Abstract | ||
---|---|---|
An important step in the diagnosis of a cervical cytology specimen is estimating the proportions of the various cell types present. This is usually done with a cell classifier, the error rates of which can be expressed as a confusion matrix. We show how to use the confusion matrix to obtain an unbiased estimate of the desired proportions. We show that the mean square error of this estimate depends on a “befuddlement matrix” derived from the confusion matrix, and how this, in turn, leads to a figure of merit for cell classifiers. Finally, we work out the two-class problem in detail and present examples to illustrate the theory. |
Year | DOI | Venue |
---|---|---|
1981 | 10.1016/0031-3203(81)90092-3 | Pattern Recognition |
Keywords | Field | DocType |
Classifier,Error rates,ROC curve,Confusion matrix,Sampling error,Mean square error,Proportion estimation | Confusion matrix,Pattern recognition,Sampling error,Matrix (mathematics),Mean squared error,Figure of merit,Sampling (statistics),Artificial intelligence,Classifier (linguistics),Mathematics | Journal |
Volume | Issue | ISSN |
13 | 5 | 0031-3203 |
Citations | PageRank | References |
2 | 0.55 | 0 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Benjamin S. White | 1 | 6 | 1.84 |
Kenneth R. Castleman | 2 | 91 | 12.80 |