Towards Automated Differential Diagnosis of Skin Diseases Using Deep Learning and Imbalance-Aware Strategies

2026-01-01

arXiv.org

AI Summary

This study addresses the challenges of delayed and inaccurate dermatological diagnoses resulting from limited access to specialized healthcare resources by proposing a deep learning approach based on the Swin Transformer architecture. The method integrates transfer learning, targeted data augmentation, and an imbalance-aware strategy to significantly enhance the automatic recognition of multiple skin lesion categories. Evaluated on the ISIC2019 dataset, the proposed model achieves a classification accuracy of 87.71% across eight distinct skin diseases, substantially outperforming existing state-of-the-art methods. These results demonstrate the model’s strong potential for clinical decision support and patient self-assessment applications in real-world dermatological care settings.

Technology Category

• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification
• Computer Vision: Object Detection & Categorization
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning

Application Category

• Web Mining and Content Analysis: Large pretrained models with web data
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

As dermatological conditions become increasingly common and the availability of dermatologists remains limited, there is a growing need for intelligent tools to support both patients and clinicians in the timely and accurate diagnosis of skin diseases. In this project, we developed a deep learning based model for the classification and diagnosis of skin conditions. By leveraging pretraining on publicly available skin disease image datasets, our model effectively extracted visual features and accurately classified various dermatological cases. Throughout the project, we refined the model architecture, optimized data preprocessing workflows, and applied targeted data augmentation techniques to improve overall performance. The final model, based on the Swin Transformer, achieved a prediction accuracy of 87.71 percent across eight skin lesion classes on the ISIC2019 dataset. These results demonstrate the model's potential as a diagnostic support tool for clinicians and a self assessment aid for patients.

Problem

• differential diagnosis
• skin diseases
• deep learning
• class imbalance
• automated diagnosis

Innovation

• Deep Learning
• Swin Transformer
• Imbalance-Aware Strategies
• Skin Disease Classification
• Data Augmentation