Pigeons can detect breast cancer with 99% accuracy: study
21 Nov 2015
Pigeons can distinguish between healthy and cancerous tissue in x-rays and microscope slides with an accuracy rate of up to 99 per cent, a new study in Plos One has reported.
In a series of three experiments, led by Richard Levenson, professor of pathology and laboratory medicine at the University of California Davis Medical Center, it was found that pigeons had the capacity to learn how to identify whether an image showed healthy or cancerous breast tissue.
According to the study, the birds ''share many visual system properties with humans''.
In the first experiment, eight pigeons were presented with 144 breast tissue images, at various levels of magnification and with and without colour.
To differentiate between the healthy and diseased tissue images, the birds could peck a blue or yellow button on either side of each image.
The birds were rewarded with food if they chose correctly, but were repeatedly presented the images until they correctly identified it if they chose wrongly.
''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,'' Levenson told the International Business Times.
The study was aimed at understanding how physicians developed medically essential visual skills for diagnosis, and how they processed visual cues.
Pigeons were chosen as their visual system properties resembled that of humans.
"The birds were remarkably adept at discriminating between benign and malignant breast cancer slides at all magnifications, a task that can perplex inexperienced human observers, who typically require considerable training to attain mastery," said Levenson.
"Pigeons' accuracy from day one of training at low magnification increased from 50 per cent correct to nearly 85 per cent correct at days 13 to 15."
According to the authors, the study's results suggested the birds "could be used as suitable surrogates for human observers in certain medical image perception studies, thus avoiding the need to recruit, pay, and retain clinicians as subjects for relatively mundane tasks".