Artificial `brain` that detects breast cancer
Washington: This year’s winner of the second annual Google Science Fair wrote a cloud-based computer program that makes breast cancer detection less invasive.
In the science talent competition for kids aged 13 to 18, which was held this month in Palo Alto, California, 17-year-old Brittany Wenger created computer programs coded to think like the human brain and then used them to locate mass malignancy in breast tissue samples.
She called it the “Global Neural Network Cloud Service for Breast Cancer”, Discovery News reported.
Traditional methods of finding mass malignancy use a minimally invasive, but painful, biopsy called a fine needle aspirate (FNA).
Analyzing tissues collected with this method isn’t always effective and sometimes results in further invasive procedures.
Wegner tested her method with 7.6 million trials to see how accurately it would detect cancerous tumors.
It succeeded with a 97.4 percent success rate in prediction and 99.1 percent sensitivity to malignancy when analyzing samples collected from FNA.
Employing this data to a cloud service could make it possible for doctors to assess tumors without employing more invasive testing.
For winning the competition, Wegner received 50,000 dollars, a trip to the Galapagos Islands and one year of mentoring and internship opportunities.