Work

One-shot synthesis of rare gastrointestinal lesions improves diagnostic accuracy and clinical training

Year: 2026

Type: article

Abstract: Rare gastrointestinal lesions are infrequently encountered in routine endoscopy, limiting data 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 lesion exemplars from a single reference image. Using 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 validate EndoRare across four rare pathologies: calcifying fibrous tumor, juvenile polyposis syndrome, familial adenomatous polyposis, and Peutz-Jeghers syndrome. Experts judge the synthetic images clinically plausible, and data augmentation significantly improves downstream AI classifiers, increasing true positive rates at low false-positive rates. In an exploratory reader study, exposure to EndoRare-generated cases is associated with improved image-level recognition by novice endoscopists. These findings support the potential use of EndoRare as a data-efficient tool for rare-lesion education and motivate prospective controlled validation.

Source: Nature Communications

DOI: 10.1038/s41467-026-78492-y