AI detects cancer and viral infections with nanoprecision

Researchers have developed an artificial intelligence that can distinguish cancer cells from normal cells and detect the very early stages of a viral infection in cells. The results were published today in a study in the journal Nature-Machine-Intelligencepave the way for improved diagnostic techniques and new disease surveillance strategies. The researchers come from the Centre for Genomic Regulation (CRG), the University of the Basque Country (UPV/EHU), the Donostia International Physics Center (DIPC) and the Fundación Biofisica Bizkaia (FBB, located at the Biofisika Institute).

The AINU (AI of the NUcleus) tool scans high-resolution images of cells. The images are captured using a special microscopy technique called STORM, which produces an image that captures many finer details than conventional microscopes can detect. The high-resolution snapshots show structures at nano-resolution.

A nanometer (nm) is one billionth of a meter, and a human hair is about 100,000 nm wide. AI can detect changes within cells as small as 20 nm, 5,000 times smaller than the width of a human hair. These changes are too small and subtle for human observers to detect using conventional methods alone.

“The resolution of these images is high enough for our AI to detect certain patterns and differences with remarkable accuracy, including changes in the arrangement of DNA in cells. This allows changes to be detected very soon after they occur. We believe that this type of information will one day allow doctors to gain valuable time to monitor diseases, personalize treatments and improve patient outcomes,” says ICREA research professor Pia Cosma, co-author of the study and researcher at the Centre for Genomic Regulation in Barcelona.

“Face recognition” at the molecular level

AINU is a convolutional neural network, a type of AI specifically designed to analyze visual data such as images. Examples of convolutional neural networks include AI tools that allow users to unlock smartphones with their face, or others used by self-driving cars to understand and navigate environments by recognizing objects on the road.

In medicine, convolutional neural networks are used to analyze medical images such as mammograms or CT scans and detect signs of cancer that may escape the human eye. They can also help doctors detect abnormalities in MRI scans or X-rays, allowing for faster, more accurate diagnosis.

AINU detects and analyzes tiny structures inside cells at the molecular level. The researchers trained the model by feeding it nanometer-sized images of the nucleus of many different cell types in different states. The model learned to recognize certain patterns in cells by analyzing how nuclear components are distributed and arranged in three-dimensional space.

For example, cancer cells exhibit significant changes in their nuclear structure compared to normal cells, such as changes in the organization of their DNA or the distribution of enzymes in the cell 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.

The nanoscale resolution of the images allowed the AI ​​to detect changes in the cell nucleus as early as one hour after infection with herpes simplex virus type 1. The model was able to detect the presence of the virus by noting slight differences in the density of DNA that occur when a virus begins to alter the structure of the cell nucleus.

“Our method can detect cells infected with a virus very soon after the infection begins. Usually, doctors take a while to detect an infection because they rely on visible symptoms or major changes in the body. However, with AINU, we can immediately detect tiny changes in the cell nucleus,” says Ignacio Arganda-Carreras, co-author of the study and Ikerbasque research associate at the UPV/EHU and member of the FBB Biofisika Institute and the DIPC in San Sebastián/Donostia.

“Researchers can use this technology to see how viruses affect cells almost immediately after they enter the body, which could help develop better treatments and vaccines. In hospitals and clinics, AINU could be used to quickly diagnose infections from a simple blood or tissue sample, which would make the process faster and more accurate,” adds Limei Zhong, co-first author of the study and researcher at the Guangdong Provincial People's Hospital (GDPH) in Guangzhou, China.

Laying the foundation for clinical readiness

Before the technology can be tested or used in clinical settings, researchers still need to overcome important limitations. For example, STORM images can only be captured using specialized equipment typically found only in biomedical research labs. Setting up and maintaining the imaging systems required by AI requires significant investment in equipment and technical expertise.

Another limitation is that STORM imaging typically analyzes only a few cells at a time. For diagnostic purposes, especially in clinical settings where speed and efficiency are critical, doctors would need to capture many more cells in a single image to detect or monitor disease.

“There are many rapid advances in the field of STORM imaging, which means that microscopes could soon be available in smaller or less specialized laboratories and eventually even in the clinic. The limitations in accessibility and throughput are easier problems to solve than we previously thought and we hope to be able to perform preclinical experiments soon,” says Dr. Cosma.

Although clinical benefits are years away, AINU will accelerate scientific research in the short term. The researchers found that the technology can identify stem cells with very high precision. Stem cells can develop into any cell type in the body, an ability called pluripotency. Pluripotent cells are studied for their potential to help repair or replace damaged tissues.

AINU can make the process of detecting pluripotent cells faster and more accurate, helping to make stem cell therapies safer and more effective.

“Current methods for detecting high-quality stem cells are based on animal testing. However, our AI model only requires a sample stained with specific markers that highlight important nuclear features. Not only is it easier and faster, but it can also accelerate stem cell research while helping to reduce the use of animals in science,” says Davide Carnevali, lead author of the study and researcher at the CRG.