Researchers take a new AI approach to analyzing tumors

picture:

New AI methods are constantly being developed to interpret data from satellite images, for example to automatically identify cities, lakes, forests and deserts in large satellite images. In ecology, advanced techniques are used to reveal how species of plants, animals, and microorganisms live together in communities within a specific geographic area.

– We realized that interpreting tumor images is similar to interpreting satellite images and that the relationships between cells in tissues are similar to the relationships between species in communities of organisms. By combining techniques used in satellite imaging and ecology and adapting them to analyze tumor tissue, we have now been able to turn complex data into new insights into how cancer works, he says. Jan Housersenior researcher at Department of Cell and Molecular BiologyKarolinska Institutet, which led the research.

Tailored cancer treatments

The next step is to apply the new method in clinical trials. Researchers are collaborating with a large cancer hospital in Lyon, France, to search for answers as to why only some patients respond to cancer immunotherapy. In another collaboration with the Mayo Clinic in the US, they are investigating why some breast cancer patients do better without chemotherapy.

Using our new method, we can reveal important details in tumor tissue that could be important in whether cancer treatment is successful or not. The long-term goal is to be able to tailor cancer treatments based on individual needs and avoid unnecessary side effects, says Jan Hauser.

The research was mainly funded by the Norwegian Cancer Fund, the Swedish Research Council, and SciLifeLab. There are no reports of conflicts of interest.

Publishing

“NIPMAP: Phenotypic Mapping of Multiple Tissue Data by Community Ecology”Anisa Marhi, Fabio Libreri, Zeke Kang, Louise Jessel, Albert Eroglu, David Albert, Jan Hauser, Nature Communicationsonline 7 November 2023, doi: 10.1038/s41467-023-42878-z.