Nucleus Detection in Cervical Samples Stained With AgNOR

Abstract

ABSTRACTCervical cancer is a public health problem, where the treatment hasa better chance of success if detected early. This paper explores oneway of to analyze argyrophilic nucleolus organizer regions (AgNOR)stained slide using deep learning approaches of object detection fordetecting the different categories of nucleus. Our results show thata balanced dataset between the explored categories was essential,also that a ResNet-50 as backbone of Fast RCNN shows an AP of61.8% and 42.5% to detect nucleus and out of focus nucleus.