In a study on ovarian cancer cells, researchers from Karolinska Institutet demonstrate how the tumor environment influences how cancer cells respond to drugs by using AI. The study has been published in the journal Communications Biology.
The cancer cells were cultured together with fibroblasts, a type of support cell, and treated with different drugs. Advanced computer programs were used to analyze images of the cancer cells to see how they changed. Fibroblasts, play an important role in the tumor microenvironment. They can promote tumor growth, spread, and drug resistance, as well as affect the immune system.
"Our study shows that ovarian cancer cells cultured together with fibroblasts change their appearance when treated with drugs. This demonstrates how the tumor environment influences how cancer cells respond to drugs," says Osheen Sharma , PhD student at the Department of Oncology-Pathology , Karolinska Institutet, and the study's first author.
By studying the morphology of cancer cells when cultured with fibroblasts, resesarchers can gain a better understanding of how these support cells affect cancer development and how drugs work. This can help in the development of better treatments for cancer.
AI-analysis of cancer cells
"We took over 61,000 images of cancer cells and fibroblasts treated with 528 different drugs. Then we used advanced computer programs to analyze the images and see how the cancer cells changed. We also verified that our computer program could recognize similar changes from drugs with the same mechanism of action," explains Brinton Seashore-Ludlow , Associate Professor at the same department and the study's last author.
The researchers will now investigate how cancer cells and fibroblasts directly affect each other to understand how the cells communicate within the tumor. They also share their image material so that others can use it in their research on cancer and drugs.
This research highlights how different drugs affect cancer cells in various ways and emphasizes the significant variation in the appearance of cancer cells and their responses to treatments.
The research was funded by the Swedish Research Council, Karolinska Institutet, the Knut and Alice Wallenberg Foundation, Sagen Stiftelse, and the Research Council of Finland, among others.
Publication
Evaluating feature extraction in ovarian cancer cell line co-cultures using deep neural networks.
Sharma O, Gudoityte G, Minozada R, Kallioniemi OP, Turkki R, Paavolainen L, Seashore-Ludlow B
Commun Biol 2025 Feb;8(1):303
