Segmentation of Erythema from Skin Photographs for Assisted Diagnosis in Allergology

Abstract

Abstract. More than 2 people out of 10 suffer from allergies, which can take various forms, from eczema to anaphylactic reactions with possible lethal consequences. Diagnosis is achieved through so-called prick-tests or IDR (intradermo-reaction): the injection of a small quantity of substances suspected to cause the allergic manifestation induces an erythema, the size of which is a useful indicator for the diagnosis. The manual surface measurement is timeconsuming and inaccurate. This article presents a method for the semi-automatic measurement of the erythema from a photograph of the skin, taken in such conditions that lighting problems are minimized. The method is based on region growing and takes advantage of the most significant color spaces; the Lab space appears to be the best suited. It was tested on nearly 100 images, taken by various operators, on patients with various skin pigmentations; it gave promising results and proved to be robust.

Practical Imaging in Dermatology

“…This is in coherence with the results of earlier studies (Nischik & Forster, 1997;Roullot et al, 2005), who have also discovered the importance of the a * component in skin color analysis. However, the difference between color spaces is not that significant, especially when using a Gaussian kernel for the KFD.…”

“…Among the earlier studies in the field, Roullot et al (2005) considers seven well known color spaces and compares the separability of the reaction from the background using a training database. As a result, they discover that the optimal dimension among the color spaces is the a * -component of the L * a * b * color space.…”

“…The emphasis is often on detecting signs of melanoma and there exists a lot of literature on melanoma segmentation (Celebi et al, 2009;Gomez et al, 2008;2007), but only a few studies of measurement of allergic reactions from 2D pictures (Nischik & Forster, 1997;Roullot et al, 2005). There are also some studies which have been performed with 3D imaging (Santos et al, 2008) or other specialized imaging hardware (Wöhrl et al, 2006).…”

Kernel Fisher Discriminant and Elliptic Shape Model for Automatic Measurement of Allergic Reactions

“…There exists a lot of literature on melanoma segmentation [2,4,5], but only a few studies of measurement of allergic reactions from 2D pictures [8,9], 3D profiles [10] or other specialized imaging hardware [13]. Our concern is in low-cost 2D digital color photography.…”

“…Our concern is in low-cost 2D digital color photography. Among these, Roullot et al [9] considers seven well known color spaces and compares the separability of the reaction from the background using a training database. As a result, they discover that the optimal dimension among the color spaces is the a * -component of the L * a * b * color space.…”