Scholarlink

Background <p>Malignant melanoma (MM) is the most aggressive skin cancer, requiring early diagnosis for better outcomes. While deep learning models have shown promise in dermatological image analysis, their performance is constrained by limited training data. Generative Adversarial Networks (GANs) offer a solution by generating synthetic images for data augmentation. However, assessing their clinical reliability remains difficult as automated metrics may not fully capture visual realism or clinical usability.</p> The Objective <p>This study presents a comprehensive framework for creating high-quality synthetic dermatoscopic pictures of MM lesions, as well as a holistic validation methodology that uses quantitative metrics and qualitative dermatologist assessment to provide a full clinical evaluation of the generated images. Three GAN architectures (DCGAN, StyleGAN2, and StyleGAN3-t) are explored. Lesions on the face, palms, and soles are excluded due to their unique dermoscopic patterns.</p> Materials and Methods <p>A dataset of 1,774 dermatoscopic body MM images was used to train the models, assessed with Fréchet Inception Distance (FID), Kernel Inception Distance (KID), precision, and recall. Afterwards, a panel of 17 dermatologists with different levels of expertise assessed image quality using a 7-point Likert scale, with accuracy, sensitivity, specificity, and inter-rater agreement analysed.</p> Results <p>StyleGAN2 achieved the best image fidelity (FID: 18.89, KID: 0.0025), while StyleGAN3-t demonstrated stable but slower convergence. Both StyleGAN models outperformed DCGAN in diversity and fidelity. The validation study showed that StyleGAN2-generated images were often indistinguishable from real ones, reflected in low specificity and accuracy values among evaluators.</p> Conclusions <p>The study highlights the effectiveness of GANs in generating high-quality synthetic images, proposing a validation framework that integrates expert assessments with state-of-the-art quantitative metrics. This approach advances standardisation in GAN evaluation, ensuring synthetic images are clinically relevant for dermatological AI applications.</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

Advancing synthetic data for dermatology: GAN comparison with multi-metric and expert validation approach

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年4月25日

查看全文
  • Alessio Luschi,
  • Linda Tognetti,
  • Alessandra Cartocci,
  • Gabriele Cevenini,
  • Pietro Rubegni,
  • Ernesto Iadanza

摘要

Background

Malignant melanoma (MM) is the most aggressive skin cancer, requiring early diagnosis for better outcomes. While deep learning models have shown promise in dermatological image analysis, their performance is constrained by limited training data. Generative Adversarial Networks (GANs) offer a solution by generating synthetic images for data augmentation. However, assessing their clinical reliability remains difficult as automated metrics may not fully capture visual realism or clinical usability.

The Objective

This study presents a comprehensive framework for creating high-quality synthetic dermatoscopic pictures of MM lesions, as well as a holistic validation methodology that uses quantitative metrics and qualitative dermatologist assessment to provide a full clinical evaluation of the generated images. Three GAN architectures (DCGAN, StyleGAN2, and StyleGAN3-t) are explored. Lesions on the face, palms, and soles are excluded due to their unique dermoscopic patterns.

Materials and Methods

A dataset of 1,774 dermatoscopic body MM images was used to train the models, assessed with Fréchet Inception Distance (FID), Kernel Inception Distance (KID), precision, and recall. Afterwards, a panel of 17 dermatologists with different levels of expertise assessed image quality using a 7-point Likert scale, with accuracy, sensitivity, specificity, and inter-rater agreement analysed.

Results

StyleGAN2 achieved the best image fidelity (FID: 18.89, KID: 0.0025), while StyleGAN3-t demonstrated stable but slower convergence. Both StyleGAN models outperformed DCGAN in diversity and fidelity. The validation study showed that StyleGAN2-generated images were often indistinguishable from real ones, reflected in low specificity and accuracy values among evaluators.

Conclusions

The study highlights the effectiveness of GANs in generating high-quality synthetic images, proposing a validation framework that integrates expert assessments with state-of-the-art quantitative metrics. This approach advances standardisation in GAN evaluation, ensuring synthetic images are clinically relevant for dermatological AI applications.