Related Experiment Video
Updated: Jul 3, 2026
10:39
A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment
Published on: May 24, 2022
Multiple-phase segmentation approach for blood vessel extraction on cervical MRA image sequence.
1Division of Information and Communication Engineering, Sunchon National University, Sunchon, Jeonnam 540-742, Republic of Korea. dykim@sunchon.ac.kr
Magnetic Resonance Imaging
|August 9, 2008
Summary
A new multiple-phase algorithm accurately segments carotid arteries (CA) by adaptively adjusting image criteria and using connectivity between slices. This method improves upon single-phase approaches for medical image analysis.
Area of Science:
- Medical Imaging
- Computer Vision
- Image Analysis
Background:
- Accurate region segmentation is crucial for medical image analysis and radiological tasks.
- Automating the delineation of anatomical structures like the carotid artery (CA) is essential for clinical applications.
Purpose of the Study:
- To develop and evaluate a novel multiple-phase segmentation algorithm for automated carotid artery (CA) extraction.
- To improve the accuracy and efficiency of CA segmentation in medical imaging.
Main Methods:
- Automatic seed selection based on a priori knowledge of CA anatomy.
- Adaptive adjustment of average intensity values as a homogeneity criterion for slice-wise segmentation.
- Utilizing stack features and duplicated stacks for efficient branch detection and connectivity preservation.
Main Results:
- The proposed multiple-phase algorithm demonstrated superior segmentation results compared to single-phase and combined methods.
- The algorithm maintained seed position within the CA area across consecutive slices, ensuring connectivity.
- Branch detection was automated and optimized using stack features.
Conclusions:
- The developed multiple-phase segmentation algorithm offers a robust and accurate method for carotid artery extraction.
- This approach shows potential for segmenting other tree-like organ structures, such as renal arteries, coronary arteries, and airway trees, across various medical imaging modalities.
