Get access

A perceptually oriented method for contrast enhancement and segmentation of dermoscopy images

Authors

  • Qaisar Abbas,

    Corresponding author
    1. Center for Biomedical imaging and Bioinformatics, Key Laboratory of Image Processing, Faisalabad, Pakistan
    • Department of Computer Science, National Textile University, Faisalabad, Pakistan
    Search for more papers by this author
  • Irene Fondón Garcia,

    1. Department of Signal Theory and Communications, School of Engineering Path of Discovery, Seville, Spain
    Search for more papers by this author
  • M. Emre Celebi,

    1. Department of Computer Science, Louisiana State University, Shreveport, Louisiana, USA
    Search for more papers by this author
  • Waqar Ahmad,

    1. Department of Computer Science, National Textile University, Faisalabad, Pakistan
    2. Center for Biomedical imaging and Bioinformatics, Key Laboratory of Image Processing, Faisalabad, Pakistan
    Search for more papers by this author
  • Qaisar Mushtaq

    1. Department of Computer Science, National Textile University, Faisalabad, Pakistan
    2. Center for Biomedical imaging and Bioinformatics, Key Laboratory of Image Processing, Faisalabad, Pakistan
    Search for more papers by this author

Address:

Dr Qaisar Abbas

Department of Computer Science

National Textile University

Faisalabad-37610

Pakistan

Tel: +92 41 9230081 Ext: 140

Fax: +92 (41) 9230082

e-mail: drqaisar@ntu.edu.pk, qaisarabbasphd@gmail.com

Abstract

Background/Purpose

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.

Method

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 L*a*b* 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 L*a*b*, a hill-climbing algorithm is used later to detect region-of-interest (ROI) map in a perceptually oriented color space using color channels (L*,a*,b*) 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.

Results

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%.

Conclusions

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.

Ancillary