Pigeons Can Spot Breast Cancer with Training
Pigeons have a long history of collaborating with humans. From being messengers to working with magicians, it seems these birds can be trained to do a lot.
Now, a team of researchers has trained pigeons to identify breast cancer, and they report that the birds did just as well as humans. How fascinating.
RELATED: BIRDS MAY ACTUALLY SEE EARTH’S MAGNETIC FIELDS THANKS TO PROTEINS IN THEIR EYES
"Pigeons can distinguish identities and emotional expressions on human faces, letters of the alphabet, misshapen pharmaceutical capsules, and even paintings by Monet vs Picasso," Prof Edward Wasserman from the University of Iowa, a co-author of the study, told the BBC.
"Their visual memory capacity is equally impressive, with a proven recall of more than 1,800 images."
The researchers trained the pigeons to distinguish microscope images of cancerous and non-cancerous tissue. The pigeons were able to correctly identify tumors in unseen microscope images and performed well at particular mammogram-classifying tasks.
They used a rewards system where the birds were given food pellets every time they guessed cancer correctly. The training was so effective that pigeons could even recognize tumors in the absence of color.
85% accuracy
The whole ordeal took two weeks to implement and resulted in the pigeons reaching an impressive level of 85% accuracy.
"The birds were remarkably adept at discriminating between benign and malignant breast cancer slides," told BBC lead author Prof Richard Levenson, from the University of California, Davis.
There was one drawback. The birds were bad at classifying suspicious masses.
"As this task reflects the difficulty even humans have, it indicates how pigeons may be faithful mimics of the strengths and weaknesses of humans in viewing medical images," Levenson told the BBC.
The pigeons could soon prove useful in developing imaging-based cancer diagnostic tools.
Whatever the outcome, it is quite surprising to see how intelligent these birds are. And of course, any technique that can help in cancer diagnosis is always welcome.