Researchers have developed an artificial intelligence that can distinguish between cancer cells and normal cells and detect the early stages of viral infection within cells. The results of a study published today in the journal Nature Machine Intelligence pave the way for improved diagnostic techniques and new disease surveillance strategies. The researchers are from the Center for Genome Regulation (CRG), the University of the Basque Country (UPV/EHU), the Donostia International Physics Center (DIPC) and the Biofiica Bizkaia Foundation (FBB, located at the Biofisika Institute).
The tool AINU (AI of the NUcleus) scans high-resolution images of cells. The images were obtained through a special microscope technology called STORM, which creates images that capture many finer details than can be seen with a normal microscope. High-definition snapshots reveal structures at nanoscale resolution.
One nanometer (nm) is one billionth of a meter, and the length of a human hair is about 100,000 nanometers. AI can detect intracellular rearrangements as small as 20 nanometers (5,000 times smaller than the length of a human hair). These changes are too small and subtle for human observers to detect using traditional methods alone.
“The resolution of these images is powerful enough to allow our artificial intelligence to very accurately identify specific patterns and differences, including changes in the way DNA is arranged within cells, helping to detect changes quickly after they occur.” We believe that one day, this type of large amount of information could buy doctors valuable time to monitor the disease, personalize treatment and improve patient outcomes,”said Professor Pia Cosma, co-corresponding author of the study and a researcher at the Center for Genome Regulation in Barcelona.
“Face Recognition” at the molecular level
AINU is a convolutional neural network, an artificial intelligence specifically used to analyze visual data such as images. Examples of convolutional neural networks include artificial intelligence tools that allow users to unlock smartphones through their faces, or other tools used by self-driving cars to understand and navigate the 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 may miss. They can also help doctors detect abnormalities in MRI scans or X-rays, helping make a faster and more accurate diagnosis.
AINU detects and analyzes microscopic structures within cells at the molecular level. The researchers trained the model by inputting nanoscale resolution images of the nuclei of many different types of cells in different states into the model. The model learned to identify specific patterns in cells by analyzing the distribution and arrangement of nuclear components in three-dimensional space.
For example, compared with normal cells, the nuclear structure of cancer cells has undergone significant changes, such as changes in the organization of DNA or the distribution of enzymes within the nucleus. After training, AINU can analyze new images of cell nuclei and classify them as cancerous or normal based on these characteristics alone.
The nanoscale resolution of the image allows artificial intelligence to detect changes in the cell’s nucleus one hour after a cell is infected with herpes simplex virus type 1. The model can detect the presence of the virus by discovering subtle differences in how tightly DNA is packed, which occur when the virus begins to change the structure of the cell’s nucleus.
“Our method can detect virus-infected cells quickly after infection begins. Often, doctors take time to detect infections because they rely on visible symptoms or large changes in the body. But with AINU, we can study co-corresponding author Ignacio Arganda-Carreras, Ikerbasque researcher at UPV/EHU, the FBB-Biofisika Institute affiliated with San Sebastian/Donostia and DIPC.
“Researchers can use this technology to observe how the virus affects cells almost immediately after entering the body, which can help develop better treatments and vaccines. In hospitals and clinics, AINU can be used to quickly diagnose infections through simple blood or tissue samples, making the process faster and more accurate,”added Zhong Limei, co-lead author of the study and a researcher at the People’s Hospital of Guangdong Province in Guangzhou, China.
Lay the foundation for clinical preparation
Before the technology is ready for testing or deployment in a clinical environment, researchers must overcome important limitations. For example, STORM images can only be taken using dedicated equipment typically found only in biomedical research laboratories. Setting up and maintaining the imaging systems needed for artificial intelligence is a major investment in equipment and technical expertise.
Another limitation is that STORM imaging typically only analyzes a few cells at a time. For diagnostic purposes, especially in clinical settings where speed and efficiency are crucial, doctors need to capture a greater number of cells in a single image to be able to detect or monitor disease.
“There are many rapid advances in STORM imaging, which means that microscopes may soon be used in smaller or less specialized laboratories and eventually even in clinics. Accessibility and flux limitations are issues that are easier to deal with than we previously thought, and we hope to proceed with preclinical trials as soon as possible,”Dr. Cosma said.
Although clinical benefits may be years away, AINU expects to accelerate scientific research in the short term. Researchers found that the technology can identify stem cells with very high precision. Stem cells can develop into any type of cell in the body, an ability called pluripotency. Study the potential of pluripotent cells to help repair or replace damaged tissue.
AINU can make the detection process of pluripotent cells faster and more accurate, helping to make stem cell therapy safer and more effective.
“Current methods of testing high-quality stem cells rely on animal testing. However, all our artificial intelligence model needs to work on is a sample stained with specific markers that highlight key nuclear features. In addition to making it easier and faster, it could also accelerate stem cell research while helping to reduce the shift in animal use in science,”said Davide Carnevali, lead author of the study and a researcher at CRG.
If you want to learn more, you can click on the link below the video.
Thank you for watching this video. If you like it, please subscribe and like it. thank
Original text:https://medicalxpress.com/news/2024-08-ai-cancer-viral-infections-nanoscale.html
More information: A deep learning method that identifies cellular heterogeneity using nanoscale nuclear features, Nature Machine Intelligence (2024). DOI: 10.1038/s42256-024-00883-x
More information: A deep learning method that uses nanoscale nuclear features to identify cell heterogeneity, Nature Machine Intelligence (2024). DOI：10.1038/s42256-024-00883-x
Journal information: Nature Machine Intelligence
Journal information: “Nature·Machine Intelligence”
Oil tubing: