Deep learning for computational cytology: A survey

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

Automated summary

Computational cytology is a critical and rapidly developing topic in medical image computing. Deep learning approaches have achieved significant advancements in cytology image analysis, leading to a substantial increase in publications. This article surveys over 120 publications on deep learning-based cytology image analysis, investigating advanced methods and comprehensive applications. It introduces different deep learning schemes, summarizes public datasets, evaluation metrics, and versatile applications, and discusses current challenges and potential research directions in computational cytology.