An animal model of radiological medical image reading: detection of lung abnormalities in multi-slice CT by pigeons (Columba livia)
Pigeons learned to find lung tumors in CT scans, proving that steady reinforcement and novel examples can train sharp visual discrimination even in a non-human.
01Research in Context
What this study did
Scientists trained pigeons to spot lung nodules in CT scans.
The birds learned a go/no-go task: peck when the scan shows a nodule, hold still when it looks normal.
Training used food rewards for correct choices.
What they found
Every pigeon learned to tell abnormal from normal scans.
The birds still pecked correctly when brand-new scans appeared, proving they had learned the rule, not just memorized pictures.
How this fits with other research
Garcia (1974) first showed pigeons can sort photos that contain "man-made stuff" from photos that do not. Qadri et al. (2026) push the same idea into medicine, proving the method works even with tricky hospital images.
Vyazovska et al. (2016) used the same go/no-go setup with colored shapes. Both studies got clean discrimination, so the procedure is solid across very different picture sets.
Lancioni et al. (2006) warn that pigeons sometimes pick the wrong cue. Qadri’s team avoided this trap: the birds still chose correctly when new nodule sizes and locations appeared, showing real lung-feature control, not a lucky shortcut.
Why it matters
If pigeons can learn to see cancer signs, the task is teachable. Use their training steps—clear yes/no pictures, instant food, many novel examples—when you teach human aides to read graphs or spot problem behavior on video. Break visual tasks into tiny, reinforced choices and keep testing with new samples; mastery will generalize just like it did for the birds.
Want CEUs on This Topic?
The ABA Clubhouse has 60+ free CEUs — live every Wednesday. Ethics, supervision & clinical topics.
Join Free →Pick one visual target your team must spot (e.g., off-task behavior), gather 20 pictures, and run a rapid yes/no game with instant praise for each correct response.
02At a glance
03Original abstract
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. The online version contains supplementary material available at 10.1007/s10071-026-02048-2.
Animal Cognition, 2026 · doi:10.1007/s10071-026-02048-2