Fractal characterisation of boundary irregularity in skin pigmented lesions

Abstract

A growing literature shows researcher's interest in fractal analysis, arising from its ability to describe and characterise quantitatively the complexity of several tumour profiles. The aim of the work was to investigate the fractal properties of skin pigmented lesion boundaries. Although melanoma is one of the most aggressive tumours, early detection and a high rate of diagnostic accuracy, followed by timely excision, can allow complete recovery in melanoma patients. A modified approach to fractal dimension estimation was performed that was able to consider, in a data fit procedure, the range in which lesions show fractal properties. Identification of this zone is the most important step towards a correct fractal analysis procedure. The method was checked against a known fractal dimension object (Koch's curve) with an error of 0.007. The fractal dimension was estimated in 110 skin pigmented lesions and showed a significantly increasing linear regression (p < 0.05), from common naevi to naevi with dysplasia to melanomas. This result is important for screening, as it can inform the decision to excise precociously malignant lesions or to avoid unnecessary removal of benign ones. The limitations of the method are discussed.

Effects of human relaxin on orthodontic tooth movement and periodontal ligaments in rats

“…16,21,22 A few other studies have applied fractal analysis to evaluate soft tissues, including quantification of skin pigmented lesion boundaries and the complexity of the epithelial connective tissue interface of pseudoepitheliomatous hyperplasia associated with granular cell tumors. 23,24 Fractal analysis was also used to quantify the complexity of the PDL-bone interface in orthodontic tooth movement, suggesting that PDL remodeling in response to force might manifest as increased complexity at this interface. 16 Third, viewer perceptions or the level of organization, quantified by a VAS, also showed greater variability in the relaxin group on day 2.…”

Combination of 3D skin surface texture features and 2D ABCD features for improved melanoma diagnosis

“…The rows indexed as "b" indicate that they are the best results selected by the forward selected only from the 2D features. The best classification performance(s) for each lesion group is(are) highlighted in bold [1,22,27] may lead to better classification results, they still suffer from the drawbacks below: firstly, although most MMs would have irregular border profiles, many benign lesions would also have large border irregularity indices [9]. Secondly, the border feature is very sensitive to imaging noise [19,33,34], this is particularly true for small lesions where the signal to noise ratio is low.…”

“…The two ABCD features not selected by the best 2D and 3D combination, diagnosis systems are based on the ABCD features of malignant melanoma, i.e. asymmetry of lesion shape [10-12, 25, 26, 32], border irregularity [1,9,22,26,27], colour variegation [2,6,8] and large diameter (typically over 6 mm). Although the discriminating capabilities of the ABCD features are indicative, they are far from convincing [31].…”

Is the Fractal Dimension of the Contour-lines a Reliable Tool for Classification of Medical Images?

“…higher fractal dimension. Although this fractal approach for describing, classifying and recognition of medical images, as well as following and predicting the patient's condition, sounds reasonable and it is justified many times (see for example [1][2][3][4][5][6]), we have detected many ambiguities which put in question the reliability of the fractal dimension when applied in medical diagnosis or in some other field where natural objects are classified on the basis of the estimated values of the fractal dimension of their 2D contours.…”

“…Our experimentation began when we tried to reproduce closely the results met in several papers for successful application of fractal dimension in diagnosing cancer ( [1][2][3][4][5][6][7]). We decided to work with skin cancer, taking into consideration the previously reported results and the dermatological ABCDE rule, according to which one of the most specific characteristic of melanoma moles is their irregular border.…”