作者: F.M. Greene , K. Beach , D.E. Strandness , G. Fell , D.J. Phillips
DOI: 10.1016/0301-5629(82)90095-3
关键词:
摘要: A minicomputer based system has been developed for studying carotid artery blood flow data obtained a combined B-mode, pulsed Doppler ultrasound scanner. The goals of this work are to devise and improve techniques estimating the extent atherosclerosis at bifurcation. Features automatically extracted from spectrum analyzed data. Five statistical pattern recognition algorithms compared, with cross validation being used estimate classification accuracy. collection protocol devised in which four sites studied along each arterial system. Classification unknowns is done using hierarchy three decisions.