Related Experiment Video
Updated: Jun 10, 2026
07:57
Positron Emission Tomography-based Dose Painting Radiation Therapy in a Glioblastoma Rat Model using the Small Animal Radiation Research Platform
Published on: March 24, 2022
A geodesic deformable model for automatic segmentation of image sequences applied to radiation therapy
1E.T.S.Ingenieros Industriales, Universidad de Castilla-La Mancha, Avda. Camilo José Cela, 3, 13071, Ciudad Real, Spain. gloria.bueno@uclm.es
Summary
A new deformable segmentation method accurately tracks organ motion in image-guided radiotherapy, improving treatment planning and evaluation for various regions without markers.
Area of Science:
- Medical Imaging
- Radiotherapy Physics
- Computational Anatomy
Background:
- Organ motion significantly impacts the accuracy of image-guided fractionated radiotherapy.
- Accurate accounting for inter- and intra-fraction organ motion is crucial for effective radiotherapy planning and evaluation.
Purpose of the Study:
- To develop and evaluate a deformable segmentation and registration method for addressing organ motion in radiotherapy.
- To enable precise inter- and intra-fraction organ motion planning and evaluation.
Main Methods:
- Developed energy-minimizing active models for tracking organs delineated by regions of interest (ROIs).
- Utilized a heat flow model for surface deformation to match ROI contours based on geometrical properties.
- Tested the deformable segmentation model using Shepp-Logan head CT simulations and quantitative metrics (ROC, Jaccard, Dice, Hausdorff).
Main Results:
- Experimental evaluation compared automated and manual segmentation for cardiac, thoracic, and pelvic regions.
- Achieved high quantitative validation metrics: 93.3% sensitivity, 99.2% specificity, 90.79% Jaccard index, 95.15% Dice coefficient, and 0.96 mm Hausdorff distance.
- Demonstrated the method's effectiveness on 2D CT data.
Conclusions:
- A model-based deformable segmentation method was successfully developed and tested for image-guided radiotherapy.
- The developed method is efficient, robust, and accurate for 2D CT data, even without markers.
- This approach enhances the precision of radiotherapy treatment planning and evaluation by accounting for organ motion.
