The researchers conducted experiments with pigeons, in which first experiment involved a cohort of eight pigeons, second and third each included four pigeons.

During the experiment one, researchers trained four pigeons with normal images and the other four with hue and brightness-balanced monochrome images.

In the experiments two and three, all of the training images have been same type for each of the four birds.

All the pigeons were housed in individual cages, with ad-lib access to grit and water. They were maintained at 85% of their free-feeding weights by controlled daily rations.

For counterbalancing purposes, the pigeons in each quartet have been divided into two groups based on which subset of slides they were given during training.

In the experiment one, a total of 144 images, including 48 at each of three magnification settings, taken from breast tissue samples were used.

Each magnification grouping has been separated into two sets, including 12 benign and 12 malignant tissue examples (yielding Sets A and B, respectively, for a total of 48 images). Group one was trained with Set A and tested with Set B, while the opposite occurred for Group two.

According to researchers, results from full color image training and testing established that pigeons could adeptly discriminate malignant from benign breast histological samples at multiple levels of magnification, in different spatial orientations, and effectively transfer those discriminations to novel stimuli.

Image: The pigeons’ training environment. Photo: courtesy of Levenson et al.