Supervised Pattern Recognition Techniques in Quantitative Diagnostic Ultrasound
作者:
MICHAEL,
INSANA ROBERT,
WAGNER BRIAN,
GARRA REZA,
MOMENAN THOMAS,
期刊:
Journal of Clinical Engineering
(OVID Available online 1988)
卷期:
Volume 13,
issue 6
页码: 447-454
ISSN:0363-8855
年代: 1988
出版商: OVID
关键词: Acoustic Properties;Hotelling Trace;Random Phasor Sum;Receiver Operating Characteristic (ROC) Analysis;Sample Size;Scattering;Statistical Pattern Recognition;Statistical Properties;Tissue Characterization;Ultrasound
数据来源: OVID
摘要:
The methods of statistical pattern recognition are well suited to the problems ofin vivoultrasonic tissue characterization. This paper describes supervised pattern recognition methods for selecting features for tissue classification, calculating decision boundaries within the selected feature space, and evaluating the performance. This paper expands on the authors' previous work (Insana, 1986a) by addressing the considerations of dimensionality and sample size. These are important in classification problems where the underlying probability distributions are not completely known. Examples are given for the detection of diffuse liver disease in the clinical environment.
点击下载:
PDF
(661KB)
返 回