Preliminary Study on Grading Diagnosis of Early Knee Osteoarthritis by Shear Wave Elastography

Research progress of ultrasound in accurate evaluation of cartilage injury in osteoarthritis

Osteoarthritis (OA) is a prevalent cause of joint algesia, loss of function, and disability in adults, with cartilage injury being its core pathological manifestation. Since cartilage damage is non-renewable, the treatment outcome in the middle and late stages of OA is unsatisfactory, which can be minimized by changing lifestyle and other treatment modalities if diagnosed and managed in the early stages, indicating the importance of early diagnosis and monitoring of cartilage injury. Ultrasound technology has been used for timely diagnosis and even cartilage injury treatment, which is convenient and safe for the patient owing to no radiation exposure. Studies have demonstrated the effectiveness of ultrasound and its various quantitative ultrasound parameters, like ultrasound roughness index (URI), reflection coefficient (R), apparent integrated backscatter (AIB), thickness, and ultrasound elastography, in the early and accurate assessment of OA cartilage pathological changes, including surface and internal tissue, hardness, and thickness. Although many challenges are faced in the clinical application of this technology in diagnosis, ultrasound and ultrasound-assisted techniques offer a lot of promise for detecting early cartilage damage in OA. In this review, we have discussed the evaluation of ultrasonic cartilage quantitative parameters for early pathological cartilage changes.

The ultrasound assessment of osteoarthritis: the current status

Traditionally, osteoarthritis (OA) is diagnosed with the clinical examination supplemented by the conventional radiography (CR). In the research literature, the role of ultrasound (US) imaging in the diagnostics of OA has risen steadily during the last two decades. US imaging is cheap and globally widely available often already in primary healthcare. Here, we reviewed the most essential US literature focusing on OA diagnostics and progression prediction using the various search engines. Starting from the year 2000, our search provided 1 445 journal articles. After reviewing the abstracts, 89 articles were finally included. Most of the reviewed articles focused on the imaging of knee and hand OA, whereas only a minority dealt with the imaging of hip, ankle, midfoot, acromioclavicular, and temporomandibular joints. Overall, during the last 20 years, the use of US imaging for OA assessment has increased in the scientific literature. In knee and hand joints, US imaging has been reported to be a promising tool to evaluate OA changes. Furthermore, the reproducibility of US as well as its association to MRI findings are excellent. Importantly, US seems to even outperform CR in certain aspects, such as detection of osteophytes, joint inflammation, meniscus protrusion, and localized cartilage damage (especially at the medial femoral condyle and sulcus area). Based on the reviewed literature, US can be truly considered as a complementary tool to CR in the clinical setup for OA diagnostics. New technical developments may even enhance the diagnostic value of the US in the future.

Retracted: Preliminary Study on Grading Diagnosis of Early Knee Osteoarthritis by Shear Wave Elastography

[This retracts the article DOI: 10.1155/2022/4229181.].

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.