Advanced Classification of Knee Osteoarthritis Using Artificial Intelligence Technologies

Main Article Content

Facundo Segura
Florencio Pablo Segura
María Paz Lucero Zudaire
Florencio Vicente Segura
Rocío Mendía
Lucía Ribotta Falco
Paula Sofía Zalazar
Daniel Esteban Sequeira

Abstract




Introduction: Knee osteoarthritis is a prevalent and debilitating musculoskeletal condition, particularly in the elderly. Early detection and accurate classification are crucial for improving patient outcomes.
 
Objective: To investigate the application of artificial intelligence (AI) and computer vision for the automated detection and classification of knee osteoarthritis based on the Kellgren-Lawrence (KL) scale. Additionally, to develop and evaluate an automated system capable of accurately classifying the severity of the disease.
 
Materials and Methods: A public dataset of radiographic knee images pre-classified according to the KL scale was used. The images were processed with LandingLens software, using the ConvNext architecture, a convolutional neural network. The model was trained with 995 images and was used to evaluate 240 trial images.
 
Results: The model achieved an overall accuracy of 92.55% in classifying knee osteoarthritis according to the KL scale, with a sensitivity of 93.33%. Per-class accuracy was as follows: 97.87% for grade 0, 79.74% for grade 1, 88.68% for grade 2, 94.04% for grade 3, and 99.42% for grade 4.
 
Conclusions: This study confirms the efficacy of AI and computer vision technologies in the automated detection of knee osteoarthritis. Integrating these technologies into clinical practice can enhance the efficiency and consistency of patient evaluations, ultimately leading to improved clinical outcomes and more personalized care.








 




Downloads

Download data is not yet available.

Metrics

Metrics Loading ...

Article Details

How to Cite
Segura, F., Segura, F. P., Lucero Zudaire, M. P., Segura, F. V., Mendía, R., Ribotta Falco, L., Zalazar, P. S., & Sequeira, D. E. (2024). Advanced Classification of Knee Osteoarthritis Using Artificial Intelligence Technologies. Revista De La Asociación Argentina De Ortopedia Y Traumatología, 89(5), 462-469. https://doi.org/10.15417/issn.1852-7434.2024.89.5.1993
Section
Clinical Research
Author Biographies

Facundo Segura, Centro Privado Ortopedia y Traumatología Segura, 2nd. Chair of Orthopedics and Traumatology, Universidad Nacional de Córdoba, Córdoba, Argentina. Instituto Conci Carpinella, Córdoba, Argentina. Instituto Médico Victoria, Córdoba, Argentina. Instituto Modelo de Cardiología, Córdoba, Argentina

Centro Privado Ortopedia y Traumatología Segura. 2nd. Chair of Orthopedics and Traumatology, Universidad Nacional de Córdoba, Córdoba, Argentina. Instituto Conci Carpinella, Córdoba, Argentina. Instituto Médico Victoria, Córdoba, Argentina. Instituto Modelo de Cardiología, Córdoba, Argentina

Florencio Pablo Segura, Centro Privado Ortopedia y Traumatología Segura, 2nd. Chair of Orthopedics and Traumatology, Universidad Nacional de Córdoba, Córdoba, Argentina. Instituto Conci Carpinella, Córdoba, Argentina. Instituto Médico Victoria, Córdoba, Argentina. Instituto Modelo de Cardiología, Córdoba, Argentina

Centro Privado Ortopedia y Traumatología Segura. 2nd. Chair of Orthopedics and Traumatology, Universidad Nacional de Córdoba, Córdoba, Argentina. Instituto Conci Carpinella, Córdoba, Argentina. Instituto Médico Victoria, Córdoba, Argentina. Instituto Modelo de Cardiología, Córdoba, Argentina

María Paz Lucero Zudaire, Centro Privado Ortopedia y Traumatología Segura, 2nd. Chair of Orthopedics and Traumatology, Universidad Nacional de Córdoba, Córdoba, Argentina. Instituto Conci Carpinella, Córdoba, Argentina. Instituto Modelo de Cardiología, Córdoba, Argentina

Centro Privado Ortopedia y Traumatología Segura, 2nd. Chair of Orthopedics and Traumatology, Universidad Nacional de Córdoba, Córdoba, Argentina. Instituto Conci Carpinella, Córdoba, Argentina. Instituto Modelo de Cardiología, Córdoba, Argentina

Florencio Vicente Segura, Centro Privado Ortopedia y Traumatología Segura, 2nd. Chair of Orthopedics and Traumatology, Universidad Nacional de Córdoba, Córdoba, Argentina. Instituto Médico Victoria, Córdoba, Argentina. Instituto Modelo de Cardiología, Córdoba, Argentina

Centro Privado Ortopedia y Traumatología Segura. 2nd. Chair of Orthopedics and Traumatology, Universidad Nacional de Córdoba, Córdoba, Argentina. Instituto Médico Victoria, Córdoba, Argentina. Instituto Modelo de Cardiología, Córdoba, Argentina

