hcarrion/spindle_cell_nevus_of_Reed

cgDDI: Spindle Cell Nevus of Reed Concept (Textual Inversion)

This repository contains the textual inversion learned concept <spindle_cell_nevus_of_Reed-class> for the dermatological condition Spindle Cell Nevus of Reed. It is trained on top of stabilityai/stable-diffusion-2-1-base as part of the cgDDI framework.

This model was introduced in the paper: Controllable Generation of Diverse Dermatological Imagery for Fair and Efficient Malignancy Classification (MICCAI 2026).

About the Project

cgDDI (Controllable Generation of Diverse Dermatological Imagery) is a hybrid framework designed to synthesize realistic, diverse, and fair dermatological datasets to improve malignancy classification.

For more details about training, LoRA checkpoints, and datasets, please visit:

• GitHub Repository: ControllableGenDDI
• Dataset: hcarrion/ControllableGenDDI

Usage

To use this concept and sample disease-conditioned images, you can refer to the official semantic_sampling.ipynb notebook in the GitHub repository.

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}
}