Development and Validation of a Multimodal Deep Learning Model for Early Esophageal Squamous Neoplasia Detection and Invasion Depth Prediction
Endoscopy · 01.05.2026 · 58 (05) · 467-480
DOI: 10.1055/a-2780-0974 ↗Kurz gefasst
Validierungsstudie in der Zeitschrift Endoscopy, erschienen am 01.05.2026. Verfasst von Chu-Ting Yu und 13 weiteren Autor:innen. Beteiligte Einrichtung: Gastroenterology, Changhai Hospital, Shanghai, China. Hauptthemen laut MEDLINE: Esophageal Neoplasms, Deep Learning, Esophageal Squamous Cell Carcinoma, Endosonography. Gefördert von: China University Industry-Research Innovation Fund - Huaton Medical Research Special Program, Grants from ShanghaiMunicipal Health Commission Fund.
Abstract (Originalsprache)
Introduction
Early detection of esophageal squamous cell carcinoma (ESCC) is critical for optimizing patient outcomes. Magnifying endoscopy (ME) and endoscopic ultrasonography (EUS) serve as established diagnostic modalities. MUMA-EDx (Multimodal Ultrasound & Magnifying-endoscopic Algorithm for Early ESCC Diagnostics) integrates deep learning-based ME and EUS imaging to improve early-stage ESCC identification and invasion depth assessment.
Methods
Model development and internal validation utilized the retrospective dataset, while the prospective cohort served for external validation. MUMA-EDx developed two TResNet_m-based classifiers (ME/EUS) followed by feature-level fusion. Model performance was evaluated using area under the receiver operating characteristic curve (AUC-ROC), accuracy, sensitivity, specificity, positive predictive value, and negative predictive value.
Results
MUMA-EDx was developed and validated using a retrospective dataset comprising 460 patients (20,889 images) and subsequently tested prospectively on an independent cohort of 131 patients (9,124 images). The feature-level multimodal approach significantly outperformed single-modality models. For tumor discrimination, the model achieved an AUC of 0.94 (95% CI: 0.92-0.96) in retrospective validation and a perfect patient-level AUC of 1.00 (95% CI: 1.00-1.00) in prospective testing. For the more complex task of multiclass invasion depth classification, it achieved a retrospective AUC of 0.95 (95% CI: 0.88-0.99), which remained strong at 0.80 (95% CI: 0.67-0.87) in the prospective cohort. In a comparative study on invasion depth classification, MUMA-EDx's performance exceeded that of novice endoscopists and was comparable to expert-level diagnostics.
Conclusion
MUMA-EDx demonstrably delivers exceptional early ESCC detection and robust invasion depth classification, achieving performance comparable to expert endoscopists and poised to significantly enhance diagnostic precision and patient outcomes.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Gastroenterology, Changhai Hospital, Shanghai, China.
- National Clinical Research Center for Digestive Diseases (Shanghai), Shanghai, China.
- Gastroenterology, West China Hospital of Sichuan University, Chengdu, China.
- Gastroenterology, Shandong Provincial Hospital Affiliated to Shandong First Medical University, Jinan, China.
- Gastroenterology, The First Affiliated Hospital of Henan University of Science and Technology, Luoyang, China.
- Gastroenterology, First Affiliated Hospital of Shihezi University School of Medicine, Shihezi, China.
ORCID-Profile: Chu-Ting Yu, Zhi-Han Wu, Hong-Wei Xu
Förderung
- China University Industry-Research Innovation Fund - Huaton Medical Research Special Program
- Grants from ShanghaiMunicipal Health Commission Fund
Zitieren
APA
Yu, C. T., Wang, T. L., Gao, Y., Wu, Z. H., Chen, Y. Z., Shi, L., Liu, B., Zhang, H., Xu, H. W., Chen, W. G., Gao, S. G., Yang, J. L., Wang, L. W., & Lin, H. (2026). Development and Validation of a Multimodal Deep Learning Model for Early Esophageal Squamous Neoplasia Detection and Invasion Depth Prediction. Endoscopy, 58(05), 467-480. https://doi.org/10.1055/a-2780-0974
Vancouver
Yu CT, Wang TL, Gao Y, Wu ZH, Chen YZ, Shi L, et al. Development and Validation of a Multimodal Deep Learning Model for Early Esophageal Squamous Neoplasia Detection and Invasion Depth Prediction. Endoscopy. 2026;58(05):467-480. doi:10.1055/a-2780-0974
BibTeX
@article{Yu2026,
author = {Yu, Chu-Ting and Wang, Ting-Lu and Gao, Ye and Wu, Zhi-Han and Chen, Ying-Zhou and Shi, Lei and Liu, Biao and Zhang, Hui and Xu, Hong-Wei and Chen, Wei-Gang and Gao, She-Gan and Yang, Jin-Lin and Wang, Luo-Wei and Lin, Han},
title = {Development and Validation of a Multimodal Deep Learning Model for Early Esophageal Squamous Neoplasia Detection and Invasion Depth Prediction},
journal = {Endoscopy},
year = {2026},
volume = {58},
number = {05},
pages = {467--480},
doi = {10.1055/a-2780-0974}
}
EUVIMED