This is official Pytorch implementation of "Lung Segmentation from Chest X-rays using Variational Data Imputation", Raghavendra Selvan et al. 2020
- Predict lung masks from CXRs
- Train the models described in the paper
- v1.0
- Basic Pytorch dependency
- Tested on Pytorch 1.3, Python 3.6
- Predict using the pretrained model: python predict.py --data DATA_DIR --post --model saved_models/lungVAE.pt
- Download preprocessed CXR data from here
- Train the model from scratch: python train.py --data DATA_DIR
- 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
- Kindly cite our publication if you use any part of the code
@article{raghav2020lungVAE,
title={Lung Segmentation from Chest X-rays using Variational Data Imputation},
author={Raghavendra Selvan et al.},
journal={arXiv preprint arXiv:2020.00000,
year={2020}}}
- For the Kaggle data
- Jaeger S, Karargyris A, Candemir S, Folio L, Siegelman J, Callaghan F, Xue Z, Palaniappan K, Singh RK, Antani S, Thoma G, Wang YX, Lu PX, McDonald CJ. Automatic tuberculosis screening using chest radiographs. IEEE Trans Med Imaging. 2014 Feb;33(2):233-45. doi: 10.1109/TMI.2013.2284099. PMID: 24108713
- Candemir S, Jaeger S, Palaniappan K, Musco JP, Singh RK, Xue Z, Karargyris A, Antani S, Thoma G, McDonald CJ. Lung segmentation in chest radiographs using anatomical atlases with nonrigid registration. IEEE Trans Med Imaging. 2014 Feb;33(2):577-90. doi: 10.1109/TMI.2013.2290491. PMID: 24239990