One-shot synthesis of rare gastrointestinal lesions improves diagnostic accuracy and clinical training
This addresses the rare-disease gap in computer-aided diagnostics and clinical education for gastrointestinal endoscopy, offering a data-efficient solution.
The paper tackled the problem of limited data for rare gastrointestinal lesions by developing EndoRare, a one-shot generative framework that synthesizes diverse, high-fidelity lesion images from a single reference, which improved AI classifier performance and increased novice endoscopists' recall by 0.400 and precision by 0.267.
Rare gastrointestinal lesions are infrequently encountered in routine endoscopy, restricting the data available for developing reliable artificial intelligence (AI) models and training novice clinicians. Here we present EndoRare, a one-shot, retraining-free generative framework that synthesizes diverse, high-fidelity lesion exemplars from a single reference image. By leveraging language-guided concept disentanglement, EndoRare separates pathognomonic lesion features from non-diagnostic attributes, encoding the former into a learnable prototype embedding while varying the latter to ensure diversity. We validated the framework across four rare pathologies (calcifying fibrous tumor, juvenile polyposis syndrome, familial adenomatous polyposis, and Peutz-Jeghers syndrome). Synthetic images were judged clinically plausible by experts and, when used for data augmentation, significantly enhanced downstream AI classifiers, improving the true positive rate at low false-positive rates. Crucially, a blinded reader study demonstrated that novice endoscopists exposed to EndoRare-generated cases achieved a 0.400 increase in recall and a 0.267 increase in precision. These results establish a practical, data-efficient pathway to bridge the rare-disease gap in both computer-aided diagnostics and clinical education.