Accurate Measles Rash Detection via Vision Transformer Fine-Tuning

TL;DR

This paper presents a transfer learning approach using a Vision Transformer model fine-tuned for accurate measles rash detection, achieving over 95% accuracy to aid early diagnosis and outbreak control.

Contribution

It introduces the application of a pretrained Data-efficient Image Transformer for measles rash classification, demonstrating high accuracy and comparing it with CNNs.

Findings

Achieved 95.17% accuracy in measles rash detection

Outperformed traditional CNN models in classification tasks

Provided insights for future research directions

Abstract

Measles, a highly contagious disease declared eliminated in the United States in 2000 after decades of successful vaccination campaigns, resurged in 2025, with 1,356 confirmed cases reported as of August 5, 2025. Given its rapid spread among susceptible individuals, fast and reliable diagnostic systems are critical for early prevention and containment. In this work, we applied transfer learning to fine-tune a pretrained Data-efficient Image Transformer (DeiT) model for distinguishing measles rashes from other skin conditions. After tuning the classification head on a diverse, curated skin rash image dataset, the DeiT model achieved an average classification accuracy of 95.17%, precision of 95.06%, recall of 95.17%, and an F1-score of 95.03%, demonstrating high effectiveness in accurate measles detection to aid outbreak control. We also compared the DeiT model with a convolutional neural network and discussed the directions for future research.