AI at the edge - counting cells
SCS developed a deep learning algorithm that determines the number of cells in an image in the microscopy system. The AI was adapted for use "at the edge" - the neural network was optimised so that it can also run on a low-power PC.
-
Problem
For many applications in biology, biotechnology and pharmaceutical technology, the development and growth of cells is monitored. This can vary, for example, due to different substances being tested. Until now, the cells on the corresponding microscopy images have been counted manually in a time-consuming process
-
Solution SCS
SCS created an algorithm based on Deep Learning that automatically determines the number of cells in an image in the microscopy system. The algorithm was specially adapted for use on low-performance computers.
-
Added value
The client can offer scientists another feature that reduces their time spent on research and development by many hours, while maintaining the same quality and requiring no new purchases.
Project insights
The novel zenCell Owl offers customers a lightweight and stackable microscopy system for the incubator. With its help, the growth of cells in 24 different samples can be monitored simultaneously. The monitoring as well as the evaluation of the data can be done comfortably on the PC. Both the degree of coverage and the number of cells can be determined automatically by the software. However, the development of the cell counting algorithm has special framework conditions.
On the one hand, the field of machine learning promises great success in the field of automatic image processing. Progress has also been made in the case of recognition, segmentation and counting of cells. These should be used for the system.
However, the typical PC in a lab is not particularly powerful. Nevertheless, fast and reliable results are expected from the algorithm.
To solve this problem, SCS first trained an algorithm with fast hardware that reliably segments the cells. This then served as a reference for a resource-saving variant that nevertheless delivers comparably good results. In the process, various cuts were gradually made and each was assessed for its effects on the accuracy and speed of the analysis.
This solution has proven to be a reliable approach to such problems.