Artificial Intelligence Detects Tumor Cells with Nanometer Precision
Artificial intelligence (AI) developed by the Centre for Genomic Regulation (CRG) of Catalonia is able to distinguish tumor cells from normal cells with nanometric precision. One nanometer is equivalent to one billionth of a meter: the width of a strand of human hair is about 100,000 nanometers. This tool opens the door to even earlier and more accurate cancer detection.
The discovery, which also allows the earliest phases of viral infection (such as herpes simplex type 1) to be diagnosed inside cells, was published in the journal Nature Machine Intelligence. The tool was created in collaboration with the University of the Basque Country (UPV), the International Physics Centre of Donostia (DIPC) and the Biophysics Foundation of Biscay (FBB).
“We used an AI algorithm combined with high-resolution microscopy to identify skin tumour cells,” explains Professor Icrea Pia Cosma, co-author of the study and researcher at the Centre for Genomic Regulation (CRG). “What’s new is that the combination of these two technologies gives us very high resolution,” he adds.
The tool is called AINU (AI Nucleus) and it scans high-resolution images of cells. The images are obtained using a special microscopy technique called Storm, which captures much more detail than conventional microscopes can see. High-resolution images allow you to see structures with nanometer resolution.
“The resolution of these images is high enough that our AI can recognize specific patterns and differences with amazing accuracy, including changes in the way DNA is organized inside cells, which helps detect very small changes after they happen,” Cosma believes. “One day,” this kind of information will allow doctors to “buy time” to monitor disease, “personalize” treatments, and “improve” patient outcomes.
The study’s authors caution that they still have important limitations to overcome before the technology is ready for testing or clinical deployment. For example, images of Storm can only be taken using specialized equipment typically found only in biomedical research labs. Installing and maintaining the imaging systems needed for AI requires significant investment.
Moreover, in this study, the scientists used human skin cells and stem cells, but not “the patient’s primary cells.” But “someday,” when it is more developed, this technique will become a reality in hospitals. “It will help us detect cancer earlier. Soon we will apply it to blood cancer, but later it will be possible to act on other types of cancer,” admits Cosma.
AINU is designed to analyze visual data, such as images. Some examples include AI tools that allow users to unlock their smartphones with their faces, or other tools that self-driving cars use to navigate their environment by recognizing objects on the road.
In medicine, convolutional neural networks (AINU is an example) are used to analyze medical images, such as mammograms or CT scans, and identify signs of cancer that the human eye might miss. They can also help doctors spot abnormalities in MRIs or X-rays, helping to make faster and more accurate diagnoses.
AINU recognizes certain patterns in cells by analyzing how nuclear components are distributed and organized in three-dimensional space. For example, cancer cells have distinctive changes in their nuclear structure compared to normal cells, such as changes in the way their DNA is organized or the distribution of enzymes within the nucleus.
In parallel, the nanometric resolution of the images allows AI to detect changes in the cell nucleus just an hour after infection with a virus, such as herpes simplex virus type 1. “Our method can detect cells infected with the herpes simplex virus type 1 very soon after the onset of infection. Usually, it takes doctors some time to detect an infection, as they rely on visible symptoms or more serious changes in the body. But with AINU, we can immediately see small changes in the cell nucleus,” says Ignacio Arganda-Carreras, co-author of the study and Ikerbasca Research Fellow at UPV/EHU, collaborating with the FBB-Instituto Biofisica and DIPC. in San Sebastian.
“This technology can be used to see how viruses affect cells almost immediately after entering the body, which could help develop more effective treatments and vaccines. In hospitals and clinics, AINU could be used to diagnose infections from a simple blood or tissue sample, making the process faster and more accurate,” adds Limei Zhong, a co-author of the study and a researcher at Guangdong Provincial People’s Hospital (GDPH) in Guangzhou, China.
Subscribe to continue reading