Related Experiment Video
Updated: Dec 28, 2025
08:05
Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia
Published on: December 19, 2020
14.6K
Region growing algorithm combined with morphology and skeleton analysis for segmenting airway tree in CT images
Hui-Hong Duan1, Jing Gong1, Xi-Wen Sun2
1School of Medical Instrument and Food Engineering, University of Shanghai for Science and Technology, Shanghai, China.
Journal of X-Ray Science and Technology
|February 11, 2020
Summary
This study presents a novel automatic method for segmenting the pulmonary airway tree in CT scans. The approach accurately identifies airway branches, crucial for diagnosing lung diseases.
Area of Science:
- Medical Imaging
- Radiology
- Computer-Aided Diagnosis
Background:
- Automatic segmentation of the pulmonary airway tree is critical for computer-aided detection and diagnosis of lung diseases.
- Computed tomography (CT) chest imaging is a primary modality for visualizing lung structures.
Purpose of the Study:
- To introduce and evaluate a novel automatic method for segmenting the pulmonary airway tree from CT chest images.
- To improve the accuracy and efficiency of airway tree segmentation for clinical applications.
Main Methods:
- A two-pass region growing algorithm combined with gray-scale morphological reconstruction and leakage elimination.
- The method involves initial rough airway tree generation, followed by distal airway detection and refinement through leakage elimination.
Main Results:
- The proposed method achieved accurate segmentation of the pulmonary airway tree in 45 clinical CT lung image cases.
- It detected up to 12 generations of bronchi, extracted an average of 148.85 branches with a low false positive rate of 0.75%.
Conclusions:
- The developed method demonstrates high accuracy for pulmonary airway tree segmentation.
- Separating leakage detection enhances the method's feasibility, ensuring a high branch detection rate with minimal leakage.
