pigeon
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.Univ. Iowa/Wassermann Lab

Researchers at the University of California have taught pigeons to identify breast cancer on X-rays with an accuracy of up to 99%. Richard Levenson, lead author of the study, said his team showed X-ray images of breast cancer tissues to pigeons which were then rewarded for correctly pecking a blue or yellow button that meant that the tissue was either cancerous or healthy.

The team spent an hour a day for 15 days teaching pigeons to correctly identify cancerous tissue. At the end of this period the birds achieved an 85% accuracy rate. When the team pooled responses from a group of four pigeons – which they described as 'flock sourcing' – the accuracy increased to 99%.

"With some training and selective food reinforcement, pigeons do just as well as humans in categorising digitised slides and mammograms of benign and malignant human breast tissue," said Levenson, professor of pathology and laboratory medicine at UC Davis Health System.

"The pigeons were able to generalise what they had learned, so that when we showed them a completely new set of normal and cancerous digitised slides, they correctly identified them," Levenson said. "Their accuracy, like that of humans, was modestly affected by the presence or absence of colour in the images, as well as by degrees of image compression.

However, one task the pigeons were unable to complete was recognising cancerous breast masses on mammograms.

"The pigeons also learned to correctly identify cancer-relevant microcalcifications on mammograms, but they had a tougher time classifying suspicious masses on mammograms -- a task that is extremely difficult, even for skilled human observers," said Levenson.

Human radiologists can only detect suspicious masses on mammograms with 80% accuracy, he added.

Levenson explains the point of the study, which was published in PLOS One: "While new technologies are constantly being designed to enhance image acquisition, processing, and display, these potential advances need to be validated using trained observers to monitor quality and reliability. This is a difficult, time-consuming, and expensive process that requires the recruitment of clinicians as subjects for these relatively mundane tasks.

"Pigeons' sensitivity to diagnostically salient features in medical images suggest that they can provide reliable feedback on many variables at play in the production, manipulation, and viewing of these diagnostically crucial tools, and can assist researchers and engineers as they continue to innovate."