Rheumatoid Arthritis (RA) is an incurable disease leading to severe disabling mutilations of synovial joints. RA affects predominantly the peripheral joints of the appendicular skeleton. RA is with 17% one of the leading causes of disability among persons aged 15 years or older. The prevalence is 1-2%. A recent study estimated the total cost to the North American economy caused by arthritis and its related effects to be 64 billion.
The accurate quantification of the progression of the disease is a decisive factor during its treatment. Until now mainly manual quantification procedures are utilized. They are time consuming and lack reproducibility as well as accuracy. Among others these restrictions have severe adverse effects to clinical trials and to continuous therapy of patients.
We propose a computer based method that performs the quantification by means of automated image analysis and pattern recognition. The goal is to fully automatically identify the bones of the hand/wrist and extract exact quantitative information about the extent of the erosions caused by rheumatoid arthritis based on a radiograph.
The following lines will be investigated during the project:
* A fully automatic method for quantification of RA based on hand radiographs.
* A more accurate, detailed scoring system for RA assessment.
* Novel concepts of Active Appearance Models (AAMs).
* Applicability of the developed methods to other similar diseases.