Pigment network detection in dermatoscopic images for melanoma diagnosis

We propose in this paper an automated structural method for the pigment network detection in dermatoscopic images. The first module of the proposed method consists in extracting the skin lesion from the input image. In fact, after the image rehaussement and the lesion segmentation using a fuzzy region growing technique, a post-processing is required to make the lesion sharpened and to select a single luminance component. Given the extracted lesion of interest in the selected luminance image, the second phase is based on a LoG filter in order to detect holes and other structures within this lesion. Besides, a Gaussian-based thresholding process is introduced in order to filter only holes belonging to the pigment network while removing other round structures such as dots, globules and oil bubbles. The main contribution of the proposed method resides in the fuzzy assessment of the membership degree of a hole to the pigment network, what permits to keep the maximum of candidates and postpones the decision until obtaining further information at the following stages. The resulting holes are connected, while verifying a spatial constraint, towards a graph representing the pigment network. The proposed method achieved an area under the ROC curve of 0.821 for successfully detecting pigment network with a correct classification rate of 85% on a dataset of 122 real-world images.