Parameter Optimized, Vertical, Nearest-Neighbor-Vote and Boundary-Based Classification
RFT-203
This invention involves a Computer Aided Detection (CAD) model that is designed to diagnose Pulmonary Embolism (PE) from CT image information data sheet. This high performance, classification system, includes a Nearest Neighbor Vote based classification and a Local Decision Boundary based classification combined with an evolutionary algorithm for parameter optimization and a vertical data structure for efficient processing. The invention was developed as a solution for the ACM KDD Cup Competition 2006, and won task 3 of that competition.
Downloads
File: rft-203.pdf
Inquiries
Jonathan L. Tolstedt
Licensing Associate/Patent Agent
NDSU Research Foundation
Fargo, North Dakota
(701) 231-8173 Work
(701) 231-6661 Fax
http://www.ndsuresearchfoundation.org/