In a new turn of technological superiority, Artificial Intelligence, now can be a great assistance for doctors to spot mammograms, say researchers from Google and medical centers in the United States and Britain reported in the journal Nature.
This one of Google’s ventures into medicine for analysing mammograms, done by X-rays of the breast, is still being worked upon and yet to be commercialised for widespread use. Computers now can be programmed to distinguish patterns and interpret images, and the company has already derived algorithms to help detect lung cancers through CT scans, diagnose eye disease in people with diabetes and diagnosed cancer on microscope slides.
This new system performed better than radiologists. The system produced a 9.4 per cent less false negatives, in which a mammogram is mistakenly read as normal, without any cancer virus. It also gives 5.7 per cent less false positives, that is misjudged as abnormal but there is no cancer.
The system beat the radiologists, with reduced false negatives by 2.7 per cent and false positives by 1.2 per cent in Britain.
Google associated with Northwestern University in Chicago and two British medical centers, Cancer Research Imperial Centre and Royal Surrey County Hospital to perform this research.