In recent years, human lifespan has been increasing, leading to a significant rise in age-related bone diseases such as osteoporosis and osteoarthritis, accompanied by the high costs of treatment for families and society. Therefore, osteoarthritis has become a concern in public healthcare. The use of technology, especially artificial intelligence, enhances the connectivity between units within the healthcare system and between healthcare facilities and the public. This strengthens the healthcare system from top to bottom; primary healthcare staff receive support from higher-level facilities, improving their expertise, the quality of care, and reducing the burden on higher-level hospitals in diagnosis and treatment. This allows for an improvement in the quality of services across the national healthcare network. Consequently, early detection of osteoarthritis helps control pain and limit the progression of the disease when symptoms appear. In this paper, we propose a technique for classifying knee osteoarthritis based on X-ray images using the Vision Transformer deep learning network in a distributed Spark environment. Experimental results show that the proposed model achieves an accuracy of up to 98.85% and improves training and classification time compared to training in a local environment. Furthermore, the proposed method aligns with the current trend of developing many healthcare applications in a distributed environment.
Tạp chí: International scientific conference proceedings “Enhancing cooperation to promote sustainable tourism in response to climate change, the fourth industrial revolution and artificial intelligence" 2024, Trường Đại học Nam Cần Thơ
Tạp chí: 8th International ICONTECH CONGRESS on Innovative Surveys in Positive Sciences, March 16-18, 2024, Azerbaijan Cooperation University, Baku, Azerbaijan
Tạp chí khoa học Trường Đại học Cần Thơ
Lầu 4, Nhà Điều Hành, Khu II, đường 3/2, P. Xuân Khánh, Q. Ninh Kiều, TP. Cần Thơ
Điện thoại: (0292) 3 872 157; Email: tapchidhct@ctu.edu.vn
Chương trình chạy tốt nhất trên trình duyệt IE 9+ & FF 16+, độ phân giải màn hình 1024x768 trở lên