Download PDF
Endoscopy
DOI: 10.1055/a-2780-0974
Original article

Development and Validation of a Multimodal Deep Learning Model for Early Esophageal Squamous Neoplasia Detection and Invasion Depth Prediction

Authors

  • Chuting Yu 

    1   Department of Gastroenterology, Changhai Hospital, Shanghai, China (Ringgold ID: RIN12520)

  • Ting-Lu Wang

    1   Department of Gastroenterology, Changhai Hospital, Shanghai, China (Ringgold ID: RIN12520)

  • Ye Gao

    1   Department of Gastroenterology, Changhai Hospital, Shanghai, China (Ringgold ID: RIN12520)

  • Zhihan Wu 

    2   Department of Gastroenterology and Hepatology, West China Hospital of Sichuan University, Chengdu, China (Ringgold ID: RIN34753)
    3   Sichuan University-University of Oxford Huaxi Joint Centre for Gastrointestinal Cancer, West China Hospital of Sichuan University, Chengdu, China (Ringgold ID: RIN34753)

  • Ying-Zhou Chen

    2   Department of Gastroenterology and Hepatology, West China Hospital of Sichuan University, Chengdu, China (Ringgold ID: RIN34753)

  • Lei Shi

    4   Endoscopy, National Cancer Center,Cancer Institute and Hospital, Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing, China

  • Biao Liu

    5   Department of Gastroenterology, Shandong Provincial Hospital Affiliated to Shandong First Medical University, Jinan, China (Ringgold ID: RIN34708)

  • Hui Zhang

    6   Department of Digestive, First Affiliated Hospital of Shihezi University School of Medicine, Shihezi, China (Ringgold ID: RIN604058)

  • Hongwei Xu 

    7   Department of Gastroenterology, Shandong Provincial Hospital affiliated to Shandong First Medical University, Jinan, China

  • Wei-Gang Chen

    6   Department of Digestive, First Affiliated Hospital of Shihezi University School of Medicine, Shihezi, China (Ringgold ID: RIN604058)

  • Shegan Gao

    8   Cancer Centre, First Affiliated Hospital of Henan Science & Technology University, Luoyang, China

  • Jinlin Yang

    9   Gastroenterology Department, Sichuan University West China Hospital, Chengdu, China (Ringgold ID: RIN34753)

  • Luowei Wang

    10   Department of Gastroenterology, Changhai Hospital, Second Military Medical University, Shanghai, China

  • Han Lin

    11   Digestive Diseases, Changhai Hospital, Shanghai, China (Ringgold ID: RIN12520)

Supported by: China University Industry-Research Innovation Fund - Huaton Medical Research Special Program 2023HT064
Supported by: Grants from ShanghaiMunicipal Health Commission Fund 202240357

Clinical Trial:

Registration number (trial ID): NCT06412419, Trial registry: Clinical Trials Registry India (http://www.ctri.nic.in/Clinicaltrials), Type of Study: Prospective and Retrospective Multicenter Study ANDRegistration number (trial ID): , Trial registry:, Type of Study: ANDRegistration number (trial ID): , Trial registry:, Type of Study:


Further Information
Also available at
 PDF Download

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.



Publication History

Received: 10 July 2025

Accepted after revision: 29 December 2025

Accepted Manuscript online:
30 December 2025

© . Thieme. All rights reserved.

Georg Thieme Verlag KG
Oswald-Hesse-Straße 50, 70469 Stuttgart, Germany