S-SYNTH: Knowledge-Based, Synthetic Generation of Skin Images

TL;DR

S-SYNTH is an innovative, open-source framework that generates diverse, realistic synthetic skin images using a knowledge-based model, aiding AI development in dermatology by addressing data limitations.

Contribution

It introduces the first adaptable, knowledge-based skin simulation framework for synthetic data generation, improving AI training and evaluation in dermatology.

Findings

Synthetic data follow similar trends as real images in AI model evaluation.

The framework mitigates dataset biases and enhances diversity.

Synthetic images support robust skin lesion segmentation models.

Abstract

Development of artificial intelligence (AI) techniques in medical imaging requires access to large-scale and diverse datasets for training and evaluation. In dermatology, obtaining such datasets remains challenging due to significant variations in patient populations, illumination conditions, and acquisition system characteristics. In this work, we propose S-SYNTH, the first knowledge-based, adaptable open-source skin simulation framework to rapidly generate synthetic skin, 3D models and digitally rendered images, using an anatomically inspired multi-layer, multi-component skin and growing lesion model. The skin model allows for controlled variation in skin appearance, such as skin color, presence of hair, lesion shape, and blood fraction among other parameters. We use this framework to study the effect of possible variations on the development and evaluation of AI models for skin lesion segmentation, and show that results obtained using synthetic data follow similar comparative trends as real dermatologic images, while mitigating biases and limitations from existing datasets including small dataset size, lack of diversity, and underrepresentation.