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

TL;DR

EndoRare is a novel one-shot generative framework that synthesizes diverse, high-fidelity images of rare gastrointestinal lesions from a single reference, enhancing AI diagnostic models and clinical training.

Contribution

The paper introduces EndoRare, a new language-guided, one-shot generative model that creates diverse, high-quality images of rare lesions without retraining, aiding diagnostics and education.

Findings

Synthetic images are clinically plausible and improve AI classifier performance.

Augmentation with generated images increases diagnostic recall and precision.

The framework effectively models multiple rare pathologies with limited data.

Abstract

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.