Pytorch implementation of segmentation based on Ultrasound B-Mode and Doppler images. Accepted at IEEE Transactions on Automation Science and Engineering.
DopUS-Net: Quality-Aware Robotic Ultrasound Imaging Based on Doppler Signal
Zhongliang Jiang*,
Felix Dülmer*,
Nassir Navab
Technical University of Munich (TUM)
*denotes equal contribution
pip install -r requirements.txt
To run the latest version of the DopUs-Network please run:
- train_segmentation.py -c configs/config_dopus_v4.json
To visualize the training process please launch a local visdom server:
- python -m visdom.server