generative_chestxray icon indicating copy to clipboard operation
generative_chestxray copied to clipboard

Repository to train Latent Diffusion Models on Chest X-ray data (MIMIC-CXR) using MONAI Generative Models

Results 8 generative_chestxray issues
Sort by recently updated
recently updated
newest added

Hi, Thank you for the amazing work! I tried training a model using your code with the DDPM scheduler, which works fine during the interference/sampling as well. However, I am...

Hello, since the MIMIC-CXR dataset is too large to download, I only need the test set. Which compressed folder is the test set of MIMIC-CXR?

Hi, I'm trying to train with my own mimic dataset. I want to run this python file: generative_chestxray/src/python/preprocessing/create_sentences_files.py. To do that, we need to have the mimic_cxr_sectioned.csv generated by create_sectioned_reports.py....

Are there any pre-trained model checkpoints that can be used?

Improve the Autoencoder KL model using the Stable Diffusion approach for the adversarial component and using a better learning rate scheduling.

Include in the training set more Chest X-ray datasets.

Improve the elements involved for the text encoding part. For example, by using a model specific for the medical imaging domain.

Improve Diffusion Model by using a better learning rate scheduler (including warm-up period) and using exponential moving average.