cgDDI: Controllable Generation of Diverse Dermatological Imagery - Angioma

This repository contains the textual inversion weights (<angioma-class>) for learning the "angioma" disease concept on top of stabilityai/stable-diffusion-2-1-base.

This model is part of the work presented in the paper Controllable Generation of Diverse Dermatological Imagery for Fair and Efficient Malignancy Classification (MICCAI 2026).

• GitHub Repository: ControllableGenDDI
• Dataset: hcarrion/ControllableGenDDI

About cgDDI

cgDDI (Controllable Generation of Diverse Dermatological Imagery) is a hybrid framework designed to address the lack of expertly annotated dermatological images, especially for underrepresented skin tones and rare diseases. It allows for the controllable generation of diverse and realistic skin images to improve both the accuracy and fairness of malignancy classification.

Citation

@inproceedings{carrion2026cgddi,
  title     = {Controllable Generation of Diverse Dermatological Imagery for Fair and Efficient Malignancy Classification},
  author    = {Carri{\'o}n, H{\'e}ctor and Norouzi, Narges},
  booktitle = {Medical Image Computing and Computer-Assisted Intervention (MICCAI)},
  year      = {2026},
  publisher = {Springer},
  series    = {Lecture Notes in Computer Science}
}