Parameter Optimized, Vertical, Nearest-Neighbor-Vote and Boundary-Based Classification (RFT-203)

Generate a PDF of this technology.

Generate PDF

Invention Summary

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.

Status

Licensed Exclusively in all Fields of Use and in all Territories

Contact

Henry Nowak, Technology Manager
hnowak@ndsurf.org
(701)231-8173

Inquire about this technology >