Unsupervised Skin Lesion Segmentation via Structural Entropy Minimization on Multi-Scale Superpixel Graphs

TL;DR

This paper introduces SLED, an unsupervised skin lesion segmentation method that minimizes structural entropy on multi-scale superpixel graphs, improving accuracy and interpretability over existing approaches.

Contribution

The paper presents a novel unsupervised segmentation framework combining structural entropy minimization and multi-scale outlier detection for skin lesion analysis.

Findings

SLED outperforms nine unsupervised methods on four benchmarks.

The multi-scale approach enhances segmentation accuracy.

Case studies confirm the effectiveness of the proposed method.

Abstract

Skin lesion segmentation is a fundamental task in dermoscopic image analysis. The complex features of pixels in the lesion region impede the lesion segmentation accuracy, and existing deep learning-based methods often lack interpretability to this problem. In this work, we propose a novel unsupervised Skin Lesion sEgmentation framework based on structural entropy and isolation forest outlier Detection, namely SLED. Specifically, skin lesions are segmented by minimizing the structural entropy of a superpixel graph constructed from the dermoscopic image. Then, we characterize the consistency of healthy skin features and devise a novel multi-scale segmentation mechanism by outlier detection, which enhances the segmentation accuracy by leveraging the superpixel features from multiple scales. We conduct experiments on four skin lesion benchmarks and compare SLED with nine representative unsupervised segmentation methods. Experimental results demonstrate the superiority of the proposed framework. Additionally, some case studies are analyzed to demonstrate the effectiveness of SLED.