunistic screening for osteoporosis by routine CT in Southern Europe. Osteoporosis International. 2017;28(3):983-990. doi: 10.1007/s00198-016-3804-3


Supplementary files

1. Figure 1. Scheme of the study
Subject
Type Исследовательские инструменты
View (219KB)    
Indexing metadata
2. Figure 2. An example of marking: a) marking of the ventral, medial and dorsal dimensions of an individual vertebra (ThII); b) Marking of the thoracic spine from ThI to ThXI. The data for seven markers are given, marked with color (validator interface, the results of all markings are presented). Measurements in the reconstruction plane are highlighted in bright color, and darker measurements in parallel planes reflected projection.
Subject
Type Исследовательские инструменты
View (243KB)    
Indexing metadata
3. Figure 3. Overview of the Comprise-G model. Stage 1: localization of the centers of the vertebrae on 3D-CT a) in the coronal; b) in the sagittal plane; c) a 3D model with non-parallel planes directed perpendicular to the spinal column; d) creating a 2D image by "straightening" the spine. Stage 2: e) determination of key points and the corresponding heights of the vertebral bodies, calculation of the G index: the color indicates the degree of compression of the vertebra according to Genant (green color - normal and weak compression: 0; 1, yellow - medium and pronounced 2; 3).
Subject
Type Исследовательские инструменты
View (358KB)    
Indexing metadata
4. Figure 4. ROC curves for classification of (a) vertebrae and (b) patients by degrees of compression using the Comprise-G artificial intelligence model based on cross-validation data (N = 1249 vertebrae, 100 patients)
Subject
Type Исследовательские инструменты
View (216KB)    
Indexing metadata
5. Figure 5. ROC curves for the classification of (a) vertebrae and (b) patients by degrees of compression using the Comprise-G artificial intelligence model when testing on a deferred sample (N = 817 vertebrae, 60 patients).
Subject
Type Исследовательские инструменты
View (211KB)    
Indexing metadata
6. Figure 6. Contingency tables for the classification of vertebrae (a) and patients (b) according to the degrees of compression fractures, produced by the Comprise-G model. Rows - degrees of compression according to expert markup data, columns - according to model measurements.
Subject
Type Исследовательские инструменты
View (165KB)    
Indexing metadata
7. Figure 7. Examples of correspondence of manual marking by experts (blue dots - separate coordinates for seven markers) to automatic measurement by the Comprise-G model (orange segments) for three patients. White arrows (a) - pronounced spondylosis with the formation of hinged osteophytes, black arrows (b) - areas of the vacuum phenomenon in the intervertebral discs, white dashed arrow (c) - osteophytes with a site of sclerosis in the vertebral body. The model demonstrates robustness in these complex tasks.
Subject
Type Исследовательские инструменты
View (290KB)    
Indexing metadata
8. Figure 8. Distribution of patients by the number of fractures (all degrees) according to expert markup N = 160.
Subject
Type Исследовательские инструменты
View (88KB)    
Indexing metadata
9. Figure 9. Distribution of the number of vertebrae with compression fractures in the thoracic spine and the first lumbar vertebra (expert marking), N = 160.
Subject
Type Исследовательские инструменты
View (200KB)    
Indexing metadata

For citation:


Petraikin A.V., Belaya Z.E., Kiseleva A.N., Artyukova Z.R., Belyaev M.G., Kondratenko V.A., Pisov M.E., Solovev A.V., Smorchkova A.K., Abuladze L.R., Kieva I.N., Fedanov V.A., Iassin L.R., Semenov D.S., Kudryavtsev N.D., Shchelykalina S.P., Zinchenko V.V., Akhmad E.S., Sergunova K.A., Gombolevsky V.A., Nisovstova L.A., Vladzymyrskyy A.V., Morozov S.P. Artificial intelligence for diagnosis of vertebral compression fractures using a morphometric analysis model, based on convolutional neural networks. Problems of Endocrinology. 2020;66(5):48-60. (In Russ.) https://doi.org/10.14341/probl12605

Views: 1024


ISSN 0375-9660 (Print)
ISSN 2308-1430 (Online)