Format

Send to

Choose Destination
Comput Med Imaging Graph. 2015 Jul;43:44-52. doi: 10.1016/j.compmedimag.2015.02.011. Epub 2015 Mar 7.

Automatic differentiation of melanoma from dysplastic nevi.

Author information

1
Computer Vision and Robotics Group, Universitat de Girona, Campus Montilivi, Edifici PIV, s/n, 17071 Girona, Spain; Le2i-UMR CNRS 6306, Université de Bourgogne, BP 47870, 21078 Dijon, France. Electronic address: mojdeh.rastgoo@gmail.com.
2
Computer Vision and Robotics Group, Universitat de Girona, Campus Montilivi, Edifici PIV, s/n, 17071 Girona, Spain.
3
Le2i-UMR CNRS 6306, Université de Bourgogne, BP 47870, 21078 Dijon, France.

Abstract

Malignant melanoma causes the majority of deaths related to skin cancer. Nevertheless, it is the most treatable one, depending on its early diagnosis. The early prognosis is a challenging task for both clinicians and dermatologist, due to the characteristic similarities of melanoma with other skin lesions such as dysplastic nevi. In the past decades, several computerized lesion analysis algorithms have been proposed by the research community for detection of melanoma. These algorithms mostly focus on differentiating melanoma from benign lesions and few have considered the case of melanoma against dysplastic nevi. In this paper, we consider the most challenging task and propose an automatic framework for differentiation of melanoma from dysplastic nevi. The proposed framework also considers combination and comparison of several texture features beside the well used colour and shape features based on "ABCD" clinical rule in the literature. Focusing on dermoscopy images, we evaluate the performance of the framework using two feature extraction approaches, global and local (bag of words) and three classifiers such as support vector machine, gradient boosting and random forest. Our evaluation revealed the potential of texture features and random forest as an almost independent classifier. Using texture features and random forest for differentiation of melanoma and dysplastic nevi, the framework achieved the highest sensitivity of 98% and specificity of 70%.

KEYWORDS:

Classification; Colour; Dermoscopy imaging; Dysplastic; Machine learning; Melanoma; Shape features; Texture

[Indexed for MEDLINE]

Supplemental Content

Full text links

Icon for Elsevier Science
Loading ...
Support Center