DermaFlux: Synthetic Skin Lesion Generation with Rectified Flows for Enhanced Image Classification

Abstract

Despite recent advances in deep generative modeling, skin lesion classification systems remain constrained by the limited availability of large, diverse, and well-annotated clinical datasets, resulting in class imbalance between benign and malignant lesions and consequently reduced generalization performance. We introduce DermaFlux, a rectified flow-based text-to-image generative framework that synthesizes clinically grounded skin lesion images from natural language descriptions of dermatological attributes. Built upon Flux.1, DermaFlux is fine-tuned using parameter-efficient Low-Rank Adaptation (LoRA) on a large curated collection of publicly available clinical image datasets. We construct image-text pairs using synthetic textual captions generated by Llama 3.2, following established dermatological criteria including lesion asymmetry, border irregularity, and color variation. Extensive experiments demonstrate that DermaFlux generates diverse and clinically meaningful dermatology images that improve binary classification performance by up to 6% when augmenting small real-world datasets, and by up to 9% when classifiers are trained on DermaFlux-generated synthetic images rather than diffusion-based synthetic images. Our ImageNet-pretrained ViT fine-tuned with only 2,500 real images and 4,375 DermaFlux-generated samples achieves 78.04% binary classification accuracy and an AUC of 0.859, surpassing the next best dermatology model by 8%.

Figures (5)

• Figure 1: DermaFlux synthesizes a skin lesion image $x_1$ by transporting Gaussian noise $z_0$ to a clean latent representation $z_1$, conditioned on the input caption. The Flux.1blackforestlabs_flux1 backbone is frozen () and only the injected LoRA parameters are trained ().
• Figure 2: Given a lesion image and its label, benign (left) or malignant (right), LLama 3.2 generates a synthetic caption using the prompt: "This is an image containing a [label] lesion. Give me a description of this mole regarding its asymmetry, border irregularity, and color."
• Figure 3: Examples highlighting our method’s capacity to produce diverse and realistic skin lesion images in both benign (top) and malignant (bottom) categories.
• Figure 4: Test accuracy scores for ResNeXt and ViT across varying real-to-synthetic training data ratios. Results are averaged over five independent runs (different seeds).
• Figure 5: DermaFlux-ViT separates malignant and benign test samples more reliably than competing models.