Scholarlink

<b>Purpose</b> <p>We describe an extended overview and evaluation of the S-SYNTH skin simulation approach (Kim et al. in MICCAI, Springer, pp 734–744, 2024), a knowledge-based skin simulation approach to generate synthetic skin images for aiding artificial intelligence (AI) algorithm development.</p> <b>Methods</b> <p>The skin object model allows for controlled variation in skin appearance, including skin color, presence of hair, lesion shape, and blood fraction. Using this approach, we study the effect of model variations on AI models for skin lesion segmentation.</p> <b>Results</b> <p>Results obtained using synthetic data follow similar comparative trends as patient dermatologic images and have the potential to mitigate biases and limitations of existing patient datasets including small dataset size and poor representativeness. We also demonstrate a novel use case where S-SYNTH can enhance diffusion model performance for dermatological applications.</p> <b>Conclusion</b> <p>Synthetic images have the ability to address many limitations of available patient datasets in skin imaging. Simulating datasets allows for tight control over the parameter space and the ability to create rare examples and annotations that are typically missing from patient datasets.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Synthetic skin image generation using a physics-based, object-to-image computational pipeline

  • 期刊论文

  • 发表日期：

    2026年3月9日

查看全文
  • Elena Sizikova,
  • Niloufar Saharkhiz,
  • Andrea Kim,
  • Miguel Lago,
  • Jana G. Delfino,
  • Aldo Badano

摘要

Purpose

We describe an extended overview and evaluation of the S-SYNTH skin simulation approach (Kim et al. in MICCAI, Springer, pp 734–744, 2024), a knowledge-based skin simulation approach to generate synthetic skin images for aiding artificial intelligence (AI) algorithm development.

Methods

The skin object model allows for controlled variation in skin appearance, including skin color, presence of hair, lesion shape, and blood fraction. Using this approach, we study the effect of model variations on AI models for skin lesion segmentation.

Results

Results obtained using synthetic data follow similar comparative trends as patient dermatologic images and have the potential to mitigate biases and limitations of existing patient datasets including small dataset size and poor representativeness. We also demonstrate a novel use case where S-SYNTH can enhance diffusion model performance for dermatological applications.

Conclusion

Synthetic images have the ability to address many limitations of available patient datasets in skin imaging. Simulating datasets allows for tight control over the parameter space and the ability to create rare examples and annotations that are typically missing from patient datasets.