AI Insight
Researchers developed GutCore, an AI model trained on 5.6 million endoscopic images, to analyze complete endoscopy examinations for gastric cancer assessment at the patient level. Testing on 11,035 endoscopic examinations, the model achieved high accuracy in detecting gastric cancer (AUC 0.995), assessing invasion depth (AUC 0.960 for deep muscle invasion), and predicting certain molecular biomarkers, while also stratifying patients into survival risk groups. The model processes all stored images from an examination without requiring manual selection of representative frames.
Why it matters
This approach could streamline gastric cancer diagnosis by automatically analyzing entire endoscopy videos rather than relying on clinicians to select key images, potentially improving detection accuracy and providing prognostic information. The ability to predict molecular biomarkers and survival outcomes directly from endoscopic images could guide treatment decisions more rapidly than waiting for tissue analysis.
Understand the Science
⚠️ Preprint – Noch nicht peer-reviewed
Dieser Artikel wurde noch nicht von unabhängigen Experten begutachtet. Die Ergebnisse sind vorläufig und sollten mit Vorsicht interpretiert werden.
Background and Aims: Endoscopic artificial intelligence is commonly validated on selected single images, whereas gastric cancer interpretation requires integrating whole examinations. We developed GutCore and evaluated whether whole-case endoscopic images could be used for patient-level assessment of gastric cancer depth, biomarkers, and prognosis. Methods: GutCore was pretrained on 5.6 million de-identified endoscopic images from more than ten hospitals. We compared it with five general, medical, and endoscopy-specific foundation models using open image-level datasets and an internal tertiary-center cohort of 11,035 de-identified endoscopic examinations (2019-2023): 8,049 with early or advanced gastric cancer and 2,986 with benign gastritis or intestinal metaplasia. All examination images were aggregated for patient-level assessment of cancer status, invasion depth, molecular biomarkers, and overall survival. Results: Aggregating all stored images from each examination enabled patient-level gastric cancer assessment without selecting representative frames. GutCore achieved AUCs of 0.995 for cancer detection, 0.960 for muscularis propria invasion, and 0.804 for SM2-or-deeper invasion. Prediction of tissue-defined biomarker status was strongest for Epstein-Barr virus status and MLH1 loss (AUC, 0.831 and 0.854), with lower HER2 performance (AUC, 0.673). In the held-out advanced gastric cancer test set, GutCore-derived risk groups showed marked survival separation (log-rank P < .0001; high-risk vs low-risk hazard ratio, 13.18; 95% CI, 6.06-28.66), with stratification persisting within pathological stage II and III disease. External frame-level benchmarks showed strong performance for anatomical landmark recognition, disease grading, and segmentation. Conclusions: GutCore supported whole-case patient-level gastric cancer assessment using routinely stored endoscopic images. Further validation in independent clinical cohorts is needed to establish generalizability and clinical utility.
Source: GutCore: An Endoscopy Foundation Model for Whole-Case Gastric Cancer Analysis