Cancer research: AI will change the way we see tumors

Researchers at the Karolinska Institutet and SciLifeLab in Sweden are developing a new approach to analyze tumors using artificial intelligence (AI). 

The innovative method combines AI techniques originally developed for satellite imaging and community ecology. 

The goal is to interpret the vast amounts of data obtained from tumor tissue, potentially paving the way for more personalized cancer treatments.

Focus of the study 

Tumor imaging has advanced significantly, offering detailed insights into the microscopic world of tumors. However, these advances have led to a new challenge: the interpretation of an enormous amount of generated data. 

“Advances in multiplex histology allow surveying millions of cells, dozens of cell types, and up to thousands of phenotypes within the spatial context of tissue sections,” noted the researchers.

Significant hurdles in tumor imaging 

Traditional imaging methods can measure hundreds of molecules in thousands of cells, but discerning which molecules and cells are crucial has become increasingly complex.

AI methods offer a solution to analyze this deluge of data. However, traditional AI often operates as a “black box,” performing tasks without providing explanations understandable to human researchers. This lack of transparency in AI processes has been a significant hurdle in its application to medical research.

Satellite image interpretation 

Seeking a solution, the team turned to techniques from different fields. They drew inspiration from analysis methods in satellite imaging and ecology, dating back to the 1950s and 2000s. 

Satellite imaging AI is adept at identifying varied geographical features in large images, such as cities and forests. Similarly, ecological techniques analyze how different species coexist in a geographic area.

Turning complex data into new insights 

“We realized that the interpretation of tumor images is similar to the interpretation of satellite images and that the relationships between cells in a tissue are similar to the relationships between species in ecology,” explained senior researcher Jean Hausser.

“By combining techniques used in satellite imaging and ecology and adapting them for the analysis of tumor tissue, we have now been able to turn complex data into new insights into how cancer works.”

Personalized cancer treatment 

Looking ahead, the researchers plan to implement this method in clinical trials. Collaborations are underway with a major cancer hospital in Lyon, France, to understand the varied responses to cancer immunotherapy among patients. 

Another partnership with the Mayo Clinic in the U.S. will focus on why certain breast cancer patients may not require chemotherapy. This cross-disciplinary approach holds promise for significantly advancing personalized cancer treatment, offering new hope for patients worldwide.

“With our new method, we can reveal important details in tumor tissue that can determine whether a cancer treatment works or not. The long-term goal is to be able to tailor cancer treatments to individual needs and avoid unnecessary side effects,” said Hausser.

The study is published in the journal Nature Communications.

Like what you read? Subscribe to our newsletter for engaging articles, exclusive content, and the latest updates.

—-

Check us out on EarthSnap, a free app brought to you by Eric Ralls and Earth.com.