Related Experiment Video
Updated: Jun 13, 2026
06:18
Pioneering Patient-Specific Approaches for Precision Surgery Using Imaging and Virtual Reality
Published on: April 5, 2024
A 3D global-to-local deformable mesh model based registration and anatomy-constrained segmentation method for image
Jinghao Zhou1, Sung Kim, Salma Jabbour
1Department of Radiation Oncology, UMDNJ-Robert Wood Johnson Medical School, The Cancer Institute of New Jersey, New Brunswick, New Jersey 08903, USA.
Medical Physics
|April 14, 2010
Summary
A new, fast method accurately segments and registers prostate cancer volumes for image-guided radiotherapy. This approach improves computational efficiency, potentially enabling real-time adaptive radiotherapy.
Area of Science:
- Medical Physics
- Radiotherapy Technology
- Image Processing
Background:
- Precise prostate segmentation and registration are crucial for adaptive radiotherapy and conformal dose delivery in external beam radiation treatment.
- Current methods may face computational time constraints in clinical settings.
Purpose of the Study:
- To develop a novel, fast, and accurate segmentation and registration method for prostate cancer treatment.
- To enhance computational efficiency for image-guided radiotherapy within clinical time limits.
Main Methods:
- A global-to-local deformable mesh model registration framework was employed.
- An automatic anatomy-constrained robust active shape model (ACRASM) algorithm was used for segmentation.
- The method captured soft tissue transformations between planning CT (pCT) and cone-beam CT (CBCT) images.
Main Results:
- ACRASM segmentation showed improved accuracy over the original active shape model (ASM), with mean distances from -0.85 to 0.84 mm versus -1.44 to 1.17 mm.
- Registration achieved a mean overlap ratio of 85.2% to 95% for prostate volumes.
- Segmentation and registration times were significantly reduced, with ACRASM segmentation under 1 minute.
Conclusions:
- A novel, rapid segmentation and deformable registration method was developed for prostate cancer radiotherapy.
- The method enhances computational efficiency, offering a foundation for real-time adaptive radiotherapy.
- This technique improves precision in capturing image transformations for improved treatment delivery.
