Skin Lesion Segmentation: U-Nets versus Clustering

TL;DR

This paper compares U-Net and C-Means clustering methods for skin lesion segmentation, highlighting U-Net's superior accuracy and the benefits of histogram equalization, all designed for CPU-based implementation.

Contribution

It introduces a CPU-compatible U-Net approach with histogram equalization and compares it to a simpler clustering method for skin lesion segmentation.

Findings

U-Nets outperform clustering in segmentation accuracy

Histogram equalization improves U-Net results

U-Nets achieve higher Jaccard Index scores

Abstract

Many automatic skin lesion diagnosis systems use segmentation as a preprocessing step to diagnose skin conditions because skin lesion shape, border irregularity, and size can influence the likelihood of malignancy. This paper presents, examines and compares two different approaches to skin lesion segmentation. The first approach uses U-Nets and introduces a histogram equalization based preprocessing step. The second approach is a C-Means clustering based approach that is much simpler to implement and faster to execute. The Jaccard Index between the algorithm output and hand segmented images by dermatologists is used to evaluate the proposed algorithms. While many recently proposed deep neural networks to segment skin lesions require a significant amount of computational power for training (i.e., computer with GPUs), the main objective of this paper is to present methods that can be used with only a CPU. This severely limits, for example, the number of training instances that can be presented to the U-Net. Comparing the two proposed algorithms, U-Nets achieved a significantly higher Jaccard Index compared to the clustering approach. Moreover, using the histogram equalization for preprocessing step significantly improved the U-Net segmentation results.