Border detection in dermoscopy images using statistical region merging

TLDR

Advances in skin imaging and image‑processing techniques have spurred interest in computer‑aided melanoma diagnosis, with automated border detection being a critical step for accurate downstream analysis. This study aims to introduce a fast, unsupervised border‑detection method for dermoscopy images of pigmented skin lesions. The method employs a statistical region‑merging algorithm, is evaluated on 90 dermoscopy images, uses dermatologist‑determined borders as ground truth, and is benchmarked against four state‑of‑the‑art automated techniques. Results show that the proposed approach delivers both rapid and accurate border detection, outperforming existing methods.

Abstract

Background: As a result of advances in skin imaging technology and the development of suitable image processing techniques, during the last decade, there has been a significant increase of interest in the computer‐aided diagnosis of melanoma. Automated border detection is one of the most important steps in this procedure, because the accuracy of the subsequent steps crucially depends on it. Methods: In this article, we present a fast and unsupervised approach to border detection in dermoscopy images of pigmented skin lesions based on the statistical region merging algorithm. Results: The method is tested on a set of 90 dermoscopy images. The border detection error is quantified by a metric in which three sets of dermatologist‐determined borders are used as the ground‐truth. The proposed method is compared with four state‐of‐the‐art automated methods (orientation‐sensitive fuzzy c‐means, dermatologist‐like tumor extraction algorithm, meanshift clustering, and the modified JSEG method). Conclusion: The results demonstrate that the method presented here achieves both fast and accurate border detection in dermoscopy images.