Enhanced Dermatology Image Quality Assessment via Cross-Domain Training

TL;DR

This paper introduces a cross-domain training approach for dermatology image quality assessment, leveraging both dermatology and general image datasets to improve accuracy and robustness in teledermatology applications.

Contribution

It proposes a novel cross-domain training method and creates a new dermatology IQA database, enhancing model performance with larger, diverse datasets.

Findings

Cross-domain training improves IQA accuracy across dermatology and general images.

The new dermatology IQA database enables better model training and evaluation.

Models trained with combined datasets outperform those trained on dermatology data alone.

Abstract

Teledermatology has become a widely accepted communication method in daily clinical practice, enabling remote care while showing strong agreement with in-person visits. Poor image quality remains an unsolved problem in teledermatology and is a major concern to practitioners, as bad-quality images reduce the usefulness of the remote consultation process. However, research on Image Quality Assessment (IQA) in dermatology is sparse, and does not leverage the latest advances in non-dermatology IQA, such as using larger image databases with ratings from large groups of human observers. In this work, we propose cross-domain training of IQA models, combining dermatology and non-dermatology IQA datasets. For this purpose, we created a novel dermatology IQA database, Legit.Health-DIQA-Artificial, using dermatology images from several sources and having them annotated by a group of human observers. We demonstrate that cross-domain training yields optimal performance across domains and overcomes one of the biggest limitations in dermatology IQA, which is the small scale of data, and leads to models trained on a larger pool of image distortions, resulting in a better management of image quality in the teledermatology process.