Related Experiment Video
Updated: Jun 20, 2026
08:12
A Volumetric Method for Quantification of Cerebral Vasospasm in a Murine Model of Subarachnoid Hemorrhage
Published on: July 28, 2018
Liver vessels segmentation using a hybrid geometrical moments/graph cuts method
Simon Esneault1, Cyril Lafon, Jean-Louis Dillenseger
1Institut National de la Santé et de la Recherche Médicale (INSERM) U642, F-35000 Rennes, France. simon.esneault@univ-rennes1.fr
IEEE Transactions on Bio-Medical Engineering
|September 29, 2009
Summary
This study presents an automated method for segmenting liver vessels in CT scans using 3D geometrical moments and graph cuts. This technique aids in precise surgical planning for procedures like high-intensity focused ultrasound.
Area of Science:
- Medical Imaging
- Computer-Aided Surgery
- Image Segmentation
Background:
- Accurate liver vessel segmentation is crucial for surgical planning.
- Existing methods may lack automation or precision.
- Computerized tomography (CT) scans are standard for preoperative imaging.
Purpose of the Study:
- To develop a fast and fully automatic method for liver vessel segmentation.
- To integrate a 3D geometrical moment-based detector into energy minimization frameworks.
- To enhance the accuracy of preoperative imaging for surgical interventions.
Main Methods:
- Utilizing a 3D geometrical moment-based detector for cylindrical shapes.
- Implementing the minimum-cut/maximum-flow energy minimization framework (graph cuts).
- Introducing a novel data term as a constraint within the graph cuts algorithm for automation.
Main Results:
- The proposed method achieves fast and fully automatic liver vessel segmentation.
- Evaluation on a synthetic dataset shows competitive performance compared to other methods.
- Demonstrated relevance for planning percutaneous high-intensity focused ultrasound (HIFU) surgery.
Conclusions:
- The developed method offers an effective and automated solution for liver vessel segmentation.
- This technique can significantly improve the accuracy of preoperative planning for complex surgeries.
- The integration of geometrical moments with graph cuts provides a robust approach for medical image analysis.
