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

• URL: http://arxiv.org/abs/2603.16392v1
• Date: Tue, 17 Mar 2026 11:25:46 GMT
• Title: DermaFlux: Synthetic Skin Lesion Generation with Rectified Flows for Enhanced Image Classification
• Abstract summary: DermaFlux is a rectified flow-based text-to-image generative framework that synthesizes clinically grounded skin lesion images.<n>We construct image-text pairs using synthetic textual captions generated by Llama 3.2.<n>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%.
• Score: 72.0680382603686
• License: http://creativecommons.org/licenses/by/4.0/
• 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%.

Related papers

• Controllable Generation of Diverse Dermatological Imagery for Fair and Efficient Malignancy Classification [5.316734431170194]
  We introduce cgDDI (Controllable Generation of Diverse Dermatological Imagery), a hybrid framework that synthesizes realistic healthy skin samples without disturbing other input properties.<n>We grow a 656-image dataset by more than 400x and validate across two datasets: biopsy-confirmed Diverse Dermatology Images (DDI) and expert-verified Fitzpatrick17k (F17k)<n>On the DDI benchmark, we achieve malignancy classification accuracy of 86.4% under synthetic-only training and 90.9% state-of-the-art performance with real data fine-tuning.
  arXiv  Detail & Related papers  (2026-07-14T17:32:13Z)
• SkinGenBench: Generative Model and Preprocessing Effects for Synthetic Dermoscopic Augmentation in Melanoma Diagnosis [0.0]
  generative architecture choice has a stronger influence on both image fidelity and diagnostic utility than preprocessing complexity.<n>Synthetic data augmentation substantially improved melanoma detection with 8-15% absolute gains in melanoma F1-score.
  arXiv  Detail & Related papers  (2025-12-19T13:52:11Z)
• A Semantically Enhanced Generative Foundation Model Improves Pathological Image Synthesis [82.01597026329158]
  We introduce a Correlation-Regulated Alignment Framework for Tissue Synthesis (CRAFTS) for pathology-specific text-to-image synthesis.<n>CRAFTS incorporates a novel alignment mechanism that suppresses semantic drift to ensure biological accuracy.<n>This model generates diverse pathological images spanning 30 cancer types, with quality rigorously validated by objective metrics and pathologist evaluations.
  arXiv  Detail & Related papers  (2025-12-15T10:22:43Z)
• Controllable Skin Synthesis via Lesion-Focused Vector Autoregression Model [23.122488283724433]
  The study highlights our controllable skin synthesis model's effectiveness in generating high-fidelity, clinically relevant synthetic skin images.<n>Our method achieves the best overall FID score (average 0.74) among seven lesion types, improving upon the previous state-of-the-art (SOTA) by 6.3%.
  arXiv  Detail & Related papers  (2025-08-27T07:04:58Z)
• LesionGen: A Concept-Guided Diffusion Model for Dermatology Image Synthesis [4.789822624169502]
  We introduce LesionGen, a clinically informed T2I-DPM framework for dermatology image synthesis.<n>LesionGen is trained on structured, concept-rich dermatological captions derived from expert annotations and pseudo-generated, concept-guided reports.<n>Our results demonstrate that models trained solely on our synthetic dataset achieve classification accuracy comparable to those trained on real images.
  arXiv  Detail & Related papers  (2025-07-30T18:07:34Z)
• SkinDualGen: Prompt-Driven Diffusion for Simultaneous Image-Mask Generation in Skin Lesions [0.0]
  We propose a novel method that leverages the pretrained Stable Diffusion-2.0 model to generate high-quality synthetic skin lesion images.<n>A hybrid dataset combining real and synthetic data markedly enhances the performance of classification and segmentation models.
  arXiv  Detail & Related papers  (2025-07-26T15:00:37Z)
• FairSkin: Fair Diffusion for Skin Disease Image Generation [54.29840149709033]
  Diffusion Model (DM) has become a leading method in generating synthetic medical images, but it suffers from a critical twofold bias. We propose FairSkin, a novel DM framework that mitigates these biases through a three-level resampling mechanism. Our approach significantly improves the diversity and quality of generated images, contributing to more equitable skin disease detection in clinical settings.
  arXiv  Detail & Related papers  (2024-10-29T21:37:03Z)
• Significantly improving zero-shot X-ray pathology classification via fine-tuning pre-trained image-text encoders [50.689585476660554]
  We propose a new fine-tuning strategy that includes positive-pair loss relaxation and random sentence sampling. Our approach consistently improves overall zero-shot pathology classification across four chest X-ray datasets and three pre-trained models.
  arXiv  Detail & Related papers  (2022-12-14T06:04:18Z)
• Harmonizing Pathological and Normal Pixels for Pseudo-healthy Synthesis [68.5287824124996]
  We present a new type of discriminator, the segmentor, to accurately locate the lesions and improve the visual quality of pseudo-healthy images. We apply the generated images into medical image enhancement and utilize the enhanced results to cope with the low contrast problem. Comprehensive experiments on the T2 modality of BraTS demonstrate that the proposed method substantially outperforms the state-of-the-art methods.
  arXiv  Detail & Related papers  (2022-03-29T08:41:17Z)
• Selective Synthetic Augmentation with HistoGAN for Improved Histopathology Image Classification [11.087537668968888]
  We propose a conditional GAN model, namely HistoGAN, for synthesizing realistic histopathology image patches conditioned on class labels. We also investigate a novel synthetic augmentation framework that selectively adds new synthetic image patches generated by our proposed HistoGAN. Our models are evaluated on two datasets: a cervical histopathology image dataset with limited annotations, and another dataset of lymph node histopathology images with metastatic cancer.
  arXiv  Detail & Related papers  (2021-11-10T23:25:39Z)
• Malignancy Prediction and Lesion Identification from Clinical Dermatological Images [65.1629311281062]
  We consider machine-learning-based malignancy prediction and lesion identification from clinical dermatological images. We first identify all lesions present in the image regardless of sub-type or likelihood of malignancy, then it estimates their likelihood of malignancy, and through aggregation, it also generates an image-level likelihood of malignancy.
  arXiv  Detail & Related papers  (2021-04-02T20:52:05Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.