Scleroderma capillary pattern identification using texture descriptors and ensemble classification

Various connective tissue diseases lead to morphological alternations of blood capillaries. Consequently, observation of the capillaries at the finger nailfold - nailfold capillaroscopy (NC) - is a standard method for diagnosing diseases such as scleroderma or Raynaud´s phenomenon. This is typically performed through manual inspection by an expert to lead to a determination of one of the established NC scleroderma patterns (early, active, and late). In this paper, we present an automated method of analysing nailfold capillaroscopy images and categorising them into NC patterns. For this purpose, we extract a carefully chosen set of texture features from the images and employ an ensemble classification approach to arrive at decisions for each captured finger which are then aggregated to form a diagnosis for the patient. Experimental results on a set of 60 NC images from 16 subjects demonstrate the accuracy and usefulness of our presented approach.