Related Experiment Video
Updated: Jul 12, 2026
06:39
Three-dimensional Location Approach with Silk Thread Guided Laparoscopic Segmentectomy for Liver Tumor
Published on: May 23, 2025
Efficient liver segmentation using a level-set method with optimal detection of the initial liver boundary from
Jeongjin Lee1, Namkug Kim, Ho Lee
1School of Electrical Engineering and Computer Science, Seoul National University, Shinlim 9-dong, Kwanak-gu, Seoul, Republic of Korea.
Computer Methods and Programs in Biomedicine
|August 28, 2007
Summary
This study introduces a fast and accurate method for liver segmentation in CT scans using seeded region growing and level-set propagation. The technique significantly reduces processing time while maintaining high accuracy for liver volume measurement.
Area of Science:
- Medical Imaging
- Computer-Aided Diagnosis
- Image Segmentation
Background:
- Automatic liver segmentation is challenging due to anatomical variations and similar intensity profiles of adjacent tissues.
- Accurate liver segmentation is crucial for clinical applications like liver transplantation planning.
Purpose of the Study:
- To develop a fast and accurate method for liver segmentation from contrast-enhanced computed tomography (CT) images.
- To improve computational efficiency and accuracy compared to existing methods.
Main Methods:
- A two-step seeded region growing (SRG) approach applied to level-set speed images for initial boundary definition.
- 2.5D shape propagation to model adjacent slice boundaries for improved segmentation.
- A rolling ball algorithm for final boundary refinement.
Main Results:
- Achieved an average absolute volume error of 1.25+/-0.70% compared to manual segmentation.
- Demonstrated an average processing time of 3.35 seconds per slice, over 15 times faster than manual methods.
- The method effectively handles variations in liver shape and ambiguous boundaries.
Conclusions:
- The proposed method offers a fast, accurate, and robust solution for automatic liver segmentation in CT images.
- This technique has significant potential for applications requiring precise liver volume quantification, such as pre-surgical planning for liver transplantation.
