Leland Stanford Junior University

Shaohua Sun

Sandy A Napel

Feng Zhuge

A Learning Enhanced Simulated Annealing (LESA) method is provided. Based on a Simulated Annealing (SA) framework, this method adds a Knowledge Base (KB) initialized at the beginning of the search and updated at each iteration, which memorizes a portion of the search history and guides the further search through a KB trial generator. The basic idea of LESA is that its search history is stored in a KB, and a KB trial generator extracts information from it and uses it to generate a new trial. The next move of the search is the weighted sum of the trial generated by the KB trial generator and the trial generated by the usual SA trial generator. The knowledge base is then updated after each search iteration.

Learning enhanced simulated annealing

A nodule registration system useful for tracking lung nodules in computed tomography (CT) scans is presented. The system registers a small sphere centered on a detected nodule in one scan with another scan under a rigid transformation assumption using a fast registration scheme. The registration scheme employs very fast simulated annealing (VFSA) with constraints to maximize a tunable cross-correlation (TCC) coefficient, enabling the system to register, with minimal registration error, all nodules within their maximum diameter. The system achieves an average registration time of 10 seconds or less on a 3.06 GHz computer programmed to implement the present invention.

Growing community of inventors

Jersey City, NJ, United States of America

Shaohua Sun