Artificial Intelligence in Endoscopic Ultrasonography for Gastrointestinal Subepithelial Lesions: Evidence, Validation, and Clinical Translation
8 affiliations
- 1Department of Medicine, Surgery and Pharmacy, University of Sassari, 07100 Sassari, Italy
- 2IHU-Strasbourg, Institute of Image-Guided Surgery, Université de Strasbourg, 67000 Strasbourg, France
- 3Gastroenterology and Digestive Endoscopy Unit, Azienda Sanitaria Universitaria Integrata del Trentino (ASUIT), 38122 Trento, Italy
- 4Unit of Gastroenterology, Ospedale Maggiore Della Carità di Novara, 28100 Novara, Italy
- 5Gastroenterology and Endoscopy Department, Koelliker Hospital, 10134 Torino, Italy
- 6Department of Gastroenterology and Hepatology, CHU UCL Namur, Université Catholique de Louvain, 5530 Yvoir, Belgium
- 7Institute for Translational Medicine and Liver Disease, ITM, UMRS_1110, Université de Strasbourg, 67000 Strasbourg, France
- 8Department of Gastroenterology and Hepatology, Hôpitaux Universitaires de Strasbourg, Université de Strasbourg, 67000 Strasbourg, France
Abstract
Artificial intelligence is increasingly being applied to endoscopic ultrasonography for gastrointestinal subepithelial lesions, but the maturity of the evidence differs substantially across clinical tasks. This narrative review critically appraises contemporary studies of lesion detection and localization, wall-layer identification, diagnostic classification, pathological risk classification of gastrointestinal stromal tumors, human–artificial intelligence interaction, and potential management support. Thirty-one original studies published from 2021 through 2026 were included in the contemporary evidence map. Binary differentiation of gastrointestinal stromal tumors from leiomyomas or other selected comparators has the largest evidence base and includes multicenter, external, prospective, and real-time evaluations. Evidence for multiclass diagnosis, layer-of-origin assessment, small lesions, and pathological risk classification is less mature and is strongly influenced by case spectrum, reference standard, equipment, image selection, and validation design. No study has demonstrated that artificial intelligence improves tissue-acquisition strategy, surveillance, treatment selection, or patient outcomes in subepithelial lesions. Progress toward clinically useful decision support will require patient-level data separation, device- and center-held-out validation, analysis of complete examinations rather than curated images, explicit uncertainty handling, prospective human–artificial intelligence studies, and trials with endoscopy-specific management and safety outcomes.
Related
- Artificial intelligence-based tongue image analysis for non-invasive screening of gastric cancer, precancerous lesions, and related gastrointestinal disorders: a systematic review
- Bridging the Artificial Intelligence Translation Gap in Perioperative Pulmonary and Respiratory Complications: A Practical Framework for Institution-Level Implementation
- Circulating Biomarkers with Artificial Intelligence for Clinical Risk Assessment and Therapeutic Monitoring: Evidence, Limitations, and Translation
- Artificial intelligence across the gastric cancer care continuum: Clinical evidence, multimodal integration, and translation
- Artificial Intelligence in Pancreatic Cancer: From Predictive Performance to Clinical Translation
BibTeX
@article{merola2026artificial,
title = {{Artificial Intelligence in Endoscopic Ultrasonography for Gastrointestinal Subepithelial Lesions: Evidence, Validation, and Clinical Translation}},
author = {Elettra Merola and Leonardo Sosa-Valencia and Andrea Michielan and Nico Pagano and Maria Pina Dore and Claudio De Angelis and Abdenor Badaoui},
journal = {Journal of Clinical Medicine},
year = {2026},
month = oct,
doi = {10.3390/jcm15218440},
url = {https://www.mdpi.com/2077-0383/15/21/8440},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Artificial Intelligence in Endoscopic Ultrasonography for Gastrointestinal Subepithelial Lesions: Evidence, Validation, and Clinical Translation
AU - Elettra Merola
AU - Leonardo Sosa-Valencia
AU - Andrea Michielan
AU - Nico Pagano
AU - Maria Pina Dore
AU - Claudio De Angelis
AU - Abdenor Badaoui
PY - 2026
DA - 2026/10/30
JO - Journal of Clinical Medicine
DO - 10.3390/jcm15218440
UR - https://www.mdpi.com/2077-0383/15/21/8440
AB - Artificial intelligence is increasingly being applied to endoscopic ultrasonography for gastrointestinal subepithelial lesions, but the maturity of the evidence differs substantially across clinical tasks. This narrative review critically appraises contemporary studies of lesion detection and localization, wall-layer identification, diagnostic classification, pathological risk classification of gastrointestinal stromal tumors, human–artificial intelligence interaction, and potential management support. Thirty-one original studies published from 2021 through 2026 were included in the contemporary evidence map. Binary differentiation of gastrointestinal stromal tumors from leiomyomas or other selected comparators has the largest evidence base and includes multicenter, external, prospective, and real-time evaluations. Evidence for multiclass diagnosis, layer-of-origin assessment, small lesions, and pathological risk classification is less mature and is strongly influenced by case spectrum, reference standard, equipment, image selection, and validation design. No study has demonstrated that artificial intelligence improves tissue-acquisition strategy, surveillance, treatment selection, or patient outcomes in subepithelial lesions. Progress toward clinically useful decision support will require patient-level data separation, device- and center-held-out validation, analysis of complete examinations rather than curated images, explicit uncertainty handling, prospective human–artificial intelligence studies, and trials with endoscopy-specific management and safety outcomes.
SN - 2077-0383
ER -