Towards the automatic detection of skin lesion shape asymmetry, color variegation and diameter in dermoscopic images.

Abder-Rahman Ali,Jingpeng Li,Sally Jane O'Shea

doi:10.1371/journal.pone.0234352

Abder-Rahman Ali, Jingpeng Li + Show 1 more

Open Access

https://doi.org/10.1371/journal.pone.0234352

Copy DOI

Abstract

Asymmetry, color variegation and diameter are considered strong indicators of malignant melanoma. The subjectivity inherent in the first two features and the fact that 10% of melanomas tend to be missed in the early diagnosis due to having a diameter less than 6mm, deem it necessary to develop an objective computer vision system to evaluate these criteria and aid in the early detection of melanoma which could eventually lead to a higher 5-year survival rate. This paper proposes an approach for evaluating the three criteria objectively, whereby we develop a measure to find asymmetry with the aid of a decision tree which we train on the extracted asymmetry measures and then use to predict the asymmetry of new skin lesion images. A range of colors that demonstrate the suspicious colors for the color variegation feature have been derived, and Feret’s diameter has been utilized to find the diameter of the skin lesion. The decision tree is 80% accurate in determining the asymmetry of skin lesions, and the number of suspicious colors and diameter values are objectively identified.

Highlights

Melanoma can be recognizable by most physicians and patients when in its advanced stage
A group of researchers at the New York University found the ABCD rule (Asymmetry, Border irregularity, Color variegation, and Diameter greater than 6mm) in 1985 as a simple framework that physicians, novice dermatologists and non-physicians could use to learn about the features of melanoma in its early curable stage [4]; the rule is being promoted by the American Cancer Society as a method to help in seeking early medical evaluation of any suspicious pigmented lesions
The aim of this paper is to present an automated approach to determining skin lesion asymmetry, color variegation, and diameter in dermoscopic images, where different methods and measures are proposed for carrying out this task

Summary

Introduction

Melanoma can be recognizable by most physicians and patients when in its advanced stage. It is highly curable if diagnosed early and treated timely [1,2]. A group of researchers at the New York University found the ABCD rule (Asymmetry, Border irregularity, Color variegation, and Diameter greater than 6mm) in 1985 as a simple framework that physicians, novice dermatologists and non-physicians could use to learn about the features of melanoma in its early curable stage [4]; the rule is being promoted by the American Cancer Society as a method to help in seeking early medical evaluation of any suspicious pigmented lesions. The ABCD rule provides a checklist of premalignant changes in skin lesions and an appraisal of pigmented cutaneous lesions that may need

Objectives

Methods

Results

Conclusion