Related Experiment Video
Updated: May 14, 2026
02:09
Multi-modal Pulmonary Imaging: Using Complementary Information from CT and Hyperpolarized 129Xe MRI to Evaluate Lung Structure-Function
Published on: April 12, 2024
Interactive segmentation of airways from chest X-ray images using active shape models.
Teshwaree Tezoo1, Tania S Douglas
1MRC/UCT Medical Imaging Research Unit, University of Cape Town, Observatory 7925, South Africa.
Summary
This study introduces an interactive airway segmentation method for chest X-rays, crucial for classifying airway shapes and aiding in pediatric tuberculosis detection.
Area of Science:
- Medical Imaging
- Computer-Aided Diagnosis
- Pediatric Radiology
Background:
- Airway shape classification in chest X-rays shows potential for detecting pediatric tuberculosis-associated lymphadenopathy.
- Accurate airway segmentation is a prerequisite for robust airway shape analysis.
Purpose of the Study:
- To present an interactive airway segmentation approach for chest X-ray images.
- To facilitate the development of an airway shape classification algorithm for computer-aided detection.
Main Methods:
- A local normalization filter was used for airway enhancement.
- Active shape models (ASMs) with affine transformation were employed for segmentation.
- Two ASM variations were developed: edge-based and edge-and-rib-based.
Main Results:
- The developed method enables interactive airway segmentation from chest X-ray images.
- The accuracy of the segmentation was evaluated using the Hausdorff distance against manual segmentations.
Conclusions:
- The proposed interactive airway segmentation technique is a viable step towards computer-aided detection of pediatric tuberculosis.
- Further development of airway shape classification algorithms can leverage this segmentation approach.
