event-icon
Description

Liquid-based cytology (LBC) is a reliable automated technique for the screening of Papanicolaou (Pap) smear data. It is an effective technique for collecting a majority of the cervical cells and aiding cytopathologists in locating abnormal cells. Most methods published in the research literature rely on accurate cell segmentation as a prior, which remains challenging due to a variety of factors, e.g., stain consistency, presence of clustered cells, etc. We propose a method for automatic classification of cervical slide images through generation of labeled cervical patch data and extracting deep hierarchical features by fine-tuning convolution neural networks, as well as a novel graph-based cell detection approach for cellular level evaluation. The results show that the proposed pipeline can classify images of both single cell and overlapping cells. The VGG-19 model is found to be the best at classifying the cervical cytology patch data with 95 % accuracy under precision-recall curve.

Learning Objective: The article guides the learner to better understand the challenges applying deep-learning to real-world cytology data where number of cases are significantly smaller than controls and necessary steps to aid physicians to locate the abnormality.

Authors:

Sudhir Sornapudi (Presenter)
Missouri University of Science and Technology

Gregory Brown, U.S. National Library of Medicine
Zhiyun Xue, U.S. National Library of Medicine
Rodney Long, U.S. National Library of Medicine
Lisa Allen, Becton Dickinson and Company
Sameer Antani, U.S. National Library of Medicine

Presentation Materials:

Tags