Automated radiographic assessment of hands in rheumatoid arthritis

Rheumatoid arthritis (RA) is a chronic inflammatory disease leading to severe joint damage, particularly in the wrist, fingers and toes. To prevent irreversible joint damage, it is crucial that RA is monitored and treated in an early stage. In the past fifty years several methods have been developed to quantify visible joint damage in radiographs of hands and feet. In general these methods are time-consuming and depend on subjective visual readings.

A measurable effect in early RA is joint space narrowing caused by degradation of the cartilage between the bones. Firstly, we evaluate different methods on how to quantify the joint space width in an accurate and robust manner. Subsequently, we present several image processing methods for analyzing radiographs. The first is a segmentation method based on a model of the hand skeleton, which is applied to detect bone and joint locations in radiographs. The second part describes a method that accurately detects bone margins within joints. Finally, the joint space width is calculated using the detected joint margins. This method is evaluated by comparing measurement results with both manual measurements, and automated measurements developed by others. It is shown that automated measurements are more precise than manual measurements.

It was observed from the image data, that a large variability of hand positioning is allowed during x-ray acquisition. This complicates not only automated analysis, but can also affect the projection angle within a specific joint. In successive radiographs, this effect can decrease the precision of measurements. Therefore, we recommend standardizing the protocol for radiographic acquisitions. For this purpose, a special positioning aid has been designed, which can be used to place a hand in a standard position.

Another measurable effect of RA is the development of bone damage in the form of erosions. To measure this effect, we investigated subtraction measurements between successive radiographs taken with some time in between. By determining the difference between two images, we demonstrate that developing erosions can be revealed. With this method, in combination with the recommended positioning aid, we expect that in the future it will become feasible to quantify bone damage.