Overview of Advanced Computer Vision Systems for Skin Lesions Characterization

Abstract

During the last years, computer-vision-based diagnosis systems have been used in several hospitals and dermatology clinics, aiming mostly at the early detection of skin cancer, and more specifically, the recognition of malignant melanoma tumour. In this paper, we review the state of the art in such systems by first presenting the installation, the visual features used for skin lesion classification, and the methods for defining them. Then, we describe how to extract these features through digital image processing methods, i.e., segmentation, border detection, and color and texture processing, and we present the most prominent techniques for skin lesion classification. The paper reports the statistics and the results of the most important implementations that exist in the literature, while it compares the performance of several classifiers on the specific skin lesion diagnostic problem and discusses the corresponding findings.

Border and Asymmetry measuring of skin lesion for diagnostic of melanoma using a perimeter ratio

“…The contour (border) of a skin lesion is the most significant factor for the early diagnosis of skin cancer, especially melanoma (8)(9)(10)(11)(12) Maglogiannis, 2009). In the first case, the main task consists in transforming the boundary of a 2D digital region into a 1D signal.…”

“…For asymmetry measuring, the main approach makes use of a set of axes to evaluate differences among regions (3) (Maglogiannis, 2009). Li uses a multi-scale local fractal distribution for measuring the difference between regions (18) (Li, 2009).…”

“…The main criterion to differentiate between benign and malignant skin lesion is the so-called ABCD rule. This criterion evaluates the asymmetry, edge, colour and size of the skin lesion to generate a diagnostic (2,3) (Korotkov, 2013, Maglogiannis, 2009.…”

“…The measurement of geometric characteristics and light reflection has led the scientific community to propose Computer-Aided Diagnosis Systems (CADS) in skin cancer early detection (3) (Maglogiannis, 2009). Fundamentally, any CADS is composed of four blocks: image processing, edge detection and segmentation, feature extraction and classification (2) (Korotkov, 2013).…”

Tree Structured Model of Skin Lesion Growth Pattern via Color Based Cluster Analysis

“…Recently, many studies have been carried out for extracting the diagnostic features using image processing techniques. In [11], an overview of some of these techniques is provided.…”