The data and demo code for Robust scatterer number density segmentation accepted in TUFFC 2022.
The demo code contains the evaluation of the network for simulation and phantom data. The trained network weights are also provided. In order to use the code, follow these steps:
- download PAN
- Place the folder in the directory of the code
- Replace network.py in PAN with the network.py of the demo code
- Install the dependencies of PAN
- Download the phantom data and place it in the directory
The demo code and the network’s weight can be downloaded by:
The phantom data contains the 100 frames of CIRS phantom imaged by Alpinion machine, simulated Field II data, and 20 grid-based generated samples.
If you use the code please cite the following papers:
Tehrani, Ali KZ, Ivan M. Rosado-Mendez, and Hassan Rivaz. “Robust Scatterer Number Density Segmentation of Ultrasound Images.” IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control (2022).
Li, Hanchao, Pengfei Xiong, Jie An, and Lingxue Wang. “Pyramid attention network for semantic segmentation.” arXiv preprint arXiv:1805.10180 (2018).
Should you have any questions, please contact alikafaei1991@gmail.com