Deep Learning for Computational Cytology: A Survey

TL;DR

This survey reviews over 120 studies on deep learning techniques applied to computational cytology, highlighting methods, datasets, applications, challenges, and future research directions in cancer screening.

Contribution

It provides a comprehensive overview of DL-based cytology image analysis, systematically categorizing methods, datasets, and applications, and discusses future challenges and research opportunities.

Findings

Deep learning methods have significantly advanced cytology image analysis.

Various datasets and evaluation metrics are used in the field.

DL applications include classification, detection, and segmentation tasks.

Abstract

Computational cytology is a critical, rapid-developing, yet challenging topic in the field of medical image computing which analyzes the digitized cytology image by computer-aided technologies for cancer screening. Recently, an increasing number of deep learning (DL) algorithms have made significant progress in medical image analysis, leading to the boosting publications of cytological studies. To investigate the advanced methods and comprehensive applications, we survey more than 120 publications of DL-based cytology image analysis in this article. We first introduce various deep learning methods, including fully supervised, weakly supervised, unsupervised, and transfer learning. Then, we systematically summarize the public datasets, evaluation metrics, versatile cytology image analysis applications including classification, detection, segmentation, and other related tasks. Finally, we discuss current challenges and potential research directions of computational cytology.