A perceptually oriented method for contrast enhancement and segmentation of dermoscopy images. Issue 1 (13th August 2012)

• Record Type: Journal Article
• Authors: Abbas, Qaisar; Garcia, Irene Fondón; Emre Celebi, M.; Ahmad, Waqar; Mushtaq, Qaisar
• Is Part Of: Skin research and technology. Volume 19:Issue 1(2013)
• Page Start: e490
• Page End: e497
• Publication Date: 2012-08-13
• Subjects: Skin -- Research -- Periodicals; Skin -- Diseases -- Periodicals; Skin -- Physiology -- Periodicals; 616.5
• DOI: 10.1111/j.1600-0846.2012.00670.x
• Languages: English
• ISSNs: 0909-752X

Abstract

<abstract abstract-type="main" id="srt670-abs-0001"> <title> <x xml:space="preserve">Abstract</x> </title> <sec id="srt670-sec-0001" sec-type="section"> <title>Background/Purpose</title> <p>Dermoscopy images often suffer from low contrast caused by different light conditions, which reduces the accuracy of lesion border detection. Accordingly for lesion recognition, automatic melanoma border detection (MBD) is an initial as well as crucial task.</p> </sec> <sec id="srt670-sec-0002" sec-type="section"> <title>Method</title> <p>In this article, a novel perceptually oriented approach for MBD is presented by combing region and edge‐based segmentation techniques. The MBD system for color contrast and segmentation improvement consists of four main steps: first, the RGB dermoscopy image is transformed to CIE <italic>L*a*b*</italic> color space, lesion contrast is then enhanced by adjusting and mapping the intensity values of the lesion pixels in the specified range using the three channels of CIE <italic>L*a*b*</italic>, a hill‐climbing algorithm is used later to detect region‐of‐interest (ROI) map in a perceptually oriented color space using color channels (<italic>L*, a*, b*</italic>) and finally, an adaptive thresholding is applied to determine the optimal lesion border. Manually drawn borders obtained from an experienced dermatologist are utilized as a ground truth for performance evaluation.</p> </sec> <sec id="srt670-sec-0003" sec-type="section"> <title>Results</title> <p>The proposed MBD method is tested on a total of 100 dermoscopy images. A comparative study with three state‐of‐the‐art color and texture‐based segmentation techniques (JSeg, dermatologists‐like tumor area extraction: DTEA and region‐based active contours: RAC), is also conducted to show the effectiveness of our MBD method using measures of true positive rate (TPR), false positive rate (FPR), and error probability (EP). Among different algorithms, our MBD algorithm achieved TPR of 94.25%, FPR of 3.56%, and EP of 4%.</p> </sec> <sec id="srt670-sec-0004" sec-type="section"> <title>Conclusions</title> <p>The proposed MBD approach is highly accurate to detect the lesion border area. The MBD software and sample of dermoscopy images can be downloaded at http://cs.ntu.edu.pk/research.php.</p> </sec> </abstract>