Cytology deep learning

These findings demonstrated our deep learning ROI detection model was able to automatically select tiles from a bone marrow WSI appropriate for bone marrow cytology with high accuracy and precision, providing the foundation for an automated end-to-end bone marrow cytology model and abrogating the need for manual ROI identification.

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.

Deep learning (DL) is a component or subset of artificial intelligence.
DL has contributed significant change in feature extraction and image classification.
Various algorithmic models are used in DL such as:

1. a convolutional neural network (CNN)
2. recurrent neural network
3. restricted Boltzmann machine
4. deep belief network and autoencoders

DL may be useful for tumour diagnosis, classification of the tumour and grading of the tumour in cytology.
In this brief review, the basic concept of the DL and CNN are described.
The application, prospects and challenges of the DL in the cytology are also discussed.