Israeli scientists discover new method to predict spread of melanoma
Cancer cells [illustrative]
(photo credit: PIXABAY)
Now, the team is trying to better understand what they found and its practical implications.
A research team headed by Dr. Assaf Zaritsky of Ben-Gurion University of the Negev has developed a method to identify melanoma cells that are likely to metastasize to other parts of the body.
The method is based on deep neural networks, which use sophisticated mathematical modeling to process data in complex ways. Melanomas are a form of aggressive skin cancer.
Zaritsky, a member of BGU’s Department of Software and Information Systems Engineering, worked with Gaudenz Danuser of the University of Texas Southwestern Medical Center at Dallas during his postdoctoral research, to develop what they are calling “quantitative live cell histology.” The approach calls for filming live cancer cells with microscopic cameras, and using artificial intelligence to analyze the video sequence and identify cells’ appearance and behavioral patterns that associate with metastatic potential.
The team demonstrated at the American Society for Cell Biology/EMBO conference in San Diego last December that their representation of the functional state of individual cells can predict the chances that a stage III melanoma will progress to stage IV, the most advanced phase of melanoma and a serious form of skin cancer. This means that the cancer has spread from the lymph nodes to other organs, most often the lungs.
Zaritsky told The Jerusalem Post that his research team used melanoma cells from patients that were previously implanted into mice and showed associated metastatic potential to the patient’s outcome. The team investigated whether this potential can be predicted from the cells’ dynamics.
He explained that, normally, metastatic progression is predicted through a combination of genetic tests, patient history and static histological slides. He said that it’s common to measure the properties of cells, such as their shape. However, “regular imaging methods would not give information about the rapid dynamics happening within the cells,” he said. “Deep neural networks capture some of this information and allow us to distinguish between melanoma cells, including those that will move into stage IV or not.
“We identified hidden patterns within the video sequence,” he continued. “By hidden, I mean [ones] that the human eye cannot see or appreciate.”
Now, Zaritsky is trying to better understand what he and the team found and its practical implications. He said “the dream” is that a person would come with stage III melanoma and doctors could predict if it would progress to stage IV or not and, based on that, adjust his or her treatment.
“Another further dream would be drug screening,” Zaritsky said. “We would take cells from patients and apply different drugs to them to see how these drugs change the cells – [whether] they behave more like cells with less metastatic potential.”
“That would be personalized medicine,” he said. “But we are just in the preliminary stages. It is a long process.”