Spanish researchers develop AI that can distinguish cancer cells from normal cells
A research team from the Centre for Genomic Regulation (CRG) in Barcelona, University of the Basque Country (UPV/EHU), International Physics Center Donostia (DIPC) and the Biscay Biophysical Foundation (FBB) have developed artificial intelligence (AI) which can recognize certain patterns and changes in cancer DNA molecules, so it is able to differentiate cancer cells from normal cellsand also discover the earliest phases viral infection inside.
This discovery opens the way to develop new diagnostic methods and disease monitoring strategies. “It usually takes doctors time to detect an infection because they rely on visible symptoms or serious changes in the body,” he said. Ignacio Arganda-Carrerasco-author of the study and associate researcher at UPV/EHU. However, the researcher noted that with this tool, “we immediately see small changes in the cell nucleus.”
Almost instant response
The instrument, which was named AI cores (AINU)scans high-resolution images of cells through STORMa special microscopic technique designed to capture details which elude conventional microscopes.
High-resolution images reveal structures with resolution at the nanometer (nm) level, that is, billionth fraction of a meter. Nanometer-level imaging resolution allowed AI to detect changes in the cell nucleus just an hour after she was infected herpes simplex virus type 1.
Very high accuracy
Thus, rearrangements can be detected within cells measuring just 20 nm, or 5,000 times smaller than the width of a human hairthe changes are too small to be detected by human observers using traditional methods.
“The image resolution is powerful enough to recognize specific patterns with remarkable accuracyincluding changes in the way it is organized DNA in cells“, explained the ICREA research professor, Pia Cosmaco-lead author of the study and research fellow at the Centre for Genomic Regulation (CRG) in Barcelona.
For my part, Limei Zhongco-author of the study and researcher in Guangdong Provincial People’s Hospital (GDPKH) in Guangzhou (China) added: “In hospitals and clinics, AINU can be used to diagnose infections from a simple blood or tissue sample. However, the study’s authors caution that they still need to overcome “important limitations” before the technology is ready for testing or clinical implementation.