Certain diseases cause permanent changes to the shapes and densities of nai
lfold capillaries and, therefore, nailfold capillaroscopy is important as a
tool for diagnosing and monitoring these diseases. The first aim of the pr
oject is to resolve differences in terminology that have developed over the
years in previous work. We propose a taxonomy for nailfold capillaries tha
t cover six descriptive classes: cuticulis, open, tortuous, crossed, bushy,
and bizarre. The first three are parametric in that they may be distinguis
hed by the ratio of capillary length to width and by the curvature of the c
apillary limbs. The last three are characterized by their topology; a cross
ed capillary has a closed area that is not connected to the image backgroun
d. Bushy and bizarre capillaries have atypical shapes that are characterize
d by the convex hull of their skeleton. These descriptive classes may be mo
dified according to anomalies in width and length.
The second aim is to automate the classification of capillaries by encapsul
ating the taxonomy in an algorithm; our computer program rivals the most ex
perienced clinicians in classifying capillaries consistently with an overal
l agreement of 85% with the clinicians' majority view This was particularly
valuable in classifying borderline shapes objectively and consistently.