Imagine if the technology already used for facial recognition in surveillance cameras or unlocking smartphones were used to detect diseases early. This is what a team of Spanish researchers has just presented who have created an artificial intelligence (AI) tool, called AINU (NUcleus AI), capable of recognizing specific patterns and changes in the shape of DNA molecules characteristic of cancer and viral infections.
The book is presented this Tuesday in the magazine Natural Machine Intelligenceand scientists from the Genomic Regulation Center (CRG), the University of the Basque Country (UPV/EHU), the International Physics Center of Donostia (DIPC) and the Bizkaia Biophysics Foundation (FBB, located in the Biophysics Institute) are participating. The tool scans high-resolution images of cells obtained with a special microscopy technique called STORM, which creates an image that captures much more detail than normal microscopes can see.
“We developed an AI algorithm that, combined with the use of high-resolution images, allowed us to identify certain chromatin changes in the cell nucleus,” Pia Cosma, co-lead author of the study and researcher, told elDiario.es. from the Center for Genomic Regulation (CRG) in Barcelona.
These high-definition snapshots reveal structures at nanometer (nm) resolution and allow the tool to detect rearrangements in cells as small as 20 nm, or 5,000 times smaller than the width of a human hair, alterations too small and subtle for human observers to detect with traditional methods.
“The resolution of these images is powerful enough that our AI can recognize specific patterns and differences with remarkable accuracy, helping to detect alterations very quickly after they occur,” Cosma says. Cancer cells have distinctive changes in their nuclear structure compared to normal cells, such as alterations in how their DNA is organized or in the distribution of enzymes in the nucleus. After training, AINU was able to analyze new images of cell nuclei and classify them as cancerous or normal based on these features alone.
Look for cancer, look for Wally
AINU is a convolutional neural network, a type of AI designed specifically to analyze visual data such as images. In medicine, convolutional neural networks 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 detect abnormalities in MRI or X-ray images, helping to make a faster and more accurate diagnosis.
In this case, the system is a kind of Where is Wally? in which the machine does not look for the character in the striped shirt, but for abnormal cells that can give rise to a pathology. However, there are some small differences with facial recognition. “To identify a person’s face, you have to use many images to train the algorithm,” explains the researcher. “In our case, we used few images, because the resolution is very high, but when faced with two cells that look exactly the same by any other method, this algorithm can distinguish them.”
For this reason, he says, the authors believe that one day this type of information could allow doctors to save time in monitoring the disease, personalizing treatments and improving patient outcomes. “The main advantage of the system is that, a prioriOnce a cancer type has been identified, the algorithm will be able to continue to detect it in other patients, regardless of their specific mutation. “It will be specific to the cancer type,” Cosma says. “If one patient has one mutation and another has another, through the algorithm we will recognize both.”
One hour after infection
The system has also proven useful in viral infections. Using this approach, the AI was able to detect changes in a cell’s nucleus just an hour after it was infected with herpes simplex virus type 1. The model can detect the presence of the virus by finding small differences in DNA density, which occurs when a virus begins to alter the structure of the cell nucleus.
Our method allows us to detect cells infected by a virus very soon after the start of infection.
Ignacio Arganda-Carreras
— Co-author of the study and associate researcher of Ikerbasque at the UPV/EHU
“Our method can detect cells infected with a virus very soon after the onset of infection,” he explains. Ignacio Arganda-Carrerasco-author of the study and associate researcher of Ikerbasque at the UPV/EHU. “It usually takes a while for doctors to detect an infection, because they rely on visible symptoms or larger changes in the body. But with AINU, we can immediately see small changes in the nucleus of the cell.
“This technology can be used to see how viruses affect cells almost immediately after they enter the body, which could help develop better treatments and vaccines,” adds Limei Zhong, co-senior author of the study and a researcher at the Guangdong Provincial People’s Hospital (GDPH) in Guangzhou, China. “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.”
How to get tested in clinic
The study authors caution that they still need to overcome significant limitations before the technology is ready for testing or implementation in clinical settings. For example, STORM images can only be taken with specialized equipment typically found only in biomedical research labs. Installing and maintaining the imaging systems required by AI represents a significant investment in equipment and technical skills.
“Accessibility and performance limitations are more manageable issues than we thought, and we hope to conduct preclinical experiments soon.
Pia Cosma
— Co-lead author of the study and researcher at the Center for Genomic Regulation (CRG)
Another limitation is that STORM imaging analyzes few cells at a time. For diagnostic purposes, especially in clinical settings where speed and efficiency are crucial, physicians would need to capture many more cells in a single image to be able to detect or monitor disease.
But, according to Cosma, these microscopes could soon be available in smaller or less specialized laboratories. “Simpler microscopes are being developed, the hope is that they will enter very soon in any laboratory and any hospital,” he says. “The ideal use will be to analyze the liquid tumor, that is, to be able to identify its early presence through a blood test, but we must be very careful because we are not there yet; “This is only an initial proof of concept work.”
Identifying stem cells
Finally, the study authors found that the technology can also identify stem cells with very high accuracy. These cells can become any type of cell in the body and are being studied for their potential to help repair or replace damaged tissue. Developing this capability would help make the resulting therapies safer and more effective.
“Current methods for detecting high-quality stem cells are based on animal testing,” explains Davide Carnevali, first author of the study and a CRG researcher. “However, all our AI model needs to work is a sample stained with specific markers highlighting the main nuclear features. “In addition to being simpler and faster, this can accelerate stem cell research and, at the same time, contribute to the change in reducing the use of animals in science.”
