Finger joint synovitis detection in ultrasound images

Ultrasonography has proved its usefulness in the evaluation of joint inflammations caused by rheumatoid arthritis. The illness severity is scored by human examiners based on their experience, but some discrepancies in the final diagnosis and treatment frequently occur. Therefore, the main aim of this work is the elaboration of an automatic method of the localization of finger joint inflammation level in ultrasound images. In this paper we propose a novel, fully automated framework for synovitis region segmentation. In our approach we compare several bones and joint localization methods based on the seeded region growing technique, which is combined with different speckle noise filtering algorithms. This technique extracts a region from the image using some predefined criteria of similarity between initially selected point and the pixels in its neighborhood. The seed point is localized automatically as the darkest patch within a small region between two detected finger bones close to the joint. The region affected by synovitis is found using the adopted criterion of homogeneity based on a patch to patch similarity measure. The obtained results exhibit a satisfying accuracy in comparison with the annotations prepared by an expert and the results delivered by semi-automatic methods that require manual bones delineation.