vgonzalezd / ultrasound-confidence-maps-using-random-walks

Python implementation of Ultrasound Confidence Maps using Random Walks for confidence map estimation in ultrasound imaging, based on the paper by Karamalis et al.

Ultrasound Confidence Maps using Random Walks

This repository contains a Python implementation of the method described in the paper:

"Ultrasound confidence maps using random walks" by Athanasios Karamalis, Wolfgang Wein, Tassilo Klein and Nassir Navab.

The paper can be found at: https://www.sciencedirect.com/science/article/pii/S1361841512000977

This Python implementation was developed by Vahit Buğra Yeşilkaynak at Technische Universität München.

The original MATLAB code was developed by Athanasios Karamalis at the Chair for Computer Aided Medical Procedures (CAMP), Technische Universität München.

Getting Started

This implementation provides a working example with test images for confidence map estimation using random walks in ultrasound imaging.

Prerequisites

To use this code, make sure you have Python 3.x installed. Additionally, you may need to install the following Python packages:

• numpy
• scipy
• matplotlib

Running the Example

To run the example script, navigate to the main directory and execute:

python main.py

This will run the example with the provided test images and display the generated confidence maps.

License

This code is provided for research and non-commercial purposes only. Please see the original LICENSE file for further details on the terms and conditions of use.

Reference

If you use this code in your research, please cite the original paper:

A. Karamalis, W. Wein, T. Klein, N. Navab: Ultrasound Confidence Maps using Random Walks, Medical Image Analysis, 16, 6, 1101 - 1112, 2012
DOI: http://dx.doi.org/10.1016/j.media.2012.07.005

Contact

For questions and feedback about this implementation, please contact Vahit Buğra Yeşilkaynak at [email protected].

For questions and feedback related to the original MATLAB code, please contact Athanasios Karamalis at [email protected].