EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-SA 4.0

An Interpretable Hybrid Deep Learning Framework for Computer-Aided Detection of Gastrointestinal Diseases in Endoscopic Imaging

Shafiqul Islam Talukder, Md Jobaer Ahmed, Farhad Uddin Mahmud, Md Fokrul Islam Khan, Emon Hasan, Abu Kowshir Bitto

EAI Endorsed Transactions on AI and Robotics · 27.05.2026 · 5

DOI: 10.4108/airo.12566 ↗

Kurz gefasst

Fachartikel in der Zeitschrift EAI Endorsed Transactions on AI and Robotics, online erschienen am 27.05.2026. Verfasst von Shafiqul Islam Talukder und 5 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-SA 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Gastrointestinal (GI) illnesses, especially gastric polyps and gastroesophageal reflux disease (GERD), are still ubiquitous diagnostic challenges with their complicated presentation and high inter-observer variation on endoscopy. The current research proposes Xnception, a new dual-backbone deep learning network that synergistically combines the Xception and InceptionV3 architectures to facilitate classification robustness and feature expressivity for analysis of endoscopic images. Using transfer learning and fold wise validation, the model is optimized for small-sized medical datasets with ensured generalizability. The fusion mechanism combines deep semantic representations of both backbones through specialized dense layers to enable precise discrimination between pathological and non-pathological classes. Explainable AI (XAI) techniques, Local Interpretable Model-agnostic Explanations, Integrated gradients, Grad-CAM++, are employed to visualize important regions impacting the model's predictions, hence ensuring transparency and clinical trustworthiness. Quantitative results on publicly available datasets demonstrate that Xxception outperforms its component individual models as well as other common baselines on several measures like accuracy, precision, and AUC. The proposed framework demonstrates promise to improve real-time diagnostic pipelines in gastroenterology and provides a scalable platform for AI-augmented endoscopic screening.

Zitieren

APA

Talukder, S. I., Ahmed, M. J., Mahmud, F. U., Khan, M. F. I., Hasan, E., & Bitto, A. K. (2026). An Interpretable Hybrid Deep Learning Framework for Computer-Aided Detection of Gastrointestinal Diseases in Endoscopic Imaging. EAI Endorsed Transactions on AI and Robotics, 5. https://doi.org/10.4108/airo.12566

Vancouver

Talukder SI, Ahmed MJ, Mahmud FU, Khan MFI, Hasan E, Bitto AK. An Interpretable Hybrid Deep Learning Framework for Computer-Aided Detection of Gastrointestinal Diseases in Endoscopic Imaging. EAI Endorsed Transactions on AI and Robotics. 2026;5. doi:10.4108/airo.12566

BibTeX
@article{Talukder2026,
  author = {Talukder, Shafiqul Islam and Ahmed, Md Jobaer and Mahmud, Farhad Uddin and Khan, Md Fokrul Islam and Hasan, Emon and Bitto, Abu Kowshir},
  title = {An Interpretable Hybrid Deep Learning Framework for Computer-Aided Detection of Gastrointestinal Diseases in Endoscopic Imaging},
  journal = {EAI Endorsed Transactions on AI and Robotics},
  year = {2026},
  volume = {5},
  doi = {10.4108/airo.12566}
}
Kostenlos starten →