Share Email Print

Proceedings Paper

Performance Comparison Of Extracted Features In Automated Classification Of Cervical Smears
Author(s): Andrew Seit; Dapeng Tien; Peter Nickolls; Alan Yeung; Jim Tucker
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Automated cervical smear screening is potentially a cheap, rapid method for detecting early cervical cancer and so preventing deaths from this disease. CERVIFIP is a fast scanning machine which classifies microscope images of cervical smears. Although its current false negative error rate is below that of cytotechnicians, its false positive error rate is unacceptably high. New boundary and grey-level texture algorithms are being applied to reduce these rates. In addition a hierarchical rules-based classifier is to be superimposed on the existing statistical classifiers.

Paper Details

Date Published: 27 June 1988
PDF: 8 pages
Proc. SPIE 0914, Medical Imaging II, (27 June 1988); doi: 10.1117/12.968671
Show Author Affiliations
Andrew Seit, University of Sydney (Australia)
Royal North Shore Hospital (Australia)
Dapeng Tien, University of Sydney (Australia)
Peter Nickolls, University of Sydney (Australia)
Alan Yeung, University of Sydney (Australia)
Jim Tucker, Western General Hospital (Scotland)

Published in SPIE Proceedings Vol. 0914:
Medical Imaging II
Samuel J. Dwyer; Roger H. Schneider; Samuel J. Dwyer; Roger H. Schneider; Roger H. Schneider; Samuel J. Dwyer, Editor(s)

© SPIE. Terms of Use
Back to Top