Difference between revisions of "Projects:UtahTumorSimulation"
(Created page with ' Back to Utah 2 Algorithms __NOTOC__ = Tumor Simulation for Validating Change Tracking Applications = Determining extent of pathology as it changes over tim…') |
|||
| Line 6: | Line 6: | ||
Determining extent of pathology as it changes over time is an important clinical task. However, there is a lack of a reliable, objective ground truth for evaluating automatic tracking methods. We have developed a simulation tool that can generate MR images with known tumor and edema. This tool provides test MR image data along with the underlying ground truth, that can be used for performing objective, repeatable assessment of the performance of segmentation or change tracking systems. | Determining extent of pathology as it changes over time is an important clinical task. However, there is a lack of a reliable, objective ground truth for evaluating automatic tracking methods. We have developed a simulation tool that can generate MR images with known tumor and edema. This tool provides test MR image data along with the underlying ground truth, that can be used for performing objective, repeatable assessment of the performance of segmentation or change tracking systems. | ||
| − | We are exploring the use of the simulated datasets for validating the meningioma change tracking project at BWH. | + | We are exploring the use of the simulated datasets for validating the meningioma change tracking project at BWH. The simulations are performed using a modified version of our simulator that was developed previously. We provide extensions for the dura modelling and more exposure of internal modeling parameters. A summary of our simulation scheme is shown in the figure below. |
| + | |||
| + | [[File:UtahTumorSimulationSummary.png]] | ||
Project Activities: | Project Activities: | ||
Revision as of 19:32, 7 October 2009
Home < Projects:UtahTumorSimulationBack to Utah 2 Algorithms
Tumor Simulation for Validating Change Tracking Applications
Determining extent of pathology as it changes over time is an important clinical task. However, there is a lack of a reliable, objective ground truth for evaluating automatic tracking methods. We have developed a simulation tool that can generate MR images with known tumor and edema. This tool provides test MR image data along with the underlying ground truth, that can be used for performing objective, repeatable assessment of the performance of segmentation or change tracking systems.
We are exploring the use of the simulated datasets for validating the meningioma change tracking project at BWH. The simulations are performed using a modified version of our simulator that was developed previously. We provide extensions for the dura modelling and more exposure of internal modeling parameters. A summary of our simulation scheme is shown in the figure below.
Project Activities: 2009 Project Week Followup Project
Key Investigators
- Utah Algorithms: Marcel Prastawa, Guido Gerig
- Brigham and Women's Hospital: Andriy Fedorov, Ron Kikinis
