Three‐phase general border detection method for dermoscopy images using non‐uniform illumination correction

Abstract

The accuracy of our method was competitive or better than five recently published methods. Our new method is the first method for detecting borders of both non-melanocytic and melanocytic skin lesions.

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

“…The original authors of the algorithm reported similar unsuccessful cases produced by the algorithm during experimentation [12]. Moreover, Norton et al [83] reported an unsuccessful case of the modified JSEG for failing to segment fourteen test images in the most challenging situations. On the other hand, despite the absence of image artifact filtering, Im2 produced by the PCDS algorithm does not contain oil bubbles as seen in the original image.…”

“…This study applies the precision ( ), recall ( ), accuracy ( ), and dice ( ) evaluation metrics to quantitatively score the binary segmentation results computed by the comparative algorithms. These evaluation metrics are widely used for judging the performance of binary segmentation algorithms [8,13,19,20,47,48,61,[83][84][85]. A binary segmentation algorithm with satisfactory performance has high precision, recall, accuracy, and dice values.…”

A computational approach for detecting pigmented skin lesions in macroscopic images

“…An anisotropic diffusion filter has also been regularly used for smoothing skin lesion images, particularly to remove artefacts with good results and without losing relevant information about lesions ( Barcelos & Pires, 2009 ). Based on set theory, morphological filtering ( Gonzalez & Woods, 2002 ) enables removing image noise Silveira et al, 2009 ), and may also be used to enhance skin lesions in images ( Beuren, Janasieivicz, Pinheiro, Grando, & Facon, 2012 ), as well as to include areas with borders of low contrast in previously detected lesion regions ( Norton et al, , 2012.…”

“…From these, threshold-based algorithms have been widely used, mainly because of their simplicity. Thus, thresholding algorithms, such as the Otsu ( Celebi et al, 2007b;Celebi, Wen, Hwang, Iyatomi, & Schaefer, 2013;Norton et al, 2010Norton et al, , 2012, type-2 fuzzy logic ( Yuksel & Borlu, 2009 ) and the Renyi entropy method ( Beuren et al, 2012 ), aim to establish the threshold values in order to separate the regions of interest (ROIs) in the input images. However, these techniques may reveal some problems; for example the segmented lesions tend to be smaller than their real size, and the segmentation process may lead to highly irregular lesion borders ( Yuksel & Borlu, 2009 ).…”

Incorporating Colour Information for Computer-Aided Diagnosis of Melanoma from Dermoscopy Images: A Retrospective Survey and Critical Analysis

“…Norton et al [130] used adaptive histogram equalization to reduce the shading effect on the green channel before applying grey-level thresholding for segmentation of lesion. Tanaka et al [131] subtracted each image from a background brightness that accounted for shading due to body curvature.…”