Rocío Mendía, Instituto Conci Carpinella, Córdoba, Argentina

Instituto Conci Carpinella, Córdoba, Argentina

Lucía Ribotta Falco, Instituto Conci Carpinella, Córdoba, Argentina

Instituto Conci Carpinella, Córdoba, Argentina

Paula Sofía Zalazar, Instituto Conci Carpinella, Córdoba, Argentina

Instituto Conci Carpinella, Córdoba, Argentina

Daniel Esteban Sequeira, Instituto Conci Carpinella, Córdoba, Argentina

Instituto Conci Carpinella, Córdoba, Argentina

References

1. Zhang Y, Jordan JM. Epidemiology of osteoarthritis. Clin Geriatr Med 2010;26(3):355-69.
https://doi.org/10.1016/j.cger.2010.03.001

2. Lawrence RC, Felson DT, Helmick CG, Arnold LM, Choi H, Deyo RA, et al. Estimates of the prevalence of arthritis
and other rheumatic conditions in the United States: Part II. Arthritis Rheum 2008;58(1):26-35.
https://doi.org/10.1002/art.23176

3. Zheng S, Tu L, Cicuttini F, Zhu Z, Han W, Antony B, et al. Depression in patients with knee osteoarthritis: risk
factors and associations with joint symptoms. BMC Musculoskelet Disord 2021;22(1):40.
https://doi.org/10.1186/s12891-020-03875-1

4. Bannuru RR, Osani MC. Vaysbrot EE, Arden NK, Bennell K, Bierma-Zeinstra SMA, et al. OARSI guidelines
for the non-surgical management of knee, hip, and polyarticular osteoarthritis. Osteoarthritis Cartilage 2019:27(11):1578-89. https://doi.org//10.1016/j.joca.2019.06.011

5. Pongsakonpruttikul N, Angthong C, Kittichai V, Chuwongin S, Puengpipattrakul P, Thongpat P, et al. Artificial
intelligence assistance in radiographic detection and classification of knee osteoarthritis and its severity: a crosssectional diagnostic study. Eur Rev Med Pharmacol Sci 2022;26(5):1549-58.
https://doi.org/10.26355/eurrev_202203_28220

6. Sikkandar MY, Begum SS, Alkathiry AA, Alotaibi MSN, Manzar MD. Automatic detection and classification of
human knee osteoarthritis using convolutional neural networks. Computers, Materials & Continua 2022;70(3):4279-91. https://doi.org/:10.32604/cmc.2022.020571

7. Schwartz AJ, Clarke HD, Spangehl MJ, Bingham JS, Etzioni DA, Neville MR. Can a convolutional neural network
classify knee osteoarthritis on plain radiographs as accurately as fellowship-trained knee arthroplasty surgeons? J Arthroplasty 2020;35(9):2423-8. https://doi.org/10.1016/j.arth.2020.04.059

8. Mahmoudian A, Lohmander LS, Mobasheri A, Englund M, Luyten FP. Early-stage symptomatic osteoarthritis of the knee — time for action. Nat Rev Rheumatol 2021;17(10):621-32. https://doi.org/10.1038/s41584-021-00673-4

9. Kohn MD, Sassoon AA, Fernando ND. Classifications in Brief: Kellgren-Lawrence Classification of Osteoarthritis. Clin Orthop Relat Res 2016;474(8):1886-93. https://doi.org/10.1007/s11999-016-4732-4

10. Wing N, Van Zyl N, Wing M, Corrigan R, Loch A, Wall C. Reliability of three radiographic classification systems
for knee osteoarthritis among observers of different experience levels. Skeletal Radiol 2021;50(2):399-405.
https://doi.org/10.1007/s00256-020-03551-4

11. Eckersley T, Faulkner J, Al-Dadah O. Inter- and intra-observer reliability of radiological grading systems for knee osteoarthritis. Skeletal Radiol 2021;50(10):2069-78. https://doi.org/10.1007/s00256-021-03767-y

12. Galli M, De Santis V, Tafuro L. Reliability of the Ahlbäck classification of knee osteoarthritis. Osteoarthritis
Cartilage 2003;11(8):580-4. https://doi.org/ 10.1016/s1063-4584(03)00095-5

13. Kessler S, Guenther KP, Puhl W. Scoring prevalence and severity in gonarthritis: the suitability of the Kellgren & Lawrence scale. Clin Rheumatol 1998;17(3):205-9. https://doi.org/10.1007/BF01451048

14. Ahmed HA, Mohammed EA. Using Artificial Intelligence to classify osteoarthritis in the knee joint. NTU Journal of Engineering and Technology [Internet] 2022;1(3):31-40. Disponible en: https://www.iasj.net/iasj/download/fc5a99f585e6bbda

15. Deokar DD, Patil CG. Effective feature extraction based automatic knee osteoarthritis detection and classification using neural network. International Journal of Engineering and Techniques [Internet] 2015;1(3):134-9. Disponible en: http://www.ijetjournal.org/Volume1/Issue3/IJET-V1I3P22.pdf