19. October 2022

How Cell Counting Algorithms Work

Cell counting underpins much of biomedical research. Yet it is a complex process that requires sophisticated computer technology to yield accurate results in a time efficient manner To do so, scientists rely on artificial intelligence, such as machine learning, to perform advanced model training while imaging and counting cells for medical purposes In order to automate this process, cell counting algorithms must be developed.

Here, we take a deeper look at automated cell counting, with a focus on the different cell counting algorithms that make it possible.

What is the most accurate way to count cells?

There are various ways of counting cells, each with their own strengths and weaknesses [1]. First and foremost is manual cell counting, which is often the most time consuming and error prone method. This approach can utilize a specific microscope slide designed as a counting chamber. However, cells can also be plated and grown on a petri dish, where their colonies can be counted, and their cell count can then be calculated.

Another way of counting cells is indirectly by using a spectrophotometer, which measures light intensity and can give information on how cell´s scatter light. However, this method can only provide an estimate of cell numbers and cannot discriminate between living and dead cells. Automated cell counting, is the most time efficient way of counting cells. This method utilizes flow cytometry, which passes a narrow line of cells in front of a laser beam and detects the amount of light reflected from each cell in order to provide a cell count. However, although sophisticated, flow cytometry is expensive.

The most accurate and economical way to count cells within tissues is image analysis. By employing cell counting algorithms to biomedical imaging, object detection, image classification, and image segmentation can be conducted and improved in real time. Furthermore, cell counting algorithms can automatically calculate and learn from errors to provide the most accurate data possible in a rapid fashion, without manual intervention [1].

Cell counting algorithms developed by TissueGnostics

Automated cell counting within IF or IHC processed samples (tissues, cells, biopsy’s, TMAs, cultured cells) with stable and reliable cell counting algorithms profoundly impacts tissue cytometry workflows and enables more accurate data collection and evaluation. As a recognized provider of tissue cytometers, TissueGnostics has created products and services designed to amplify and make cell counting easier via the cell counting algorithms, including a new deep learning algorithm for nuclei detection, that accompany various software packages.

As a leader in tissue cytometry, TissueGnostics can provide reliable cell counting algorithms as well as more sophisticated analysis workflows including spatial phenotyping and metastructure detection. More information about the wide selection of products available can be found across our website.

If you are interested in adding automated cell counting amplified by cell counting algorithms to your laboratory space, please reach out to a member of the TissueGnostics team as soon as possible.


  1. Wikipedia Contributors (2022). Cell counting. [online] Wikipedia. Available at: https://en.wikipedia.org/wiki/Cell_counting

Are you also interested in Understanding the Tumour Immune Microenvironment?

or in How to Carry Out Complex Characterization of the Tissue Microenvironment?


TissueGnostics GmbH
Taborstraße 10/2/8
1020 Vienna, Austria
+43 1 216 11 90
This email address is being protected from spambots. You need JavaScript enabled to view it.

We use cookies on our website. Some of them are essential for the operation of the site, while others help us to improve this site and the user experience (tracking cookies).
You can decide for yourself whether you want to allow cookies or not. Please note that if you reject them, you may not be able to use all the functionalities of the site.