Search papers, labs, and topics across Lattice.
This paper introduces RATNet, a foundation model for gastrointestinal endoscopy imaging that leverages analogical reasoning for improved diagnosis. RATNet is pre-trained using a cyclic strategy across five datasets with heterogeneous annotations, enabling knowledge transfer between them. Experiments demonstrate that RATNet outperforms existing foundation models in various scenarios, including few-shot learning, zero-shot transfer, and robustness to long-tailed distributions, highlighting the effectiveness of analogical reasoning for generalization in medical image analysis.
Analogical reasoning lets a single foundation model diagnose diverse gastrointestinal diseases, even with limited data, outperforming specialized models in generalization and robustness.
Gastrointestinal diseases impose a growing global health burden, and endoscopy is a primary tool for early diagnosis. However, routine endoscopic image interpretation still suffers from missed lesions and limited efficiency. Although AI-assisted diagnosis has shown promise, existing models often lack generalizability, adaptability, robustness, and scalability because of limited medical data, domain shift, and heterogeneous annotations. To address these challenges, we develop RATNet, a foundation model for gastrointestinal endoscopy imaging based on analogical reasoning. RATNet acquires and transfers knowledge from heterogeneous expert annotations across five gastrointestinal endoscopy datasets through a cyclic pre-training strategy. Its architecture consists of an encoder, a relevance-knowledge acquisition and transfer (RAT) module, a projector, and a multi-task head, and supports fine-tuning, linear probing, and zero-shot transfer. Evaluations show that RATNet outperforms existing foundation models, including GastroNet and GastroVision, across six scenarios: diagnosis of common gastrointestinal diseases, few-shot learning for rare diseases, zero-shot transfer to new medical sites, robustness under long-tailed disease distributions, adaptation to novel diseases, and privacy-preserving deployment via federated learning. Its advantage comes from an analogical reasoning mechanism that matches image-derived posterior knowledge to a learned prior knowledge base and transfers relative knowledge to guide diagnosis, improving generalization and resistance to bias. RATNet is open and cost-effective, supports automatic integration of heterogeneous annotations without manual label unification, and reduces data acquisition costs, making it a practical foundation for intelligent gastrointestinal diagnosis, especially in resource-limited settings.