Cervical nuclei classification: Feature engineering versus deep belief network

Abstract

A database of 9405 cervical cells is introduced, which was collected from Pap-smear images: 1791 cells are pathologic cases (two types), the rest are healthy cases (three types). Their cell nuclei are classified using two methods: once with a traditional feature engineering approach using in particular iso-contours; and once with a Deep Belief Network made of Restricted Boltzmann Machines. The Deep Belief Network returns higher accuracy, but not in all classification tasks. The retrieval results show that nuclei information alone can be probably sufficient for a computer-assistive diagnosis of Pap-smear images.