EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

EndoNet: A Multiscale Deep Learning Framework for Multiple Gastrointestinal Disease Classification via Endoscopic Images

Omneya Attallah iD, Muhammet Fatih Aslan iD, Kadir Sabanci iD

Diagnostics · 11.08.2025 · 15 (16) · 2009

DOI: 10.3390/diagnostics15162009 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Diagnostics, online erschienen am 11.08.2025. Verfasst von Omneya Attallah und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electronics and Communications Engineering, College of Engineering and Technology, Arab Academy for Science, Technology and Maritime Tr…. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 55 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Gastrointestinal (GI) disorders present significant healthcare challenges, requiring rapid, accurate, and effective diagnostic methods to improve treatment outcomes and prevent complications. Wireless capsule endoscopy (WCE) is an effective tool for diagnosing GI abnormalities; however, precisely identifying diverse lesions with similar visual patterns remains difficult.

Methods

Many existing computer-aided diagnostic (CAD) systems rely on manually crafted features or single deep learning (DL) models, which often fail to capture the complex and varied characteristics of GI diseases. In this study, we proposed “EndoNet,” a multi-stage hybrid DL framework for eight-class GI disease classification using WCE images. Features were extracted from two different layers of three pre-trained convolutional neural networks (CNNs) (Inception, Xception, ResNet101), with both inter-layer and inter-model feature fusion performed. Dimensionality reduction was achieved using Non-Negative Matrix Factorization (NNMF), followed by selection of the most informative features via the Minimum Redundancy Maximum Relevance (mRMR) method.

Results

Two datasets were used to evaluate the performance of EndoNer, including Kvasir v2 and HyperKvasir. Classification using seven different Machine Learning algorithms achieved a maximum accuracy of 97.8% and 98.4% for Kvasir v2 and HyperKvasir datasets, respectively.

Conclusions

By integrating transfer learning with feature engineering, dimensionality reduction, and feature selection, EndoNet provides high accuracy, flexibility, and interpretability. This framework offers a powerful and generalizable artificial intelligence solution suitable for clinical decision support systems.

Schlagwörter

Stichwörter der Autor:innen

convolutional neural networksfeature fusiongastrointestinal disease classificationminimum redundancy maximum relevancenon-negative matrix factorization

Autor:innen und Institutionen

  • Department of Electronics and Communications Engineering, College of Engineering and Technology, Arab Academy for Science, Technology and Maritime Transport, Alexandria 21937, Egypt.
  • Wearables, Biosensing, and Biosignal Processing Laboratory, Arab Academy for Science, Technology and Maritime Transport, Alexandria 21937, Egypt.
  • Department of Electrical and Electronics Engineering, Karamanoglu Mehmetbey University, Karaman 70100, Türkiye.

ORCID-Profile: Omneya Attallah, Muhammet Fatih Aslan, Kadir Sabanci

Zitieren

APA

Attallah, O., Aslan, M. F., & Sabanci, K. (2025). EndoNet: A Multiscale Deep Learning Framework for Multiple Gastrointestinal Disease Classification via Endoscopic Images. Diagnostics, 15(16), 2009. https://doi.org/10.3390/diagnostics15162009

Vancouver

Attallah O, Aslan MF, Sabanci K. EndoNet: A Multiscale Deep Learning Framework for Multiple Gastrointestinal Disease Classification via Endoscopic Images. Diagnostics. 2025;15(16):2009. doi:10.3390/diagnostics15162009

BibTeX
@article{Attallah2025,
  author = {Attallah, Omneya and Aslan, Muhammet Fatih and Sabanci, Kadir},
  title = {EndoNet: A Multiscale Deep Learning Framework for Multiple Gastrointestinal Disease Classification via Endoscopic Images},
  journal = {Diagnostics},
  year = {2025},
  volume = {15},
  number = {16},
  pages = {2009},
  doi = {10.3390/diagnostics15162009}
}
Kostenlos starten →