Related Experiment Video
Updated: May 5, 2026
13:35
Segmentation and Linear Measurement for Body Composition Analysis using Slice-O-Matic and Horos
Published on: March 21, 2021
11.0K
Texture analysis improves level set segmentation of the anterior abdominal wall
Zhoubing Xu1, Wade M Allen, Rebeccah B Baucom
1Electrical Engineering, Vanderbilt University, Nashville, Tennessee 37235.
Medical Physics
|December 11, 2013
Summary
This study introduces a novel image segmentation method for abdominal walls, improving ventral hernia repair by providing quantitative geometric measurements from CT scans. This technique enhances surgical planning and aims to reduce hernia recurrence rates.
Area of Science:
- Medical Imaging
- Computational Anatomy
- Surgical Planning
Background:
- Ventral hernia repair has high recurrence rates (24-43%) despite mesh use.
- Current computed tomography (CT) guided interventions rely on qualitative clinical judgment.
- Quantitative image-processing metrics are lacking for abdominal wall assessment.
Purpose of the Study:
- To develop and validate image segmentation methods for capturing abdominal wall 3D structure.
- To enable quantitative measurement of geometric properties for hernia and surrounding tissues.
- To provide a foundation for optimizing ventral hernia intervention and improving patient outcomes.
Main Methods:
- Utilized 20 postoperative patient CT scans for geometric classification of the abdominal wall.
- Employed texture analysis with Gabor filters for feature extraction.
- Applied fuzzy c-means clustering and level set evolution guided by texture analysis.
Main Results:
- Achieved mean surface errors < 2 mm for outer abdominal wall segmentation.
- 91% of the outer surface segmentation was within 5 mm of manual tracings.
- Texture-based methods significantly outperformed non-texture methods, reducing errors.
Conclusions:
- The proposed approach establishes a baseline for abdominal wall characterization in ventral hernia care.
- Inherent CT scan texture patterns aid tissue classification.
- Texture analysis enhances level set segmentation accuracy in the abdominal region.
