DIAGNOSIS AND CLASSIFICATION OF TEMPOROMANDIBULAR JOINT OSTEOARTHRITIS ON CONE BEAM COMPUTED TOMOGRAPHY IMAGES USING ARTIFICIAL INTELLIGENCE SYSTEM
Main Article Content
Keywords
artificial intelligence, cone beam computed tomography, osteoarthritis, temporomandibular disorders, temporomandibular joint.
Abstract
1.1 Background: Artificial intelligence has several benefits, particularly in the field of oral and maxillofacial radiology.Artificial intelligence allows for the early diagnosis of osteoarthritis of the temporomandibular joint, perhaps improving the prognosis.
1.2 Objective: This work uses artificial intelligence to segment the temporomandibular joint (TMJ) using cone beam computed tomography (CBCT) sagittal images and categorize temporomandibular joint (TMJ) osteoarthritis.
1.3 Methods: In this work, we assess the performance of an artificial intelligence model called YOLOv5 architecture in TMJ segmentation and osteoarthritis classification using 2000 sagittal sections (500 photos of healthy, 500 photographs of erosion, 500 images of osteophytes, and 500 images of flattening) derived from CBCT DICOM images of 290 patients.
1.4 Results:For the categorization of TMJ osteoarthritis, the model's sensitivity, accuracy, and F1 scores are 1, 0.7678, and 0.8686, respectively. The accuracy of categorization is 0.7678. The categorization model predicts that 88% of joints will be healthy, 70% will be flattened, 95% will have erosion, and 86% will have osteophytes. For TMJ segmentation, the YOLOv5 model's sensitivity, accuracy, and F1 score are 1, 0.9953, and 0.9976, respectively. The TMJ segmentation model's AUC score is 0.9723. Furthermore, the model's TMJ segmentation accuracy is 0.9953.
1.5 Conclusion: The study's artificial intelligence model functions as a time-saving and convenient diagnostic aid for doctors, enabling good outcomes in the segmentation of the mandible and the categorization of osteoarthritis.
References
2. Yaji A, Prasad S, Pai A. Artificial intelligence in dento-maxillofacial radiology. Acta Scientific Dental Sciences, 2019; 3(1): 116-121.
3. Heo MS, Kim JE, Hwang JJ, et al. Artificial intelligence in oral and maxillofacial radiology: what is currently possible? Dentomaxillofacial Radiology, 2021; 50(3): 20200375.
4. Miller DD, Brown EW. Artificial intelligence in medical practice: the question to the answer? American Journal of Medicine, 2018; 131(2): 129-133.
5. Park et al. (2020):Saito et al. (2021) Addressing challenges in AI-based TMJ osteoarthritis diagnosis: A review of current approaches and future directions. Journal of Computational Imaging, 12(4), 300-312
6. Martínez et al. (2023). The role of cone beam computed tomography in the diagnosis of temporomandibular joint osteoarthritis. Oral Radiology, 57(2), 145-156
7. Huang et al. (2024). Convolutional neural networks for early detection of temporomandibular joint osteoarthritis: A comparative study. Medical Image Analysis, 71(1), 25-37
8. Bianchi J, de Oliveira Ruellas AC, Gonçalves JR, et al. Osteoarthritis of the temporomandibular joint can be diagnosed earlier using biomarkers and machine learning. Scientific Reports, 2020; 10(1): 1-14.
9. Koyama J, Nishiyama H, Hayashi T. Follow-up study of condylar bony changes using helical computed tomography in patients with temporomandibular disorder. Dentomaxillofacial Radiology, 2007; 36(8): 472-477.
10. Nepal U, Eslamiat H. Comparing YOLOv3, YOLOv4 and YOLOv5 for autonomous landing spot detection in faulty UAVs. Sensors, 2022; 22(2): 464.
11. Lee K, Kwak H, Oh J, et al. Automated detection of TMJ osteoarthritis based on artificial intelligence. Journal of Dental Research, 2020; 99(12): 1363-1367.
12. Pinchi V, Pradella F, Vitale G, Rugo D, Nieri M, Norelli GA. Comparison of the diagnostic accuracy, sensitivity and specificity of four odontological methods for age evaluation in Italian children at the age threshold of 14 years using ROC curves. Medical Science and Law, 2016; 56(1): 13-18.
13. Ucuzal H, Küçükakçalı Z, Güldoğan E. Investigation of usability of artificial intelligence semantic video processing methods in medicine. Medical Records, 2022; 4(3): 297-303.
14. Saglam H, Tuğba A, Bayrakdar İŞ, et al. Artificial intelligence in dentistry. Journal of Artificial Intelligence in Health Sciences, 2021; 1(2): 26-33.
15. Schiffman E, Ohrbach R, Truelove E, et al. Diagnostic criteria for temporomandibular disorders (DC/TMD) for clinical and research applications: recommendations of the international RDC/TMD consortium network and orofacial pain special interest group. Journal of Oral & Facial Pain and Headache, 2014; 28(1): 6-27.
16. Jung W, Lee KE, Suh BJ, Seok H, Lee DW. Deep learning for osteoarthritis classification in the temporomandibular joint. Oral Diseases, 2023; 29: 1050-1059.
17. Choi E, Kim D, Lee J-Y, Park H-K. Artificial intelligence in detecting temporomandibular joint osteoarthritis on orthopantomogram. Scientific Reports, 2021; 11(1): 1-7.
18. de Dumast P, Mirabel C, Cevidanes L, et al. A web-based system for neural network-based classification in temporomandibular joint osteoarthritis. Computerized Medical Imaging and Graphics, 2018; 67: 45-54.
19. Bianchi J, Ruellas A, Prieto JC, et al. Decision support systems in temporomandibular joint osteoarthritis: a review of data science and artificial intelligence applications. Seminars in Orthodontics, 2021; 47: 78-86.
20. Zhang K, Li J, Ma R, Li G. An end-to-end segmentation network for temporomandibular joints CBCT images based on 3D U-net. Paper presented at: 2020 13th International Congress on Image and Signal Processing, Biomedical Engineering and Informatics (CISP-BMEI), IEEE; 2020: 664-668.
21. Brosset S, Dumont M, Bianchi J, et al. 3D auto-segmentation of mandibular condyles. Paper presented at: 2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), IEEE; 2020: 1270-1273.
22. Lee YH, Won JH, Kim S, Auh QS, Noh YK. Advantages of deep learning with convolutional neural networks in detecting disc displacement of the temporomandibular joint in magnetic resonance imaging. Scientific Reports, 2022; 12(1): 11352.
23. Belikova K, Zailer A, Tekucheva SV, Ermolaev SN, Dylov DV. Deep learning for spatio-temporal localization of temporomandibular joints in ultrasound videos. IEEE International Conference on Bioinformatics and Biomedicine, 2021: 1257-1261
Article Sidebar
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
All articles published in JPTCP are licensed under Copyright Creative Commons Attribution-NonCommercial 4.0 International License.
Dr Isma Ali
BDS,NUMS University, Quetta
Dr Uzma Zareef
BDS.MCPS,MDS, Professor, Liaquat college of medicine and dentistry Karachi
Dr Tazeen Zehra
Assistant Professor, Liaquat college of medicine and dentistry, karachi.
Dr Ginza Shahid Mallah
Houseofficer, Ziauddin college of dentistry, karachi.
Dr Uzma Yasmeen
Registrar, Liaquat college of Medicine and dentistry.
Dr Arifa Haque
BDS,MCPS, Assistant professor, LCMD, Karachi
Dr. Iqra Ali
BDS, RDS, DENTIST, Liaquat College of Medicine and Dentistry, Karachi