AI in the now... Image processing, X-ray diagnosis...

doifeellucky (64)in #ai • 5 years ago

The University of Stanford has a budget of 6,3 (!!!) billion dollars yearly.

How will AI change medicine and health care?

Here a little example of what already is possible today!

One of their achievements in the field of AI is the diagnosis of illnesses based on X-ray pictures. They even build an app that you can use on your smart phone or tablet. Just put an X-ray in front of your mobile lens and it comes up with the diagnosis.

Before radiologists had to have decades of experience and had to look at ten thousands of X-ray images to raise their certainty for accurate diagnosis.

With the app and the AI in the background that was trained with about 100 thousand of X-ray images including the definitive diagnosis, provided by national health organization, does this in the matter of seconds. With every image they processed in this very large data set the regarding illness was also part of the data. With machine learning it was possible to "train" the AI to get better and better results in the diagnosis accuracy.

So in short, they've generated an intelligent algorithm that allows a quick and pretty accurate method to do diagnosis based on these images that can be used by people without being an radiology specialist.

This is clearly a good example of a positive use of AI in the present and these systems get better and better.

What will happen to the radiologists if they aren't needed anymore for this kind of diagnosis methods?

Check out their most recent paper in this field:

Rajpurkar P, Irvin J, Ball RL, Zhu K, Yang B, Mehta H, Duan T, Ding D, Bagul A, Langlotz CP, Patel BN, Yeom KW, Shpanskaya K, Blankenberg FG, Seekins J, Amrhein TJ, Mong DA, Halabi SS, Zucker EJ, Ng AY, Lungren MP. Deep learning for chest radiograph diagnosis: A retrospective comparison of the CheXNeXt algorithm to practicing radiologists. PLoS Med. 2018 Nov 20;15(11):e1002686.

https://www.ncbi.nlm.nih.gov/pubmed/30457988

Check out their work in this field here

The AIMI Center

Stanford has established the AIMI Center to develop, evaluate, and disseminate artificial intelligence systems to benefit patients. We conduct research that solves clinically important imaging problems using machine learning and other AI techniques.