Encrypted login | home

Program Information

A 4D Lung Phantom for Coupled Registration/Segmentation Evaluation

no image available
D Markel

D Markel1*, I El Naqa1 , I Levesque2 , (1) McGill University, Montreal, QC, (2) Montreal University Health Centre, Montreal, Quebec


TU-F-17A-3 Tuesday 4:30PM - 6:00PM Room: 17A

Purpose: Coupling the processes of segmentation and registration (regmentation) is a recent development that allows improved efficiency and accuracy for both steps and may improve the clinical feasibility of online adaptive radiotherapy. Presented is a multimodality animal tissue model designed specifically to provide a ground truth to simultaneously evaluate segmentation and registration errors during respiratory motion.

Methods: Tumor surrogates were constructed from vacuum sealed hydrated natural sea sponges with catheters used for the injection of PET radiotracer. These contained two compartments allowing for two concentrations of radiotracer mimicking both tumor and background signals. The lungs were inflated to different volumes using an air pump and flow valve and scanned using PET/CT and MRI. Anatomical landmarks were used to evaluate the registration accuracy using an automated bifurcation tracking pipeline for reproducibility. The bifurcation tracking accuracy was assessed using virtual deformations of 2.6 cm, 5.2 cm and 7.8 cm of a CT scan of a corresponding human thorax. Bifurcations were detected in the deformed dataset and compared to known deformation coordinates for 76 points.

Results: The bifurcation tracking accuracy was found to have a mean error of -0.94, 0.79 and -0.57 voxels in the left-right, anterior-posterior and inferior-superior axes using a 1x1x5 mm3 resolution after the CT volume was deformed 7.8 cm. The tumor surrogates provided a segmentation ground truth after being registered to the phantom image.

Conclusion: A swine lung model in conjunction with vacuum sealed sponges and a bifurcation tracking algorithm is presented that is MRI, PET and CT compatible and anatomically and kinetically realistic. Corresponding software for tracking anatomical landmarks within the phantom shows sub-voxel accuracy. Vacuum sealed sponges provide realistic tumor surrogate with a known boundary. A ground truth with minimal uncertainty is thus realized that can be used for comparing the performance of registration and segmentation algorithms.

Contact Email: