Approximate Lesion Localization in Dermoscopy Images

TL;DR

This paper introduces a fast and accurate method for approximate lesion localization in dermoscopy images, serving as a preprocessing step for border detection in melanoma diagnosis.

Contribution

It presents a novel ensemble thresholding approach combined with iterative frame removal for efficient lesion localization in dermoscopy images.

Findings

Achieves fast lesion localization with low error rates.

Validated on 428 images with dermatologist-verified borders.

Outperforms existing localization methods in accuracy and speed.

Abstract

Background: Dermoscopy is one of the major imaging modalities used in the diagnosis of melanoma and other pigmented skin lesions. Due to the difficulty and subjectivity of human interpretation, automated analysis of dermoscopy images has become an important research area. Border detection is often the first step in this analysis. Methods: In this article, we present an approximate lesion localization method that serves as a preprocessing step for detecting borders in dermoscopy images. In this method, first the black frame around the image is removed using an iterative algorithm. The approximate location of the lesion is then determined using an ensemble of thresholding algorithms. Results: The method is tested on a set of 428 dermoscopy images. The localization error is quantified by a metric that uses dermatologist determined borders as the ground truth. Conclusion: The results demonstrate that the method presented here achieves both fast and accurate localization of lesions in dermoscopy images.