Researchers from the University of Kent have developed a computer algorithm that can identify differences in cancer cell lines based on microscopic images. The cell lines are isolated and grown as cell cultures in laboratories for study and developing anti-cancer drugs. However, many cell lines can be misidentified after being swapped or contaminated with others, meaning many researchers may work with incorrect cells. This AI breakthrough has the potential to provide an easy-to-use tool that enables the rapid identification of all cell lines in a laboratory.
The research was lead by Dr. Chee (Jim) Ang (SoC) and Dr. Gianluca Marcelli (EDA) with leading experts in cancer cell lines Professor Martin Michaelis and Dr. Mark Wass (School of Biosciences).
"The results also show that the computer models can allocate exact criteria used to identify cell lines correctly," said Dr Ang, Senior Lecturer in Multimedia/Digital Systems, "meaning that the potential for future researchers to be trained in identifying cells accurately may be greatly enhanced too."
Researchers at the Kent School of Engineering and Digital Arts (EDA) and the School of Computing (SoC) trained computers in a time of mass comparison of cancer cell data using a pilot collection of cell lines and using computer models capable of "deep learning." Thus an algorithm has been developed which allows the computers to examine and accurately identify and mark separate microscopic digital cell line images.
This innovation is likely to include an easy-to-use tool that enables a laboratory without the know-how and equipment to easily classify all cell lines.