https://github.com/agr78/prlx-gan
Generative modeling and latent projection label denoising approach to create synthetic rim lesions on QSM
https://github.com/agr78/prlx-gan
cornell-university cvpr cvpr2025 deep-learning generative-adversarial-network generative-ai generative-model label-noise label-noise-learning mri multiple-sclerosis paramagnetic-rim-lesion pytorch qsm quantitative-susceptibility-mapping rim-classifier stylegan2-ada synthetic-data weill
Last synced: about 1 month ago
JSON representation
Generative modeling and latent projection label denoising approach to create synthetic rim lesions on QSM
- Host: GitHub
- URL: https://github.com/agr78/prlx-gan
- Owner: agr78
- Created: 2025-04-04T17:22:42.000Z (about 1 year ago)
- Default Branch: main
- Last Pushed: 2025-05-29T10:13:12.000Z (about 1 year ago)
- Last Synced: 2025-05-29T11:10:58.832Z (about 1 year ago)
- Topics: cornell-university, cvpr, cvpr2025, deep-learning, generative-adversarial-network, generative-ai, generative-model, label-noise, label-noise-learning, mri, multiple-sclerosis, paramagnetic-rim-lesion, pytorch, qsm, quantitative-susceptibility-mapping, rim-classifier, stylegan2-ada, synthetic-data, weill
- Language: Shell
- Homepage: https://openreview.net/pdf?id=wFkiqB5spT
- Size: 7.11 MB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# PRLx-GAN
Repository for [_Synthetic Generation and Latent Projection Denoising of Rim Lesions in Multiple Sclerosis_](https://openreview.net/forum?id=wFkiqB5spT&referrer=%5Bthe%20profile%20of%20Alexandra%20Grace%20Roberts%5D(%2Fprofile%3Fid%3D~Alexandra_Grace_Roberts1)) published in [Synthetic Data](https://syndata4cv.github.io/) at [CVPR 2025](https://cvpr.thecvf.com/).
## Summary
Paramagnetic rim lesions (PRLs) are a rare but highly prognostic lesion subtype in multiple sclerosis, visible only on susceptibility ($\chi$) contrasts. [This work](https://huggingface.co/papers/2505.23353) presents a generative framework to:
* Synthesize new rim lesion maps that address class imbalance in training data
* Enable a novel denoising method to resolve radiologist disagreements on noisy labels, "ambiguous rim lesions"
Latent projection iterations to identify the denoised rim lesion from a "noisy" rim lesion.
## Contents
Uncurated synthetic rim lesion [susceptibilities](https://huggingface.co/datasets/agr78/PRLx-GAN-synthetic-rim) can be found in [`png`](https://github.com/agr78/PRLx-GAN/tree/main/png)
Pretrained [weights](https://huggingface.co/agr78/PRLx-GAN) are located in [`net`](https://github.com/agr78/PRLx-GAN/tree/main/net)
## Preliminaries
To download the pretrained weights, ensure [Git Large File Service](https://git-lfs.com/) is installed
```
sudo apt-get install git-lfs
git lfs install
```
The `main.sh` script will skip retraining unless `\your\QSM\data` is replaced by a valid path
## Installation
Clone the repository with
```
git clone https://github.com/agr78/PRLx-GAN.git
```
Navigate to the repository
```
cd PRLx-GAN
```
Run the setup script
```
source ./src/main.sh
```
Wait...then check the generated and denoised outputs
```
cd ./out
```
## Publications
If this code is used, please cite the following:
> [Conference Paper](https://openreview.net/forum?id=wFkiqB5spT¬eId=wFkiqB5spT): A. G. Roberts et al., "Synthetic Generation and Latent Projection Denoising of Rim Lesions in Multiple Sclerosis," Synthetic Data for Computer Vision at CVPR, 2025.
>
## BibTex
```bibtex
@inproceedings{
roberts2025synthetic,
title={Synthetic Generation and Latent Projection Denoising of Rim Lesions in Multiple Sclerosis},
author={Alexandra Grace Roberts and Ha Manh Luu and Mert Sisman and Alexey V. Dimov and Ceren Tozlu and Ilhami Kovanlikaya and Susan Gauthier and Thanh D. Nguyen and Yi Wang},
booktitle={Synthetic Data for Computer Vision Workshop @ CVPR 2025},
year={2025},
url={https://openreview.net/forum?id=wFkiqB5spT}
}
```
## Acknowledgements
This method relies on the [StyleGAN2-ADA](https://github.com/NVlabs/stylegan2-ada-pytorch) architecture developed by [`@tkarras`](https://github.com/tkarras).
## Contact
Please direct questions to [Alexandra G. Roberts](https://github.com/agr78) at agr78@cornell.edu.