摘要 |
The invention detects areas of interest at low magnification (18), locating possible abnormal cells or other cells of interest using image processing and statistical pattern recognition techniques. Next, at high magnification (20), the areas identified at low magnification are re-examined. The information from low magnification (18) and high magnification (20) scans is collated (24) and a determination is made about the slide - whether it is normal, abnormal, contains endocervical component, and so forth. The invention also provides a method and apparatus to train object feature and slide feature classifiers. The invention provides an automated cytology system that can process training slides for use in the feed back classifier development environment. The invention also can classify endocervical group of cells.
|
申请人 |
NEOPATH, INC. |
发明人 |
LEE, SHIH-JONG, J.;WILHELM, PAUL, S.;MEYER, MICHAEL, G.;BANNISTER, WENDY, R.;KUAN, CHIH-CHAU;ORTYN, WILLIAM, E.;NELSON, LARRY, A.;FROST, KEITH, L.;HAYENGA, JON, W. |