Osaka University-based researchers have created an AI-based system with the potential of differentiating between different kinds of cancer cells.
The findings garnered by the researchers were published in a piece titled “A convolution neural network uses microscopic images to differentiate between mouse and human cell lines and their radioresistant clones,” and published in a journal, Cancer Research.
The researchers from Osaka University have shown through an artificial intelligence (AI)-based system that they can recognize different kinds of cancer cells by scanning microscopic images.
By doing so, they attained increased accuracy compared to human judgment.
The team behind this remarkable research claimed that the system operates on the basis of a convolutional neural network, a part of AI that is based on the visual system of human beings.
The AI-based system was applied to differentiate cancer cells from humans and mice as well as similar cells that had also been picked for their resistance to radiation.
“We first trained our system on 8,000 images of cells obtained from a phase-contrast microscope,” corresponding author Hideshi Ishii said in a release. “We then tested its accuracy on another 2,000 images, to see whether it had learned the features that distinguish mouse cancer cells from human ones, and radioresistant cancer cells from radiosensitive ones.”
Furthermore, the researchers revealed that there is still some hope of training the AI-based system on additional cancer cell types, with the ultimate objective of creating a ubiquitous system with the potential of identifying and distinguishing such cells.