Automated Measurement of Eczema Severity with Self-Supervised Learning

2025-04-21

AI Summary

To address the scarcity of manually annotated data for automatic severity assessment of atopic dermatitis (eczema) in home-based settings, this paper proposes a two-stage self-supervised learning framework. In the first stage, SegGPT enables few-shot lesion segmentation with minimal pixel-level annotations; in the second stage, self-supervised visual features extracted by DINO are fused with segmentation-mask-guided regional representations and classified into four severity levels via a lightweight MLP. Evaluated on a real-world eczema image dataset, the method achieves a weighted F1-score of 0.67±0.01—significantly outperforming fine-tuned ResNet-18 (0.44) and ViT (0.40). The core contribution lies in the first integration of context-learning-based segmentation and self-supervised representation learning for quantitative skin disease severity assessment, establishing a scalable, low-resource paradigm for medical image analysis.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Unsupervised & Self-Supervised Learning
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Responsible Web: Data and user privacy-enhancing technologies for the Web

Abstract

Automated diagnosis of eczema using images acquired from digital camera can enable individuals to self-monitor their recovery. The process entails first segmenting out the eczema region from the image and then measuring the severity of eczema in the segmented region. The state-of-the-art methods for automated eczema diagnosis rely on deep neural networks such as convolutional neural network (CNN) and have shown impressive performance in accurately measuring the severity of eczema. However, these methods require massive volume of annotated data to train which can be hard to obtain. In this paper, we propose a self-supervised learning framework for automated eczema diagnosis under limited training data regime. Our framework consists of two stages: i) Segmentation, where we use an in-context learning based algorithm called SegGPT for few-shot segmentation of eczema region from the image; ii) Feature extraction and classification, where we extract DINO features from the segmented regions and feed it to a multi-layered perceptron (MLP) for 4-class classification of eczema severity. When evaluated on a dataset of annotated"in-the-wild"eczema images, we show that our method outperforms (Weighted F1: 0.67 $pm$ 0.01) the state-of-the-art deep learning methods such as finetuned Resnet-18 (Weighted F1: 0.44 $pm$ 0.16) and Vision Transformer (Weighted F1: 0.40 $pm$ 0.22). Our results show that self-supervised learning can be a viable solution for automated skin diagnosis where labeled data is scarce.

Problem

• Automated eczema severity measurement using self-supervised learning
• Few-shot segmentation and classification with limited annotated data
• Outperforming existing methods in eczema severity classification

Innovation

• Self-supervised learning for eczema diagnosis
• SegGPT for few-shot eczema region segmentation
• DINO features with MLP for severity classification