Using Pigeons to Diagnose Cancer

Research reveals surprising visual sophistication

pigeon

The pigeons' training environment included a food pellet dispenser, a touch-sensitive screen which projected the medical image, as well as blue and yellow choice buttons on either side of the image. Pecks to those buttons and to the screen were automatically recorded

Credit: Copyright Univ. Iowa/Wassermann Lab

Brazilian folk tradition holds that if your asthma is acting up, you might consider sharing dinner with a bird.

Feeding leftovers to a white-naped jay in particular is thought by some healers to transfer the illness to unsuspecting avians. If that doesn’t work, the roasted, powdered liver of the black vulture also apparently helps open restricted airways.

Birds and certain bird bits — their beaks, their feathers, their livers — are involved in traditional remedies throughout the world, practices that trace back to Mesopotamia, Ancient Egypt and early China. It turns out birds may play a helpful role in modern western medicine too. A new study suggests that the common pigeon can reliably distinguish between benign versus malignant tumors and, in doing so, could help researchers develop better cancer screening technologies.


On supporting science journalism

If you're enjoying this article, consider supporting our award-winning journalism by subscribing. By purchasing a subscription you are helping to ensure the future of impactful stories about the discoveries and ideas shaping our world today.


Diagnosing cancer has a lot to do with vision. Pathologists study biopsy samples looking for cancerous cells. Radiologists scan x-rays and MRIs for possible malignancies. The authors of the new study were curious how these specialists acquire the skill to identify features and qualities of an image that signify cancer. To find out they turned to pigeons. Though primates and pigeons haven't shared a common ancestor for over 300 million years (it looked something like this) our visual processing biology is surprisingly similar to that of birds.

In the study, 16 pigeons were trained to detect cancer by putting them in a roomy chamber where magnified biopsies of possible breast cancers were displayed. Correctly identifying a growth as benign or malignant by pecking one of two answer buttons on a touchscreen earned them a tasty 45 milligram pigeon pellet. Once trained, the pigeons’ average diagnostic accuracy reached an impressive 85 percent. But when a “flock sourcing” approach was taken, in which the most common answer among all subjects was used, group accuracy climbed to a staggering 99 percent, or what would be expected from a pathologist. The pigeons were also able to apply their knowledge to novel images, showing the findings weren’t simply a result of rote memorization.

Credit: Univ. Iowa/Wassermann Lab

Analyzing mammograms proved more difficult for the birds, though they still proved themselves proficient radiologists. Even when presented with new images, they identified tiny accumulations of calcium that often indicate breast cancer with similar accuracy to the pathology images. However, though they could memorize suspicious tissue densities that can signal cancer, they were stumped when doing so on previously unseen mammograms.

“The birds might be able to assess the quality of new imaging techniques or methods of processing and displaying images without forcing humans to spend hours or days doing detailed comparisons to figure out if certain innovations are in fact better or worse than current methods,” said study co-author Dr. Richard M. Levenson, a professor in the Department of Pathology at the University of California Davis. Doing so would avoid the need to recruit and pay clinicians for these mundane, repetitive tasks.

Dr. Levenson cautions against expecting pigeon physicians any time soon: “I don’t anticipate that pigeons, no matter how good they become at pathology or radiology, will be playing a role in actual patient care—certainly for the foreseeable future. There are just too many regulatory barriers—at least in the West.” But he does believe the findings could help develop more effective training methods for budding clinicians.

Pigeon vision isn't as sharp as that of majestic raptors like eagles, hawks and falcons — birds of prey can spot the scurry of a field mouse from 1000 feet. But they’re easy to house and at least 50 years of research has confirmed that despite their commonplace reputation — puttering scavengers in search of a mishandled bagel — pigeons have plenty going on in their tiny bird brains, visually anyway. As the authors point out, pigeons can learn to recognize letters of the alphabet; identify objects like cats, cars and chairs; and distinguish between Monet and Picasso paintings. In all they can learn and remember nearly 2,000 images and even pick up on facial expressions indicating human emotions.

Levenson speculates that pigeons could contribute to technical image analysis in various fields, gauging qualities like brightness, contrast and compression. “Maybe the pigeons could determine if doing x,y, or z to an image makes it easier or harder to see a target of interest,” he commented, suggesting that beyond just practicing medicine the birds could assist with various remote surveillance operations, military and otherwise. Unlike, say, cancer-sniffing dogs, pigeons may not be ready for the clinic, but one could envision numerous ways to exploit their image-analysis talents.

Perhaps, given their eye for Impressionism, they might even find work in art restoration.

Are you a scientist who specializes in neuroscience, cognitive science, or psychology? And have you read a recent peer-reviewed paper that you would like to write about? Please send suggestions to Mind Matters editor Gareth Cook. Gareth, a Pulitzer prize-winning journalist, is the series editor of Best American Infographics and can be reached at garethideas AT gmail.com or Twitter 

@garethideas.

Bret Stetka was a writer based in New York City and editorial director of Medscape Neurology (a subsidiary of WebMD). His work appeared in Wired, NPR and the Atlantic. He graduated from the University of Virginia School of Medicine in 2005. Stetka died in 2022.

More by Bret Stetka

It’s Time to Stand Up for Science

If you enjoyed this article, I’d like to ask for your support. Scientific American has served as an advocate for science and industry for 180 years, and right now may be the most critical moment in that two-century history.

I’ve been a Scientific American subscriber since I was 12 years old, and it helped shape the way I look at the world. SciAm always educates and delights me, and inspires a sense of awe for our vast, beautiful universe. I hope it does that for you, too.

If you subscribe to Scientific American, you help ensure that our coverage is centered on meaningful research and discovery; that we have the resources to report on the decisions that threaten labs across the U.S.; and that we support both budding and working scientists at a time when the value of science itself too often goes unrecognized.

In return, you get essential news, captivating podcasts, brilliant infographics, can't-miss newsletters, must-watch videos, challenging games, and the science world's best writing and reporting. You can even gift someone a subscription.

There has never been a more important time for us to stand up and show why science matters. I hope you’ll support us in that mission.

Thank you,

David M. Ewalt, Editor in Chief, Scientific American

Subscribe