Thursday, 19 November 2015

PIGEONS ARE ACTUALLY PRETTY GOOD AT IDENTIFYING MALIGNANT CANCER

The pigeons' training environment consisted of a conditioning chamber with a food pellet dispenser, and a touch-sensitive screen.

Looking at pathology slides and diagnosing cancer can be very challenging; and it takes a long time for a doctor or pathologist to quickly decide whether a microscopic group of cells looks malignant or benign, or whether a small lump seen on a mammogram is suspicious. Well, it turns out that pigeons may one day be able to help out.

In a new study by researchers at the University of California, Davis and the University of Iowa, pigeons were trained to distinguish between healthy and malignant tissue. The study was based on humans and pigeons sharing many of the same visual systems.

During the experiment, each pigeon was shown a set of microscopic images of breast tissue. After staring at the image, the pigeon would then chose either a yellow- or blue-colored button that corresponded to either cancerous or non-cancerous. If the pigeon answered correctly, it was rewarded with a tasty treat. Each pigeon had 15 one-hour long sessions and by the end, they answered correctly about 85 percent of the time.

But when the pigeons were asked to detect cancerous breast masses on mammograms, the pigeons were only able to memorize the correct answer--they couldn't look at a new image and determine whether that mass was cancerous or benign.

So while the pigeons' results are impressive, they still aren’t as accurate as those of a trained pathologist, but the researchers hope this experiment will  shed light on how pathologists get better overtime.

It is expected that by figuring out what pigeons look at to make their diagnosis, researchers will be able to train pathologists and computer systems in a better, more strategic way.

The study was published in PLOS one.

No comments:

Post a Comment

Reactions in Medical School #Memes

Which one can you identify with? πŸ˜‰πŸ˜‰ Tag a friendπŸ‘πŸ½ . Credit @krakstv #Inspiredbykrakslist _______________________________ A p...