An animal model of radiological medical image reading: detection of lung abnormalities in multi-slice CT by pigeons (Columba livia).

Accurate detection of pathologies like pulmonary lung nodules is critical as they can be a marker of a potential cancerous, life-threatening condition. The detection of such nodules, however, is a difficult visual task requiring extensive radiological training. But, considering this process as a perceptual categorization task generates avenues for using pigeons to understand the underlying visual processes as these birds are experts at categorizing objects and behaviors visually, using a highly flexible and accurate visual cognition. Using a go/no-go paradigm, we presented six pigeons with short movies of CT sections that contained a solid lung nodule (Abnormal) or CT sections without nodules (Normal). Half the pigeons were reinforced for pecking during Abnormal, and the other half during Normal. Pigeons learned to detect the nodules and generalized their discrimination to novel exemplars, indicating the use of implicit visual categorization processes. Critically, this categorization transferred to different, visually distinct abnormalities (emphysema and ground glass nodules). Hence, pigeons can be employed as an animal model for evaluating perceptual processes during abnormality detection and may give insight into novel radiological training optimized by pigeons’ implicit visual cognitive mechanisms instead of explicit didactic instruction.