1 / 13

Importance of Reference Image Databases to Evaluate the Performance of Clinical Decision Tools.

Presentation Outline. Define role of Reference Image Data BasesExample:

galahad
Download Presentation

Importance of Reference Image Databases to Evaluate the Performance of Clinical Decision Tools.

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


    1. Importance of Reference Image Databases to Evaluate the Performance of Clinical Decision Tools. Laurence (Larry) P. Clarke PhD NCI Cancer Imaging Program NIBIB: Detail NIST: Guest Scientist NIST Workshop Sept April 23th

    2. Presentation Outline Define role of Reference Image Data Bases Example: “RIDER” Project Explain the motivation and planned contents Introduce current project participants Outline the informatics infrastructure and need for interoperability standards Review the levels of complexity in the development and implementation of standards for “clinical decision tools” Criteria for success: Engagement of stake holders

    3. RIDER Overall Goals RIDER is a web accessible public resource of validated image data for different organ systems-modalities employed to: Reduce the physical sources of uncertainty for data collection and analysis methods across different imaging platforms. Permit optimization of these methods and their standardized assessment by benchmarking tools performance. Accelerate FDA approval and CMS reimbursement Improve methods for planned clinical drug trials. Design a scalable resource as a trans-agency initiative: Ensure data interoperability, image annotation and markup standards using open source tools. Develop an imaging workspace that includes an array of open source validation and statistical tools.

    4. Research Plan and Organizational Structure Nature of the Data: Data Sources: Collections from on going NCI (ACRIN, CALGB, CTEP) and privately funded PhRMA trails. Data Types: Initially CT and FDG PET CT for lung cancer, and DCE MRI, MRS and Optical for other organ systems, including phantom-other calibration data. Data Format: Meet caBIG data interoperability and scalability requirements, including image annotation and mark up. Data Base Size: Sufficient to differentiate the performance of different analysis tools (of the order of 1000 serial cases). Organizational Oversight: Inter agency (NCI, NIBIB, FDA, NIST): Collaboration with academia, cancer centers and industry. Consensus on Validation Methods: For example: Data base content, mark up, and functionality requirements to train and test change analysis methods, calibration data analysis. Leveraging: Intent is to seek a public private partnership with both the imaging industries and PhRMA.

    5.

More Related