Melanocytic Lesions Screening through Particle Swarm Optimization

Melanocytic Lesions Screening through Particle Swarm Optimization

Rustem Popa (“Dunarea de Jos” University of Galati, Romania)
DOI: 10.4018/978-1-4666-4450-2.ch012
OnDemand PDF Download:
$30.00
List Price: $37.50

Abstract

Early detection of malignant melanoma, which is the most dangerous skin cancer, significantly improves the chances of curing it. For this reason, dermatologists are looking for new methods for the examination of suspicious lesions that changes their shape over time. The author investigates in this chapter some algorithms which may be used for automated diagnosis of skin lesions. First algorithm performs the image segmentation by edge detection, which plays an important role in identifying borders of the lesion. Next algorithm uses the Particle Swarm Optimization (PSO) paradigm for recognizing the images of the same melanocytic nevus taken at different moments of time. The idea is that a novel view of an object can be recognized by simply matching it to combinations of known views of the same object. The main difficulty in implementing this idea is determining the parameters of the combination of views. The space of parameters is very large and we propose a PSO approach to search this space efficiently. The effectiveness of this approach is shown on a set of real images captured with a camera under different angles of view.
Chapter Preview
Top

Introduction

Detection and early diagnosis of skin cancer remains the main concern of dermatologists worldwide. Malignant melanoma is now one of the most common forms of cancer among world’s population, especially in fair-skinned individuals. Change of recreational behavior together with the increase in ultraviolet radiation cause a dramatic increase in the number of melanomas diagnosed. The curability of this type of skin cancer (about 70%) depends of early enough recognition and surgically treatment. Many publications report on isolated efforts into the direction of automated melanoma recognition by image processing, but complete integrated dermatological image analysis systems are hardly found in clinical use (Gauster et al., 2001).

Małaczewska and Dabkowski (2004) talk about the contemporary view on the melanocytic nevi and their role in the pathogenesis of skin malignant melanoma. There is a strong relationship between the presence of the melanocytic nevi and the incidence of melanoma. For that reason dermatologists should pay close attention to patients from the risk group, with many common and atypical melanocytic nevi, family history of melanoma, bright fair skin, with history of sun burns. These patients should be meticulously and regularly checked up. Examination should include photographic surveillance and dermatoscopy and every suspected mole should be excised with further histological examination. This kind of procedure intensifies the possibility of early recognition of melanoma malignum of the skin, which is crucial for successful treatment of this dangerous disease.

Clinical features of melanoma are summarized as what’s called ABCD rule, promoted by the America Cancer Society: A (Asymmetry), B (Border irregularity), C (Color variegation) and D (Diameter greater than 6mm). Early recognition of changes of lesion in terms of the previous features provides important diagnostic and prognostic information. Other screening guidelines are established by the seven-point checklist, advocated by a group of dermatologists from Glasgow. This checklist emphasizes the progression of the symptoms and consists of three major features (change in size, shape and color) and four minor features (inflammation, crusting or bleeding, sensory change, and diameter greater than 7mm). When any of the major features is detected in a melanocytic lesion, immediate help from health professionals is recommended. The presence of any minor features is advised to be monitored regularly (Lee, 2001; Liu et al., 2011). Schleicher et al. (2003) attached two more letters to the ABCD rule: E (Elevation) and I (Itch). Over time, most melanomas will become raised, and a very early signal that a mole is becoming cancerous is the sensation of itching at the site of the lesion.

Patients with large congenital melanocytic nevi are at increased risk for developing various medical problems, including cutaneous melanoma. In general, most studies reporting on the risk of melanoma in large congenital melanocytic nevi enrolled patients with lesions that were at least 20 cm in diameter, but there are no evidences between the risk and the absolute size of the lesion or its clinical appearance (flat, raised, rugous, speckled, etc). However, some recent data suggest that the risk for melanoma may be highest for lesions greater than 40 cm, located on the torso rather than on the head, neck or extremities (Slutsky et al., 2010). The method described in this chapter may be used also for this kind of lesions.

As a melanocytic lesion ages, both the skin where it is settled as well the nevi cells themselves, undergo alterations in their structure. An estimated percentage of 20 or 30 of lesions disappear in old age. This process of involution and disappearance is hard to prove in individual lesions, but there are proven cases based on old photographs where this had happened (Cintra et al., 1994). So, it’s a good idea to follow the evolution of these lesions in time using photographs taken at different moments of time and different angles of view.

Key Terms in this Chapter

Image Segmentation: The process of partitioning a digital image into multiple segments (sets of pixels) for the purpose to simplify or change the representation of an image into something that is more meaningful and easier to analyze.

Melanocytic Nevus: A type of lesion that contains nevus cells (a type of melanocyte), called by some sources with the term “mole”.

Affine Transformation: A transformation which preserves straight lines and ratios of distances between points lying on a straight line. It is equivalent to a linear transformation followed by a translation.

Combination of Views: In the theory of algebraic functions of view, the variety of 2-D views depicting an object can be expressed as a combination of a small number of 2-D views of the object. Results are also available in 3-D.

Edge Detection: A set of mathematical methods which aim at identifying points in a digital image at which the image brightness changes sharply. These points generates an edge.

Melanoma: A malignant tumor of melanocytes and the most dangerous skin cancer. Early detection of melanoma, while it is still small and thin, and completely removal of the tumor, significantly improves the chances of cure.

Dermatoscope: An instrument used in dermatology, which lets you look at the upper 2 mm of the skin by the use of polarized light.

Genetic Algorithm: A search heuristic that generate solutions to optimization problems using techniques inspired by natural evolution, such as selection, crossover and mutation.

Image Matching: The act of checking a distance function between two sets of points which belong to some images taken from the same content.

Particle Swarm Optimization: A computational method that optimizes a problem by iteratively trying to improve a candidate solution with regard to a given measure of quality. The population of particles are moving in the search space, according with an heuristic based on each particle’s position and velocity. Each particle’s movement is influenced by its local best known position and by the best position of the swarm, which are updated as better positions are found by other particles.

Dermatoscopy: (Also known as dermoscopy) Is the examination of skin lesions with a dermatoscope.

Melanocytes: Cells that produce the dark pigment, melanin, which is responsible for the color of skin. These cells are located in the bottom layer of the skin’s epidermis and in other parts of the body.

Complete Chapter List

Search this Book:
Reset