New AI technology shows it can improve the management of breast cancer with early and precise breast cancer detection. A new study helps in early breast cancer detection, which will eventually lead to better management of breast cancer which is currently a most common cancer amongst females. This study is from the University of Copenhagen.
This year, the disease killed 670,000 people worldwide. And now, researchers at the University of Copenhagen have, for the first time, demonstrated that AI can help women get better treatment by scanning for irregular-looking cells in order to provide superior risk assessment.
New research published in The Lancet Digital Health reveals that the technology was substantially better than current clinical benchmarks for breast cancer risk assessment at predicting cancer risks.
A most important component of evaluation of risk of cancer is early detection of dying cells originating from cellular senescence. These cells are metabolically still active but no longer dividing. While earlier studies have established that the senescent state functions to restrain the development of cancers, these same senescent cells may further contribute to inflammation that supports the growth of tumours.
Senescent cells are still metabolically active but have stopped dividing. This previous research states that this senescent state helps to suppress the development of cancer.
Deep learning AI, the researchers showed, could identify senescent cells in tissue biopsies-their twin sister cells an apparent better way of predicting breast cancer risk than was accomplished using the Gail model, the present gold standard for assessing breast cancer risk.
Algorithm trained on ‘zombie cells’ can give better treatment
The researchers therefore trained the AI technology on senescent cells that have been engineered in cell culture to be damaged on purpose. The researchers then used the AI on the donor biopsies to identify senescent cells.
They are connected with cancer development, so we designed and trained the algorithm in an attempt to predict cell senescence. It specifically looks at how the cell nuclei are shaped because the nuclei become more irregular when cells are senescent,» explains Heckenbach.Â
It will take time to use the technology in the clinic, which can be applied everywhere, as it only needs standard images of sample tissues for analysis purposes.
Then women around the world can potentially make use of this new knowledge to get better treatment. According to Scheibye-Knudsen, “We will be able to use this information to stratify patients by risk and improve treatment and screening protocols.”
Reference:
University of Copenhagen. AI could predict breast cancer risk via “zombie cells” Medical Xpress‌
