Machines learn to detect breast cancer
Software that recognizes patterns in data is commonly used by scientists and economists. Now, researchers in the United States have applied similar algorithms to help them more accurately diagnose breast cancer.
Duo Zhou, MS, a biostatistician at the pharmaceutical company, Pfizer, in New York, New York, together with his colleagues, Dinesh Mital, PhD, and Shankar Srinivasan, PhD, of the University of Medicine and Dentistry of New Jersey, in Newark, point out that data pattern recognition is widely used in machine-learning applications in science. Computer algorithms trained on historical data can be used to analyze current information and detect patterns and then predict possible future patterns. However, this powerful knowledge discovery technology has not been used much in medicine.
The team suggested that just such an automated statistical analysis methodology might readily be adapted to a clinical setting. They have done just that in using an algorithmic approach to analyzing data from breast cancer screening to more precisely recognize the presence of malignant tumors in breast tissue as opposed to benign growths or calcium deposits. This could not only help improve outcomes for patients with malignancies, but also reduce the number of false-positives that otherwise lead patients to unnecessary chemotherapy, radiotherapy, or surgical interventions.
The machine-learning approach takes into account nine characteristics of a minimally invasive fine-needle biopsy, including clump thickness, uniformity of cell size, adhesions, epithelial cell size, bare cell nuclei, and other factors. Trained on definitive data annotated as malignant or benign, the system was able to correlate the many disparate visual factors present in the data with the outcome. The statistical model thus developed could then be used to test new tissue samples for malignancy.
Their work was published in the International Journal of Medical Engineering and Informatics (2013;5:321-333).