Application of convolutional neural networks for automated segmentation and classification in esophageal diseases
Frontiers in Medicine · 06.03.2026 · 13
DOI: 10.3389/fmed.2026.1742019 ↗Kurz gefasst
Fachartikel in der Zeitschrift Frontiers in Medicine, online erschienen am 06.03.2026. Verfasst von Liangpeng Pu und 4 weiteren Autor:innen. Beteiligte Einrichtung: The First School of Clinical Medicine of Nanjing Medical University, Nanjing, China. Die Arbeit nennt 26 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Objective
To develop a convolutional neural network (CNN) framework for the automated segmentation and classification of esophageal lesions in endoscopic images.
Methods
(1) Lesion localization was performed using a Region-based Convolutional Neural Network (R-CNN). (2) A dual-stream Esophageal Lesion Network (ELNet) was developed to classify images into four diagnostic categories. (3) Lesion segmentation was carried out using an ensemble of three U-Net architectures.
Results
The dual-stream ELNet achieved a classification accuracy of 92.14%, with 97.1% specificity and 88.74% sensitivity. The segmentation module based on U-Net attained an overall accuracy of 95.54% and a lesion segmentation sensitivity of 82.89%. The dual-stream ELNet consistently outperformed single-stream baseline networks, and the integrated segmentation-with-classification architecture demonstrated enhanced adaptability across diverse lesion types.
Conclusion
The proposed CNN framework enables accurate, robust, and simultaneous classification and segmentation of esophageal endoscopic lesions, exhibiting high performance and clinical potential.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- The First School of Clinical Medicine of Nanjing Medical University, Nanjing, China.
- The First Affiliated Hospital with Nanjing Medical University, Nanjing, China.
Zitieren
APA
Pu, L., Wang, X., Yan, S., Zhuang, S., & He, X. (2026). Application of convolutional neural networks for automated segmentation and classification in esophageal diseases. Frontiers in Medicine, 13. https://doi.org/10.3389/fmed.2026.1742019
Vancouver
Pu L, Wang X, Yan S, Zhuang S, He X. Application of convolutional neural networks for automated segmentation and classification in esophageal diseases. Frontiers in Medicine. 2026;13. doi:10.3389/fmed.2026.1742019
BibTeX
@article{Pu2026,
author = {Pu, Liangpeng and Wang, Xiao and Yan, Shanshan and Zhuang, Shuaishuai and He, Xiaopu},
title = {Application of convolutional neural networks for automated segmentation and classification in esophageal diseases},
journal = {Frontiers in Medicine},
year = {2026},
volume = {13},
doi = {10.3389/fmed.2026.1742019}
}
EUVIMED