lungVAE
This is the official Pytorch implementation of "Lung Segmentation from Chest X-rays using Variational Data Imputation", Raghavendra Selvan et al. 2020
How do I get set up?
- Basic Pytorch dependency
- Tested on Pytorch 1.3, Python 3.6
- Predict using the pretrained model:
python predict.py --data DATA_DIR --model saved_models/lungVAE.pt - Download preprocessed CXR data from here
- Train the model from scratch:
python train.py --data DATA_DIR
Using preprocessed diffused masks
- For speed up, the diffused noise masks are precomputed
- 200 sample masks are provided in this file
- Check the dataloader to create more or to compute the masks on the fly
- It is recommended to use precomputed masks
Usage guidelines
- Kindly cite our publication if you use any part of the code
@misc{raghav2020lungVAE,
title={Lung Segmentation from Chest X-rays using Variational Data Imputation},
author={Raghavendra Selvan and Erik B. Dam and Nicki Skafte Detlefsen and Sofus Rischel and Kaining Sheng and Mads Nielsen and Akshay Pai},
howpublished={ICML Workshop on The Art of Learning with Missing Values},
month={July},
note={arXiv preprint arXiv:2020.2005.10052},
year={2020}}
