Marcella La Cioppa Women around the world could receive better care thanks to artificial intelligence, which allows better detection of damaged cells and more accurately predicts the risk of getting breast cancer, according to new research from the University of Copenhagen.
@Canva
Breast cancer remains one of the most common types of cancer globally. In 2022 alone, it claimed the lives of 670,000 people worldwide. Now, a new study from the University of Copenhagen suggests that artificial intelligence (AI) can assist women in receiving more effective treatment by analyzing irregular-looking cells and providing a more accurate risk assessment.
Researchers have employed deep learning AI technology, developed at the University of Copenhagen, to analyze breast tissue biopsies from donors. Their goal was to detect signs of damaged cells, which indicate an increased risk of cancer.
“The algorithm represents a major leap forward in our ability to identify these cells. Millions of biopsies are performed each year, and this technology can help us better assess risks and offer improved care for women,” said the research team.
Identifying cellular senescence in cancer risk assessment
One key factor in cancer risk evaluation is the identification of dying cells, caused by what’s known as cellular senescence. Senescent cells are still metabolically active but have stopped dividing. Previous research has shown that this state of senescence can help suppress the development of cancer. However, senescent cells can also trigger inflammation, which in turn may lead to tumor growth.
By using deep learning AI to detect senescent cells in tissue biopsies, researchers were able to predict breast cancer risk more effectively than the current gold standard, the Gail model.
The study
The researchers applied AI technology to cells grown in lab cultures that had been intentionally damaged to make them senescent. They then used the AI on donor biopsies to identify senescent cells.
“We sometimes call them zombie cells because they’ve lost some of their function, but they’re not completely dead. They’re associated with cancer development, so we developed and trained the algorithm to predict cellular senescence. Specifically, our algorithm examines the shape of the cell nuclei, as these become more irregular when cells are senescent,” explained the researchers.
It will take several more years before this technology becomes available for clinical use. However, once it is, it could be applied worldwide, as it only requires standard images of tissue samples to perform the analysis. This means that women globally could potentially benefit from this new insight, enabling better treatment options.
Source: The Lancet Digital Health
