SkinGenBench: Generative Model and Preprocessing Effects for Synthetic Dermoscopic Augmentation in Melanoma Diagnosis

TL;DR

SkinGenBench systematically evaluates how different generative models and preprocessing pipelines affect synthetic dermoscopic image quality and melanoma diagnosis performance, highlighting architecture choice over preprocessing complexity.

Contribution

This work introduces SkinGenBench, a benchmark comparing StyleGAN2-ADA and diffusion models for synthetic dermoscopic data augmentation in melanoma detection.

Findings

StyleGAN2-ADA produces images with lower FID and KID scores, closer to real data.

Synthetic augmentation improves melanoma detection F1-score by 8-15%.

Advanced artifact removal offers limited benefits for diagnostic performance.

Abstract

This work introduces SkinGenBench, a systematic biomedical imaging benchmark that investigates how preprocessing complexity interacts with generative model choice for synthetic dermoscopic image augmentation and downstream melanoma diagnosis. Using a curated dataset of $14,116$ dermoscopic images from HAM10000 and MILK10K across five lesion classes, we evaluate the two representative generative paradigms: StyleGAN2-ADA and Denoising Diffusion Probabilistic Models (DDPMs) under basic geometric augmentation and advanced artifact removal pipelines. Synthetic melanoma images are assessed using established perceptual and distributional metrics (FID, KID, IS), feature space analysis, and their impact on diagnostic performance across five downstream classifiers. Experimental results demonstrate that generative architecture choice has a stronger influence on both image fidelity and diagnostic utility than preprocessing complexity. StyleGAN2-ADA consistently produced synthetic images more closely aligned with real data distributions, achieving the lowest FID ($\approx 65.5$) and KID ($\approx 0.05$), while diffusion models generated higher variance samples at the cost of reduced perceptual fidelity and class anchoring. Advanced artifact removal yielded only marginal improvements in generative metrics and provided limited downstream diagnostic gains, suggesting possible suppression of clinically relevant texture cues. In contrast, synthetic data augmentation substantially improved melanoma detection with $8$-$15$\% absolute gains in melanoma F1-score, and ViT-B/16 achieving F1 $\approx 0.88$ and ROC-AUC $\approx 0.98$, representing an improvement of approximately $14\%$ over non-augmented baselines. Our code can be found at https://github.com/adarsh-crafts/SkinGenBench