Related Experiment Video
Updated: Jul 30, 2025
Development and Evaluation of 3D-Printed Cardiovascular Phantoms for Interventional Planning and Training
Published on: January 18, 2021
3D vessel extraction using a scale-adaptive hybrid parametric tracker
Qi Sun1,2, Jinzhu Yang3,4, Shuang Ma1,2
1Key Laboratory of Intelligent Computing in Medical Image, Ministry of Education, Northeastern University, Shenyang, Liaoning, China.
Insights
Accurate 3D vessel extraction from computed tomography angiography (CTA) data is challenging. A new scale-adaptive hybrid parametric tracker (SAHPT) effectively extracts vessels by adapting to scale variations and non-uniform intensities, outperforming existing methods.
Area of Science:
- Medical Imaging
- Image Processing
- Computational Anatomy
Background:
- Accurate 3D vessel extraction from computed tomography angiography (CTA) data is crucial for diagnosing vascular diseases.
- Challenges include variations in vessel scale, curvature, intensity distribution, and interference from surrounding tissues like bone and veins.
Purpose of the Study:
- To develop a novel scale-adaptive hybrid parametric tracker (SAHPT) for robust and accurate extraction of arbitrary vessels from CTA data.
- To address the limitations of existing methods in handling diverse vessel structures and imaging conditions.
Main Methods:
- A geometry-intensity parametric model was developed to adapt to scale variations and non-uniform intensity distributions.
- A gradient parametric model utilizing a multiscale symmetric normalized gradient filter was employed to differentiate vessels from interfering tissues.
- A hybrid parametric model combining both geometry-intensity and gradient information was used for local image patch evaluation.
- A multipath spherical sampling strategy was implemented to manage anatomical complexity during extraction.
Main Results:
- The proposed SAHPT demonstrated superior performance in quantitative experiments on synthetic and clinical CTA data.
- The method effectively handled variations in vessel scale, curvature, and intensity.
- It showed improved separation of target vessels from surrounding interfering tissues.
Conclusions:
- The SAHPT is a highly effective method for 3D vessel extraction from CTA data, outperforming traditional and deep learning-based approaches.
- Its adaptive nature makes it suitable for extracting vessels across different body parts and under various imaging conditions.
- This technique holds significant potential for improving the diagnosis of vascular diseases.
Abstract:
3D vessel extraction has great significance in the diagnosis of vascular diseases. However, accurate extraction of vessels from computed tomography angiography (CTA) data is challenging. For one thing, vessels in different body parts have a wide range of scales and large curvatures; for another, the intensity distributions of vessels in different CTA data vary considerably. Besides, surrounding interfering tissue, like bones or veins with similar intensity, also seriously affects vessel extraction. Considering all the above imaging and structural features of vessels, we propose a new scale-adaptive hybrid parametric tracker (SAHPT) to extract arbitrary vessels of different body parts. First, a geometry-intensity parametric model is constructed to calculate the geometry-intensity response. While geometry parameters are calculated to adapt to the variation in scale, intensity parameters can also be estimated to meet non-uniform intensity distributions. Then, a gradient parametric model is proposed to calculate the gradient response based on a multiscale symmetric normalized gradient filter which can effectively separate the target vessel from surrounding interfering tissue. Last, a hybrid parametric model that combines the geometry-intensity and gradient parametric models is constructed to evaluate how well it fits a local image patch. In the extraction process, a multipath spherical sampling strategy is used to solve the problem of anatomical complexity. We have conducted many quantitative experiments using the synthetic and clinical CTA data, asserting its superior performance compared to traditional or deep learning-based baselines.
