Artificial intelligence will learn to distinguish cancer cells from normal cells

Researchers from different institutions have developed artificial intelligence that can distinguish cancer cells from normal cellsand identifying the earliest phases of viral infection inside cells. The findings, published today in the journal Nature Machine Intelligencewill pave the way for the development of new diagnostic methods and disease monitoring strategies.

AINU (AI Core) tool scans high resolution photographs of cells. They are obtained using a special microscopy method called STORM, which creates an image that covers much more detail than conventional microscopes can see. High-resolution images allow you to see structures with nanometer resolution.

The images were obtained using STORM microscopy, which reveals more detail than conventional microscopes.

One nanometer (nm) is one billionth of a meter, and the width of a single strand of human hair is about 100,000 nm. AI can detect rearrangements inside cells as small as 20 nmthat is, 5000 times smaller than the width of a human hair.These changes are too small and subtle to be visualized by human observers using traditional methods.

“The resolution of these images powerful enough that our AI can recognize certain patterns and differences with astonishing precision, including changes in the way DNA is organised inside cells, which helps detect changes very soon after they occur,” he says. Pia Cosmaco-lead author of the study and research fellow at the Centre for Genomic Regulation (CRG) in Barcelona.

“We believe that one day this information will allow doctors to gain time to manage the disease, personalize treatment and improve patient outcomes,” he adds.

“Face recognition” at the molecular level

AINU This convolutional neural networka type of artificial intelligence designed specifically to analyze visual data, such as images. Some examples include artificial intelligence tools that allow users to unlock smartphones

with your face or the faces of other people, which self-driving cars use to understand and navigate their environment by recognizing objects on the road.

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-rayswhich helps to make a faster and more accurate diagnosis.

The model learned to recognize certain patterns in cells by analyzing how nuclear components are distributed and organized in three-dimensional space.

AINU analyzes tiny structures inside cells at the molecular level. The team trained the model by feeding it nanometer-resolution images of the nuclei of many different cell types. The model learned to recognize certain cellular patterns by analyzing how nuclear components are distributed and organized in three-dimensional space.

For example, cancer cells have characteristic changes in their structure nuclear compared to normal cells, such as changes in the organization of their DNA or the distribution of enzymes within the nucleus. After exercise, AINU was able to analyze new images of cell nuclei and classify them as cancerous or normal based on these characteristics alone.

Changes detected in just one hour

Nanometer-resolution imaging enabled AI to detect changes in the cell nucleus just an hour after infection with the herpes simplex virus type 1. The model can detect the presence of the virus by find small differences by DNA densitywhich occurs when a virus begins to change the structure of the cell nucleus.

Our method instantly detects viral infections by observing changes in the cell nucleus, while traditional methods rely on visible symptoms.

“Our method can very quickly find cells infected with the virus after the infection begins. It usually 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,” he says. Ignacio Arganda-CarrerasCo-author and researcher at the University of the Basque Country.

“This technology can be used to see how viruses infect cells almost immediately after entering the body, which can help develop more effective treatments and vaccines. In hospitals and clinics, AINU can be used to diagnose infections in a simple way. blood or tissue samplewhich makes the process faster and more accurate,” he adds. Limei ZhongCo-lead author and researcher at Guangdong Provincial People’s Hospital, China.

Important limitations

The authors caution that they still have important limitations to overcome before the technology is ready for testing or mass-scale implementation. clinical situation

. For example, STORM images can only be taken with special equipment. which are typically found only in biomedical research laboratories. Installing and maintaining the imaging systems required for AI requires significant investment in both equipment and technical skills.

Another limitation is that STORM images analyze multiple cells simultaneouslyFor diagnostic purposes, especially in clinical settings where speed and efficiency are critical, doctors will have to capture many more cells in a single image to be able to detect or track disease.

“There are a lot of rapid advances in STORM imaging, which means that microscopes They may soon appear in smaller or less specialized labs and eventually even in clinics.“The availability and performance limitations are more solvable problems than we thought, and we hope to conduct preclinical experiments soon,” explains Cosma.

Accelerate clinical trials

Although it may take years to achieve clinical results, it is expected that in the short term AINU speed up scientific research. The authors found that the technology also can identify stem cells with very high accuracyThese cells can become any type of cell in the body and are being studied for their ability to repair or replace damaged tissue.

Do You Love Your Partner or Your Pet More? Study Shows How Love Stimulates the Brain

See more

AINU could make the process of detecting stem cells faster and more accurate and help develop treatments. safer and more effective.

“Current methods for detecting high-quality stem cells rely on animal testing. However, all our AI model needs to work is a sample stained with specific markers that highlight key nuclear features. Besides being simpler and faster, it could speed up stem cell research. and at the same time contribute to reducing the use of animals in science,” he concludes. Davide CarnevaliFirst author and CRG investigator.

This article Originally published by Agencia SINC. Scientists from the Spanish Foundation for Science and Technology.