Segmentation of both Diseased and Healthy Skin from Clinical Photographs in a Primary Care Setting

TL;DR

This study develops a deep learning method for segmenting both diseased and healthy skin in clinical photographs, highlighting the importance of fine-tuning with relevant data for improved accuracy.

Contribution

It introduces a novel dataset of clinical skin images and compares U-Net variants, demonstrating the impact of fine-tuning and transfer learning in skin segmentation tasks.

Findings

Dense Residual U-Net improves transfer learning performance by 7.8% in Jaccard index.

U-Net outperforms Dense Residual U-Net when trained with task-specific data.

Fine-tuning significantly enhances segmentation accuracy over direct transfer.

Abstract

This work presents the first segmentation study of both diseased and healthy skin in standard camera photographs from a clinical environment. Challenges arise from varied lighting conditions, skin types, backgrounds, and pathological states. For study, 400 clinical photographs (with skin segmentation masks) representing various pathological states of skin are retrospectively collected from a primary care network. 100 images are used for training and fine-tuning, and 300 are used for evaluation. This distribution between training and test partitions is chosen to reflect the difficulty in amassing large quantities of labeled data in this domain. A deep learning approach is used, and 3 public segmentation datasets of healthy skin are collected to study the potential benefits of pre-training. Two variants of U-Net are evaluated: U-Net and Dense Residual U-Net. We find that Dense Residual U-Nets have a 7.8% improvement in Jaccard, compared to classical U-Net architectures (0.55 vs. 0.51 Jaccard), for direct transfer, where fine-tuning data is not utilized. However, U-Net outperforms Dense Residual U-Net for both direct training (0.83 vs. 0.80) and fine-tuning (0.89 vs. 0.88). The stark performance improvement with fine-tuning compared to direct transfer and direct training emphasizes both the need for adequate representative data of diseased skin, and the utility of other publicly available data sources for this task.