Synthetic Melanoma Image Generation and Evaluation Using Generative Adversarial Networks
Open Access
- 20 February 2026
- journal article
- research article
- Published by MDPI AG in Bioengineering
- Vol. 13 (2) , 245
Abstract
Melanoma is the most lethal form of skin cancer, and early detection is critical for improving patient outcomes. Although dermoscopy combined with deep learning has advanced automated skin-lesion analysis, progress is hindered by limited access to large, well-annotated datasets and by severe class imbalance, where melanoma images are substantially underrepresented. To address these challenges, we present the first systematic benchmarking study comparing four GAN architectures—DCGAN, StyleGAN2, and two StyleGAN3 variants (T and R)—for high-resolution () melanoma-specific synthesis. We train and optimize all models on two expert-annotated benchmarks (ISIC 2018 and ISIC 2020) under unified preprocessing and hyperparameter exploration, with particular attention to R1 regularization tuning. Image quality is assessed through a multi-faceted protocol combining distribution-level metrics (FID), sample-level representativeness (FMD), qualitative dermoscopic inspection, downstream classification with a frozen EfficientNet-based melanoma detector, and independent evaluation by two board-certified dermatologists. StyleGAN2 achieves the best balance of quantitative performance and perceptual quality, attaining FID scores of 24.8 (ISIC 2018) and 7.96 (ISIC 2020) at . The frozen classifier recognizes 83% of StyleGAN2-generated images as melanoma, while dermatologists distinguish synthetic from real images at only 66.5% accuracy (chance = 50%), with low inter-rater agreement (). In a controlled augmentation experiment, adding synthetic melanoma images to address class imbalance improved melanoma detection AUC from 0.925 to 0.945 on a held-out real-image test set. These findings demonstrate that StyleGAN2-generated melanoma images preserve diagnostically relevant features and can provide a measurable benefit for mitigating class imbalance in melanoma-focused machine learning pipelines.
Keywords
All Related Versions
Funding Information
- Texas Tech University Innovation Hub, Prototype Fund
This publication has 40 references indexed in Scilit:
- Design and development of a systematic validation protocol for synthetic melanoma images for responsible use in medical artificial intelligenceBiocybernetics and Biomedical Engineering, 2025
- Assessing a Proposed Dynamic Ratio in Dataset Class Imbalance with GAN's Generated Melanoma Images2025
- Recent innovations in machine learning for skin cancer lesion analysis and classification: A comprehensive analysis of computer‐aided diagnosisPrecision Medical Sciences, 2025
- Diffusion-Based Data Augmentation for Skin Disease Classification: Impact Across Original Medical Datasets to Fully Synthetic Images2024
- Generative adversarial networks based skin lesion segmentationScientific Reports, 2023
- A patient-centric dataset of images and metadata for identifying melanomas using clinical contextScientific Data, 2021
- GAN-based synthetic medical image augmentation for increased CNN performance in liver lesion classificationNeurocomputing, 2018
- Fast Adaptive Bilateral FilteringIEEE Transactions on Image Processing, 2018
- Targeted agents and immunotherapies: optimizing outcomes in melanomaNature Reviews Clinical Oncology, 2017
- Epiluminescence Microscopy for the Diagnosis of Doubtful Melanocytic Skin LesionsArchives of Dermatology, 1998