The BIH Digital Health Center at the Long Night of the Sciences: Artificial intelligence for personalized cancer therapy

Around half a million people are diagnosed with cancer every year, and the trend is rising. In addition to surgery and radiation treatment, administering drugs can also play an important role. But how can we know what the right substance is in each individual case? Scientists from the Intelligent Imaging working group at the Digital Health Center of the Berlin Institute of Health (BIH) are seeking an answer to this question with the help of artificial intelligence.

In the first step, the scientists led by Dr. Christian Conrad receive primary tissue samples from surgically removed tumors. “These are often very small samples, and we are unable to test 50 different drugs to determine the effects,” Conrad explains. “Instead, we grow small three-dimensional pieces of tissue, so-called organoids, from the stem cells contained in the tissue, and we are able to then use these to carry out the tests. Under the microscope, we can observe whether a substance has caused the tumor to shrink, whether it kills the tumor cells, or if there is no effect.”

However, because there are so many samples that need to be tested, the researchers are working to automate the procedure: “We are using cell culture trays that can accommodate 100 organoids at the same time. These are automatically analyzed under the microscope, and the data is evaluated directly on a computer. Our goal is to develop models that can provide information on which drug has the best effect in the various patient tumors,” says Conrad.

At the same time, the scientists are also analyzing the genetic expression of these mini-tumors. They are able to gather information on what genetic changes are contained in the tumor and can predict which targeted drugs are most likely to be active against the tumor cells. “Most of the time, our prediction based on the sequencing data matches our observations under the microscope, but sometimes it doesn’t,” adds Conrad. “We want to find out more about the relationship between the morphology, that is, the appearance of the organoids, and the gene expression.”

Professor Roland Eils, founding director of the BIH Digital Health Center, commented that “our goal is to be able to offer different cancer patients the most effective therapy with as few side effects as possible. And in the future, we want to further develop the procedure in such a way that we can use it for as many types of cancer as possible.”