This repo provides the trained model and testing code for catheter detection as described in our paper.

Note that due to regulations on the patient data, we can not share the test dataset used in the paper. The test image provided in the dataset folder here was obtained by google image search with keyword "neonatal chest xray". The original image can be found here.

• Linux or macOS
• Python 3.6
• CPU or NVIDIA GPU + CUDA CuDNN

• Install PyTorch and dependencies from http://pytorch.org
• Install Torch vision from the source.

git clone https://github.com/pytorch/vision
cd vision
python setup.py install

• Install python libraries visdom and dominate.

pip install visdom
pip install dominate

• Clone this repo:

git clone https://github.com/xinario/catheter_detection
cd catheter_detection

• Download the pretrained detection model from here (21M) and put it into the "checkpoints/catheter_detect" folder

• Run the test script

python test.py --dataroot ./datasets/pediatric_internet/ --name catheter_detect  --phase test  --loadSize 480 --sourceoftest external

Now you can view the result by open the html file: results/catheter_detect/test_latest/index.html

If you find it useful and are using the code/model provided here in a publication, please cite our paper.

pix2pix, ConvLSTM_pytorch