Comparing Deep Learning Models for Multi-cell Classification in Liquid-based Cervical Cytology Images

TL;DR

This paper introduces a deep learning-based pipeline for classifying cervical cytology images, achieving high accuracy without relying on challenging cell segmentation, and includes a novel graph-based detection method.

Contribution

It presents a new method combining CNN fine-tuning and graph-based cell detection for improved cervical cell classification.

Findings

VGG-19 achieved 95% accuracy on cytology patch data.

The pipeline effectively classifies both single and overlapping cells.

The approach reduces reliance on complex cell segmentation.

Abstract

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.