Improved model for specimen classification based on single‐cell classifiers

C. Cox, L. L. Wheeless, J. E. Reeder, R. D. Robinson, T. K. Berkan

Research output: Contribution to journalArticlepeer-review

Abstract

We consider probabilistic models for specimen classification procedures based on systems which classify individual cells as normal or abnormal. The models which we consider generalize those discussed previously by Castleman and White (Anal. Quant. Cytol. 2:117–122, 1980; Cytometry 2:155–158, 1981) and by Timmers and Gelsema (Cytometry 6:22–25, 1985). In particular, they include the biologically plausible possibility that the specimen contains cells which are intermediate between the extremes of normal and abnormal. We find that if these additional cells occur differentially in normal and abnormal specimens, then specimen classification can become substantially more efficient when the cell classifier has different error rates for these cells.

Original languageEnglish (US)
Pages (from-to)267-272
Number of pages6
JournalCytometry
Volume8
Issue number3
DOIs
StatePublished - May 1987

Keywords

  • Classification models
  • cell classification
  • cervical cytology

ASJC Scopus subject areas

  • Pathology and Forensic Medicine
  • Biophysics
  • Hematology
  • Endocrinology
  • Cell Biology

Fingerprint Dive into the research topics of 'Improved model for specimen classification based on single‐cell classifiers'. Together they form a unique fingerprint.

Cite this