Controllable Generation of Diverse Dermatological Imagery for Fair and Efficient Malignancy Classification
2026-07-14 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors developed a new method called cgDDI to create many realistic skin images that include rare skin conditions and diverse skin tones, which are often missing in existing datasets. Their system can change skin color and lesion location on single images and works well even with very few examples. They tested their approach on two big datasets and improved both accuracy and fairness in detecting skin diseases. The authors also shared over 266,000 synthetic images and their code to help other researchers.
dermatologyimage synthesisskin toneslesion mappingdata augmentationmachine learningclassification accuracydataset fairnesssegmentation maskingsynthetic data
Authors
Héctor Carrión, Narges Norouzi
Abstract
Accurate dermatological diagnosis naturally necessitates equitable performance across diverse populations, yet a systematic lack of expertly annotated images, especially for underrepresented skin tones and rare diseases, impedes progress toward measurably fair methods. We introduce cgDDI (Controllable Generation of Diverse Dermatological Imagery), a hybrid framework that (1) synthesizes realistic healthy skin samples without disturbing other input properties, (2) maps single-sample rare lesions onto novel skin-tones and locations non-parametrically, and (3) allows for efficient parametric generation with as few as 10 training samples. The framework supports both human and automated segmentation masking, enabling scalability to datasets without pre-made lesion masks. 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). 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, alongside leading fairness metrics. Cross-dataset experiments show +13.9% accuracy improvements on unseen F17k data despite minimal disease overlap. We openly release 266k+ synthetic images, code, and generative models to further support fairness research at https://github.com/hectorcarrion/ControllableGenDDI.