Acute effects of a single bout of exercise therapy on knee acoustic emissions in patients with osteoarthritis: a double-blinded, randomized controlled crossover trial

Physical therapy as a promising treatment for osteoarthritis: A narrative review

Osteoarthritis (OA) is the most prevalent joint disease and a leading cause of disability in older adults. With an increasing population ageing and obesity, OA is becoming even more prevalent than it was in previous decades. Evidence indicates that OA is caused by the breakdown of joint tissues from mechanical loading and inflammation, but the deeper underlying mechanism of OA pathogenesis remains unclear, hindering efforts to prevent and treat this disease. Pharmacological treatments are mostly related to relieving symptoms, and there is no drug for radical cure. However, compelling evidence suggests that regular practice of resistance exercise may prevent and control the development of several musculoskeletal chronic diseases including OA, which may result in improved quality of life of the patients. In this review, we introduced the current understanding of the mechanism and clinical treatments of OA pathogenesis. We also reviewed the recent study of physical therapy in the treatment of skeletal system disorders, especially in OA. Finally, we discuss the present challenges and promising advantages of physical therapy in OA treatment.

Detection and Classification of Knee Osteoarthritis

Osteoarthritis (OA) affects nearly 240 million people worldwide. Knee OA is the most common type of arthritis, especially in older adults. Physicians measure the severity of knee OA according to the Kellgren and Lawrence (KL) scale through visual inspection of X-ray or MR images. We propose a semi-automatic CADx model based on Deep Siamese convolutional neural networks and a fine-tuned ResNet-34 to simultaneously detect OA lesions in the two knees according to the KL scale. The training was done using a public dataset, whereas the validations were performed with a private dataset. Some problems of the imbalanced dataset were solved using transfer learning. The model results average of the multi-class accuracy is 61%, presenting better performance results for classifying classes KL-0, KL-3, and KL-4 than KL-1 and KL-2. The classification results were compared and validated using the classification of experienced radiologists.