Bidimensional Colored Fuzzy Entropy Measure: a Cutaneous Microcirculation Study

In this study, we propose a new irregularity measure for colored images, the so-called bidimensional colored fuzzy entropy, FuzEnC
_2D
. This measure is based on information theory and fuzzy concept. We test its sensitivity to parameters such as tolerance level and window size, as well as its ability to quantify different degrees of irregularity in image textures. Afterwards, we evaluate dermoscopic images of two different microcirculatory states obtained at rest and upon contact heating. The goal of comparing these dermoscopic images is to test if the method is able to distinguish two kinds of microcirculation states. The results show that FuzEnC
_2D
is a proper colored image irregularity measure having low sensitivity to the choice of parameters. We also show its significance in identifying relaxed and vasodilated microcirculatory states in dermoscopic images. This work creates new opportunities in medical applications for colored images with a specific importance for bedridden patients microcirculatory assessment.