Related Experiment Video
Updated: Jun 22, 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
Robust deformable image registration using prior shape information for atlas to patient registration
Lotta M Ellingsen1, Gouthami Chintalapani, Russell H Taylor
1Department of Electrical and Computer Engineering, The Johns Hopkins University, Baltimore, MD 21218, USA. lotta@jhu.edu
Summary
This study introduces a statistical shape atlas for patient-specific surgical planning. The method enhances registration accuracy and robustness in computed tomography scans of the human pelvis.
Area of Science:
- Medical imaging
- Computational anatomy
- Surgical planning
Background:
- Statistical atlases are crucial for personalizing medical information for patient-specific applications like surgical planning.
- Accurate registration of statistical atlases to patient scans is essential for reliable surgical guidance.
Purpose of the Study:
- To develop and evaluate a statistical shape atlas registration method for computed tomography (CT) scans of the human pelvis.
- To improve the stability, robustness, and accuracy of deformable registration for patient-specific applications.
Main Methods:
- A statistical atlas, represented by a point distribution model on a tetrahedral mesh, was registered to pelvic CT scans.
- A volumetric deformable registration method was employed, ensuring mesh topology preservation and incorporating dominant 3D shape modes.
Main Results:
- The incorporation of the statistical shape atlas significantly stabilized the registration process.
- The proposed method demonstrated improved robustness and enhanced registration accuracy compared to standard methods.
Conclusions:
- The developed statistical shape atlas registration method is effective for patient-specific surgical planning.
- This approach offers a promising tool for enhancing the precision and reliability of medical image-guided interventions.
