{"slug": "researchers-use-pigeons-to-train-cancer-detection-ai", "title": "Researchers Use Pigeons To Train Cancer-Detection AI", "summary": "Researchers at the College of the Holy Cross trained six pigeons to detect lung nodules in CT scans, with the birds generalizing to unseen scans and identifying other abnormalities like emphysema. The study, published in Animal Cognition, aims to use animal visual signals to improve AI training for medical imaging, potentially supplementing scarce clinical labels.", "body_md": "### What happened\n\nAccording to reporting by Popular Science and Economic Times, and the peer-reviewed paper in **Animal Cognition** (Springer, February 2026), **Dr. Gregory DiGirolamo** of the **College of the Holy Cross** led a study in which **six pigeons** were trained to watch short **CT scan** videos and indicate whether a lung nodule was present. Economic Times reports that some birds received food rewards for correctly identifying scans with nodules, while others were rewarded for correctly recognising normal scans, and the pigeons were able to generalize to previously unseen scans. Economic Times reports the birds also detected other lung abnormalities, including **emphysema** and **ground-glass nodules**.\n\n### What the prior human research found\n\nPopular Science reports that in **2025** DiGirolamo and colleagues published an eye-tracking study showing that radiologists often fixate on suspicious lung nodules and exhibit pupil dilation even when they later mark a scan as normal. Popular Science frames the pigeon experiments as a way to study that nonconscious visual signal without human conscious decision processes interfering.\n\n### Technical context\n\nStudies that use nonhuman visual systems to probe perception provide alternative supervisory signals that differ from explicit human labels. For practitioners: animal vision can offer examples of invariances, salience, and pattern recognition not captured by standard labeled datasets, and those signals can be encoded as auxiliary training targets, attention priors, or contrastive tasks when developing medical imaging models.\n\n### Context and significance\n\nObservers place this work at the intersection of perceptual science and model training. For practitioners: leveraging behavioral readouts such as fixation patterns, reward-conditioned responses, or other proxy labels can supplement scarce clinical labels and help surface subtle features that standard annotation workflows miss. This is especially relevant in medical imaging where early-stage abnormalities are rare and hard to label consistently.\n\n### What to watch\n\nwhether signals derived from pigeon behavior can be translated into reproducible algorithmic training signals, whether such signals improve clinical metrics like sensitivity at fixed specificity, and whether methods are validated on larger clinical datasets. Observers will watch for peer-reviewed follow-on work and methodological details specifying how animal-derived signals are converted into model objectives. Popular Science reports DiGirolamo plans to use eye gaze-tracking and physiology data (such as pupil widening) to capture how radiologists respond to subtle abnormalities and feed those patterns into AI models.\n\n## Scoring Rationale\n\nThis is an intriguing research result that could influence training signals and data augmentation for medical imaging models, but it is early-stage and requires clinical validation, so its immediate impact on practitioners is moderate.\n\nPractice with real Ad Tech data\n\n90 SQL & Python problems · 15 industry datasets\n\n[Active Search Campaigns by BudgetEasy](/problems/sql/active-search-campaigns-by-budget)\n\n[High CPC Clicks & Poor Landing PagesMedium](/problems/sql/high-cpc-clicks-poor-landing-page)\n\n[Campaign ROAS by Attribution ModelHard](/problems/sql/campaign-roas-by-attribution-model)\n\n250 free problems · No credit card\n\n[See all Ad Tech problems](/problems/datasets/adtech)", "url": "https://wpnews.pro/news/researchers-use-pigeons-to-train-cancer-detection-ai", "canonical_source": "https://letsdatascience.com/news/researchers-use-pigeons-to-train-cancer-detection-ai-5a79bc8e", "published_at": "2026-06-25 02:46:17.909484+00:00", "updated_at": "2026-06-25 02:46:20.100608+00:00", "lang": "en", "topics": ["artificial-intelligence", "computer-vision", "ai-research", "ai-products", "ai-ethics"], "entities": ["College of the Holy Cross", "Dr. Gregory DiGirolamo", "Popular Science", "Economic Times", "Animal Cognition", "Springer"], "alternates": {"html": "https://wpnews.pro/news/researchers-use-pigeons-to-train-cancer-detection-ai", "markdown": "https://wpnews.pro/news/researchers-use-pigeons-to-train-cancer-detection-ai.md", "text": "https://wpnews.pro/news/researchers-use-pigeons-to-train-cancer-detection-ai.txt", "jsonld": "https://wpnews.pro/news/researchers-use-pigeons-to-train-cancer-detection-ai.jsonld"}}