A research team led by USC scientists has developed a new way to identify molecular markers of breast cancer tumors.
The identification of these molecular markers is a potentially lifesaving breakthrough that could lead to better treatment for millions of women.
With the assistance of machine learning, the researchers taught a computer to rapidly sort images of breast tumors to identify which ones had estrogen receptors, which are essential to determine prognosis and treatment options.
This helps to find a new way for breast cancer treatment that promises faster results for less cost for more people across the globe.
Determination of breast tumors using machine learning is the beginning of a revolution to use machine learning to get new information about breast cancer to the physician.
It can also be used to detect better treatments, get information to patients faster and help more people.
The key to identifying and treating cancer is knowing the nature of the tumor.
Cancer cells that contain receptors for estrogen and other hormones respond differently to cancer drugs that target these mechanisms.
Machine learning technology enables to identify a marker on the same day and there will be less delay, less stress, and potentially better outcomes.
It will also help to enable us to identify the right drug and dose more quickly.
The researchers focused on the machine learning to more clearly focus on telltale markers of a cell's nucleus.
The key was to extract parameters describing the shape of nuclei, and feeding these into a large neural network that could learn relationships between nucleus shape and molecular markers.
The new technology has the potential to enhance clinical care.