Artificial Intelligence for the Diagnosis of Pancreatic Diseases Using Endoscopic Ultrasonography
Digestive Endoscopy · 2026-06 · 38 (6)
DOI: 10.1111/den.70171 ↗Kurz gefasst
Übersichtsarbeit in der Zeitschrift Digestive Endoscopy, online erschienen am 02.06.2026. Verfasst von Takamichi Kuwahara und 12 weiteren Autor:innen. Beteiligte Einrichtung: Department of Gastroenterology, Aichi Cancer Center, Nagoya, Aichi, Japan. Hauptthemen laut MEDLINE: Artificial Intelligence, Endosonography, Pancreatic Diseases, Image Interpretation, Computer-Assisted. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 53 Literaturangaben. Gefördert von: Japan Society for the Promotion of Science.
Abstract (Originalsprache)
Artificial intelligence (AI) is rapidly being applied to medical imaging; however, the evidence base for endoscopic ultrasonography‐based AI (EUS‐AI) remains limited. We conducted a structured literature search (PubMed, Embase, and the Cochrane Library) for studies on AI for the diagnosis of pancreatic diseases using EUS images. Overall, 1 detection and 17 classifications of pancreatic tumors, 4 classifications of cystic lesions, and 4 focused on parenchymal or station recognition were reported in recent peer‐reviewed publications. Deep learning architectures, such as ResNet, EfficientNet, VGG, UNet++, YOLO, and custom convolutional networks, were utilized. Multimodal models combine imaging with clinical or cytological data. Reported accuracy ranged from 0.84 to 0.94; however, only a small number of studies performed external validation with enough data to confidently support their findings. Only one model has been approved in Japan with unpublished technical details. Significant challenges include limited data from single institutions, inconsistent case labeling, varying diagnostic criteria, and internal validation, which may overestimate the actual performance of the AI models. Future directions include establishing nationwide systems for collecting and sharing EUS images, applying large language models to assist in reporting and patient explanation, and exploring the use of AI to support or partially automate EUS procedures through integration with robotics. With the first commercial systems now appearing, continued innovation and rigorous validation are expected to accelerate the clinical usage of EUS‐AI.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Gastroenterology, Aichi Cancer Center, Nagoya, Aichi, Japan.
ORCID-Profile: Kazuo Hara, Shin Haba, Nozomi Okuno
Förderung
- Japan Society for the Promotion of Science
Zitieren
APA
Kuwahara, T., Hara, K., Mizuno, N., Haba, S., Okuno, N., Koda, H., Matsumoto, S., Oshiro, K., Ogata, T., Tanaka, T., Uba, Y., Yamazaki, Y., & Yamazoe, S. (2026). Artificial Intelligence for the Diagnosis of Pancreatic Diseases Using Endoscopic Ultrasonography. Digestive Endoscopy, 38(6). https://doi.org/10.1111/den.70171
Vancouver
Kuwahara T, Hara K, Mizuno N, Haba S, Okuno N, Koda H, et al. Artificial Intelligence for the Diagnosis of Pancreatic Diseases Using Endoscopic Ultrasonography. Digestive Endoscopy. 2026;38(6). doi:10.1111/den.70171
BibTeX
@article{Kuwahara2026,
author = {Kuwahara, Takamichi and Hara, Kazuo and Mizuno, Nobumasa and Haba, Shin and Okuno, Nozomi and Koda, Hiroki and Matsumoto, Shimpei and Oshiro, Keigo and Ogata, Tomoki and Tanaka, Tomoyuki and Uba, Yuki and Yamazaki, Yuma and Yamazoe, Saki},
title = {Artificial Intelligence for the Diagnosis of Pancreatic Diseases Using Endoscopic Ultrasonography},
journal = {Digestive Endoscopy},
year = {2026},
volume = {38},
number = {6},
doi = {10.1111/den.70171}
}
EUVIMED