Skin lesion image segmentation using Delaunay Triangulation for melanoma detection

Abstract

Developing automatic diagnostic tools for the early detection of skin cancer lesions in dermoscopic images can help to reduce melanoma-induced mortality. Image segmentation is a key step in the automated skin lesion diagnosis pipeline. In this paper, a fast and fully-automatic algorithm for skin lesion segmentation in dermoscopic images is presented. Delaunay Triangulation is used to extract a binary mask of the lesion region, without the need of any training stage. A quantitative experimental evaluation has been conducted on a publicly available database, by taking into account six well-known state-of-the-art segmentation methods for comparison. The results of the experimental analysis demonstrate that the proposed approach is highly accurate when dealing with benign lesions, while the segmentation accuracy significantly decreases when melanoma images are processed. This behavior led us to consider geometrical and color features extracted from the binary masks generated by our algorithm for classification, achieving promising results for melanoma detection.

The role of AI classifiers in skin cancer images

“…The implementation of fusion by sum of the single classification results obtained exceed the performance of the lone machine learning algorithms, delivering an accuracy (AC) of 75.69%. Pennisi at al showed the ability of Naive Bayes, Adaptive Boosting (AdaBoost), k‐NN and random trees machine learning methods in the detection of melanomas among benign lesions, segmented with Delaunay Triangulation. The best results were encountered with AdaBoost, with sensitivity (SN) and specificity (SP) values of 0.935 and 0.871, respectively.…”

“…The increase of available labelled data is of concern to improve the training task. However, the majority of studies rely on images available on databases or supplied by hospitals, being dependent of the number of given samples. Hence, strategies to address this issue are of interest for future work and have already been explored by some authors …”

Segmentation of Melanoma Skin Lesion Using Perceptual Color Difference Saliency with Morphological Analysis

“…Similarly, the mean of object color feature can be estimated by the mean of pixel values within a rectangular patch drawn close to the image center. This design principle follows the assumption of center prior [6,10,21,33,71]. However, this study applies a different computational strategy to cater for the identification of skin lesion pixels not necessarily framed near the image center.…”

“…Moreover, segmentation is one of the central stages for computer aided diagnosis of melanoma with dermoscopic images [13]. The automatic segmentation of skin lesion is particularly challenging because of the possible presence of undesirable factors in the form of skin hairs, specular 2 Mathematical Problems in Engineering reflections, variegated coloring, weak edges, low contrast, irregular and fuzzy borders, marker ink, color chart, ruler marks, dark corners, skin lines, blood vessels, and air or oil bubbles [10,[14][15][16].…”

“…However, this diagnostic process is timeconsuming and highly subjective and it requires a great deal of experience from a dermatologist [4,8]. Due to the complexity of melanoma treatment at later stages, researchers are attempting to develop an efficient noninvasive automated computer aided system to make its diagnosis faster and easily accessible to nonexpert practitioners [4,[8][9][10][11]. Such an automated system relies heavily on reliable segmentation of skin lesion, pertinent extraction of skin lesion features, and effective classification of skin lesion using the extracted features [11].…”