EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

An End-to-End Deep Learning System for Gastrointestinal Bleeding Detection and Quantification in Wireless Capsule Endoscopy

Mujeeb Rahman Kanhira Kadavath iD, Aman Kitaz iD, Nour El Houda Benyahia iD, Shatha Hussein

Diagnostics · 07.07.2026 · 16 (13) · 2121

DOI: 10.3390/diagnostics16132121 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Diagnostics, online erschienen am 07.07.2026. Verfasst von Mujeeb Rahman Kanhira Kadavath und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Biomedical Engineering, College of Engineering & Information Technology (CEIT), Ajman University, Ajman P.O. Box 346, United Arab Emira…. Die Arbeit nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background/Objectives: Gastrointestinal bleeding is a critical finding in wireless capsule endoscopy (WCE), but manual examination of thousands of image frames is labor-intensive, time-consuming, and susceptible to missed lesions. This study aimed to develop and evaluate a comprehensive deep-learning framework for automated bleeding detection, localization, and quantitative assessment in WCE images.

Methods

The proposed framework integrates three complementary deep-learning models: (i) a custom two-dimensional convolutional neural network (2D-CNN) for frame-level bleeding classification, (ii) a three-dimensional convolutional neural network (3D-CNN) for sequence-level analysis by exploiting temporal information from consecutive frames, and (iii) a U-Net architecture for pixel-level segmentation and bleeding-area quantification. The models were trained and evaluated using expert-annotated WCE datasets with pixel-level ground-truth masks.

Results

The proposed 2D-CNN and 3D-CNN achieved excellent classification performance, with areas under the receiver operating characteristic curve (AUCs) of 0.9986 and 0.9971, respectively. The U-Net model achieved a Dice similarity coefficient of 0.93, an intersection-over-union (IoU) of 0.8677, and an overall segmentation accuracy of 97.25%. The integrated framework outperformed previously reported methods, demonstrating robust performance for bleeding detection, localization, and quantitative assessment.

Conclusions

The proposed end-to-end deep-learning framework enables accurate automated bleeding detection, localization, and severity quantification in WCE images. By reducing the burden of manual image review, improving diagnostic consistency, and providing objective bleeding assessment, the framework has strong potential to support clinical decision-making and enhance gastrointestinal diagnostic workflows.

Schlagwörter

Stichwörter der Autor:innen

2D-CNN3D-CNNU-Net modelconvolutional neural networkgastro intestinal bleedingimage segmentationmachine learningquantification of intestinal bleedingwireless capsule endoscopy

Autor:innen und Institutionen

  • Department of Biomedical Engineering, College of Engineering & Information Technology (CEIT), Ajman University, Ajman P.O. Box 346, United Arab Emirates.

ORCID-Profile: Mujeeb Rahman Kanhira Kadavath, Aman Kitaz, Nour El Houda Benyahia

Zitieren

APA

Kanhira Kadavath, M. R., Kitaz, A., Benyahia, N. E. H., & Hussein, S. (2026). An End-to-End Deep Learning System for Gastrointestinal Bleeding Detection and Quantification in Wireless Capsule Endoscopy. Diagnostics, 16(13), 2121. https://doi.org/10.3390/diagnostics16132121

Vancouver

Kanhira Kadavath MR, Kitaz A, Benyahia NEH, Hussein S. An End-to-End Deep Learning System for Gastrointestinal Bleeding Detection and Quantification in Wireless Capsule Endoscopy. Diagnostics. 2026;16(13):2121. doi:10.3390/diagnostics16132121

BibTeX
@article{KanhiraKadavath2026,
  author = {Kanhira Kadavath, Mujeeb Rahman and Kitaz, Aman and Benyahia, Nour El Houda and Hussein, Shatha},
  title = {An End-to-End Deep Learning System for Gastrointestinal Bleeding Detection and Quantification in Wireless Capsule Endoscopy},
  journal = {Diagnostics},
  year = {2026},
  volume = {16},
  number = {13},
  pages = {2121},
  doi = {10.3390/diagnostics16132121}
}
Kostenlos starten →