Artificial Intelligence and Radiology: The New "Buzz"

What is AI?

Here is the Wikipedia definition for the beginners: 

Artificial intelligence (AI) is intelligence exhibited by machines. In computer science, an ideal "intelligent" machine is a flexible rational agent that perceives its environment and takes actions that maximize its chance of success at some goal. Colloquially, the term "artificial intelligence" is applied when a machine mimics "cognitive" functions that humans associate with other human minds, such as "learning" and "problem solving".

How does it work in Radiology

Artificial intelligence has serious implications for radiology in particular among other medical specialties. Simply put, an AI computer program can do tasks normally performed by intelligent people. Deep learning paradigms are trained by giving them a massive amount of data with known truth. They basically iterate on the strength of the connections until they are able to predict the known truth very accurately.

RSNA 2016 had  demonstrations about ability of AI in radiology with IBM watson and it has given a glimpse to the radiologists about a possible future. Although some people have become concerned about their jobs are at risk, consensus world wide is possibility of a partner of man-machine in future to help radiologists reduce their efforts on boring repetitive tasks and in turn enable better patient care. 

Microsoft is working on a project to develop a machine called "Hanover". Its goal is to memorize all the papers necessary to cancer and help predict which combinations of drugs will be most effective for each patient. One project that is being worked on at the moment is fighting the myeloid leukemia, a fatal cancer where the treatment has not improved in decades.

Future surely looks interesting for Medical science specially the pattern recognition specialists like us with advent of technology and re-invention of the roles of man and machine will be on cards in future.