A Machine-Learning Approach to the Automated Assessment of Joint Synovitis Activity

摘要

Medical ultrasound imaging is an important tool in diagnosing and monitoring synovitis, which is an inflammation of the syn-ovial membrane that surrounds a joint. Ultrasound images are examined by medical experts to assess the presence and progression of synovitis. Automating image analysis reduces the costs and increases the availability of the ultrasound diagnosis of synovitis and diminishes or eliminates subjective discrepancies. This article describes research that is concerned with the problem of the automatic estimation of the state of the activity of finger joint inflammation using the information that is present in ultrasonography imaging.