Pigeons Trained To Detect Cancerous Tissue On X-Rays and Slides

Read Time:2 Minute, 38 Second

by Amanda Froelich

Few consider pigeons to be an intelligent bird, but that may change now that scientists have trained an entire flock to pick out diseased breast tissue with an accuracy rate of up to 99%. 

According to a new study published in PLOS ONE, pigeons can distinguish between cancerous and healthy tissue in x-rays and microscope slides.

Three experiments, led by Richard Levenson, professor of pathology and laboratory medicine at the University of California Davis Medical Center, concluded that pigeons have a remarkable capacity to learn how to identify whether an image shows healthy or cancerous breast tissue.

According to the study, this is because the birds “share many usual system properties with humans.” 

For the first experiment, eight pigeons were presented with 144 breast tissue images, all at various levels of magnification and with and without color. The birds could then peck a blue or a yellow button on either side of each image, their choice indicating whether it was cancerous or healthy.

When the birds chose correctly, they were rewarded with food. If they guessed wrong, no treat was given and the image would remain until they correctly identified it.

Levenson told the International Business Times:

“With some training and selective food reinforcement, pigeons do just as well as humans in categorizing digitized slides and mammograms of benign and malignant human breast tissue.” 

Amazingly, after just fifteen days of training, the birds’ accuracy rate had increased from 50% to 85%. Reports The Guardian, the pigeons were then presented with new images to rule out memorization as a possible cause for their success. Soon, they were able to correctly identify the familiar images 87% of the time, and the novel images 85% of the time.

pigeon1

When the birds’ responses were combined, a method they called “flock sourcing,” they found that the group’s accuracy increased to 99%. 

“The pigeons were able to generalize what they had learned, so that when we showed them a completely new set of normal and cancerous digitized slides, they correctly identified them,” Levenson said.

The second experiment went very similar to the first. Four new birds were tested to determine if they could identify micro-calcifications – calcium deposits that are associated with the presence of cancer – in breast tissue. Their accuracy rate rose from 50% to over 85% in just 14 days.

According to the researchers, this task can also be quite difficult for humans. When a panel of radiologists were tested, they reached an 80% accuracy rate when viewing the same images.

Edward Wasserman, The Sacramento Bee: 

“These images have a lot to do with the edges of masses and how irregular they are, as well as the density of the masses. Identifying that is really tough to do. This is why people spend years perfecting the skill.”

The fact that a group of pigeons was able to hone this skill within 15 days to a 99% accuracy rate is incredible. The findings suggest that pigeons could be involved in helping scientists and engineers evaluate new medical imaging techniques in the future.

What are your thoughts? Comment below and share this news!

Source: TrueActivist

About Post Author

Professor Mike

Professor Mike is a left-leaning, dog loving, political junkie. He has written dozens of articles for Substack, Medium, Simily, and Tribel. Professor Mike has been published at Smerconish.com, among others. He is a strong proponent of the environment, and a passionate protector of animals. In addition he is a fierce anti-Trumper. Take a moment and share his work.
Happy
Happy
0 %
Sad
Sad
0 %
Excited
Excited
0 %
Sleepy
Sleepy
0 %
Angry
Angry
0 %
Surprise
Surprise
0 %
0 0 votes
Article Rating
Subscribe
Notify of

0 Comments
Inline Feedbacks
View all comments
Previous post Anonymous Claims Worldwide Terrorist Attacks, Including Paris and US, Set For Sunday
Next post Bill Maher Slams Liberals for Defending Islam: Muslims Do Not Always Share Western Values
0
Would love your thoughts, please comment.x
()
x