Accurate Segmentation of Dermoscopic Images based on Local Binary Pattern Clustering

TL;DR

This paper introduces a novel dermoscopic image segmentation method combining Local Binary Patterns and K-Means clustering, achieving more detailed and consistent lesion borders for improved skin cancer diagnosis.

Contribution

It presents a new segmentation approach that enhances border detail and consistency in dermoscopic images using LBP and K-Means clustering, outperforming traditional methods.

Findings

More realistic lesion borders detected

Reduced variability across different images

Consistent performance in diverse dermoscopic images

Abstract

Segmentation is a key stage in dermoscopic image processing, where the accuracy of the border line that defines skin lesions is of utmost importance for subsequent algorithms (e.g., classification) and computer-aided early diagnosis of serious medical conditions. This paper proposes a novel segmentation method based on Local Binary Patterns (LBP), where LBP and K-Means clustering are combined to achieve a detailed delineation in dermoscopic images. In comparison with usual dermatologist-like segmentation (i.e., the available ground-truth), the proposed method is capable of finding more realistic borders of skin lesions, i.e., with much more detail. The results also exhibit reduced variability amongst different performance measures and they are consistent across different images. The proposed method can be applied for cell-based like segmentation adapted to the lesion border growing specificities. Hence, the method is suitable to follow the growth dynamics associated with the lesion border geometry in skin melanocytic images.