Related Experiment Video
Updated: May 11, 2026
14:08
Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
Published on: April 13, 2013
Segmentation of ct liver images using phase based level set method - biomed 2013
1Indian Institute of Technology Madras.
Biomedical Sciences Instrumentation
|May 21, 2013
Summary
This study introduces a novel phase-based level set method for accurate liver segmentation in CT scans. The technique improves accuracy and avoids contour leakage, offering clinical relevance for detecting liver abnormalities.
Area of Science:
- Medical Imaging
- Image Processing
- Computational Anatomy
Background:
- Accurate liver segmentation in abdominal CT images is challenging due to similar organ intensities.
- Traditional intensity-based methods often fail to segment the liver precisely.
Purpose of the Study:
- To develop and evaluate a phase-based level set method for robust liver segmentation from CT images.
- To improve the accuracy and reliability of liver segmentation in medical imaging.
Main Methods:
- Utilized phase-based distance regularized level set segmentation on CT images from open-source and hospital databases.
- Employed a distance regularization term for contour stability and minimized the energy function.
- Applied phase congruency measure as an edge detector for level set evolution.
Main Results:
- The phase-based method demonstrated superior segmentation accuracy compared to traditional methods, achieving high similarity indices.
- Robust convergence at edges was achieved, effectively preventing contour leakage.
- Phase congruency information proved effective in distinguishing edges and lines within the CT images.
Conclusions:
- The proposed phase-based level set segmentation technique offers a clinically relevant and accurate approach for liver segmentation in CT scans.
- This method enhances the detection and characterization of liver abnormalities such as hepatoma, cysts, and tumors.
