Computer recognition of abnormal ectocervical cells. Comparison of the efficacy of contour and textural features

Abstract

The efficacy of contour and texture features for the computer recognition of abnormal ectocervical cells is compared. For this comparison, three cell groups were formed: benign, suspicious and malignant. Nine decision rules were derived. The discrimination attained by features derived from the contours of nucleus and cytoplasm is comparable to that achieved by textural features. A combination of both kinds of features gives best results.