Multimodal artificial intelligence and large language models in gastrointestinal endoscopy: From lesion detection to workflow-integrated report generation
World Journal of Gastrointestinal Endoscopy · 16.11.2026 · 18 (11)
DOI: 10.4253/wjge.126153 ↗Kurz gefasst
Fachartikel in der Zeitschrift World Journal of Gastrointestinal Endoscopy, online erschienen am 16.11.2026. Verfasst von Hua-Wei He und 4 weiteren Autor:innen. Die Arbeit nennt 89 Literaturangaben.
Abstract (Originalsprache)
Artificial intelligence (AI) has rapidly transformed gastrointestinal (GI) endoscopy, with most early applications focusing on computer-aided detection and diagnosis of lesions from endoscopic images. However, real-world endoscopic practice extends beyond image interpretation. Endoscopists must integrate real-time video, anatomical location, lesion morphology, procedural context, histopathological findings, clinical history, and standardized terminology to make diagnostic decisions and generate clinically meaningful reports. Recent advances in multimodal AI and large language models (LLMs) provide an opportunity to move beyond isolated endoscopic image analysis toward more comprehensive endoscopic workflow support. By integrating visual, textual, temporal, and clinical information, these models can support lesion characterization, anatomical navigation, procedure quality assessment, structured documentation, report generation, and patient-centered communication. Nevertheless, clinical translation remains limited by scarce high-quality multimodal datasets, heterogeneous reporting standards, insufficient external validation, hallucination risk, limited interpretability, real-time integration challenges, privacy concerns, and evolving regulation. This review summarizes current applications of AI in GI endoscopy, with particular emphasis on the emerging role of multimodal learning and LLMs in bridging lesion detection, context-aware interpretation, and automated report generation. Furthermore, the article analyzes future challenges and the methodological, clinical, ethical, and regulatory requirements for the reliable integration of these systems into clinical endoscopic practice.
Zitieren
APA
He, H., Chan, I. N., Qin, Y., Yan, T., & Wong, P. K. (2026). Multimodal artificial intelligence and large language models in gastrointestinal endoscopy: From lesion detection to workflow-integrated report generation. World Journal of Gastrointestinal Endoscopy, 18(11). https://doi.org/10.4253/wjge.126153
Vancouver
He H, Chan IN, Qin Y, Yan T, Wong PK. Multimodal artificial intelligence and large language models in gastrointestinal endoscopy: From lesion detection to workflow-integrated report generation. World Journal of Gastrointestinal Endoscopy. 2026;18(11). doi:10.4253/wjge.126153
BibTeX
@article{He2026,
author = {He, Hua-Wei and Chan, In Neng and Qin, Ye-Ying and Yan, Tao and Wong, Pak Kin},
title = {Multimodal artificial intelligence and large language models in gastrointestinal endoscopy: From lesion detection to workflow-integrated report generation},
journal = {World Journal of Gastrointestinal Endoscopy},
year = {2026},
volume = {18},
number = {11},
doi = {10.4253/wjge.126153}
}
EUVIMED