EUVIMEDEUVIMED entdecken
Crossref

ColoXAI-RecomNet: Explainable Recommender Framework for Colorectal Cancer Classification Using Integrated CNN Ensemble and LIME Interpretability

Akella S Narasimha Raju, Ranjith Kumar Gatla, G Sucharitha, M Rajababu, Shaik Jakeer Hussain, Chaganti B N Lakshmi, K Venkatesh, Salem Alqahtani, Mohamed Ghouse, Kasim Sakran Abass

Journal of Imaging Informatics in Medicine · 26.05.2026

DOI: 10.1007/s10278-026-02007-w ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Imaging Informatics in Medicine, online erschienen am 26.05.2026. Verfasst von Akella S Narasimha Raju und 9 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computing Technologies, School of Computing, College of Engineering & Technology, SRM Institute of Science and Technology. Kattankulath…. Die Arbeit nennt 83 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The classification of colorectal disease based on colonoscopy images requires not only high predictive accuracy but also interpretable decision support. This study proposes a five-stage explainable framework for multi-class colorectal image classification on the Kvasir dataset. This framework is named ColoXAI-RecomNet. The initial stage of this framework involved an investigation of three parallel hybrid CNN ensemble models: RDV-2025 (ResNet50 + DenseNet121 + VGG16), IEM-2025 (InceptionV3 + EfficientNetB0 + MobileNetV2), and DRE-2025 (DenseNet201 + ResNet101 + EfficientNetB3). These CNN models were used as parallel feature extractors. Their combined deep features were used for classification. Among these models, DRE-2025 was identified as one of the top performers in Stage 1. This model had an approximate scale of 77.2 M for its backbones. The enhanced features for decision were passed to a multi-class SVM for final classification in Stage 3. The CNN features were refined by an XGBoost model in Stage 2. The final output of this framework was converted to a clinically interpretable recommender output in Stage 5. LIME was incorporated into this framework in Stage 4 to provide visual explanations for each image. The DRE-2025 + XGBoost + SVM model, which performed best, achieved an accuracy of 98.60%, a precision of 98.75%, a recall of 98.50%, an F1-score of 98.62%, and an AUC of 99.30%. In Stage 2, the combined CNN features were improved using an XGBoost algorithm. Stage 3 then classified the Stage 2 outputs using a multi-class SVM with an RBF kernel. Stage 4 used LIME for visual explanation, and Stage 5 converted the final prediction to a clinically interpretable recommender output.

Schlagwörter

Stichwörter der Autor:innen

Colorectal cancer classificationExplainable artificial intelligence (XAI)Integrated convolutional neural networks (CNNs)Kvasir datasetLIME (local interpretable model-agnostic explanations)Multi-class support vector machine (SVM)Recommender systemXGBoost classifier

Autor:innen und Institutionen

  • Department of Computing Technologies, School of Computing, College of Engineering & Technology, SRM Institute of Science and Technology. Kattankulathur, Chennai, Tamil Nadu, 603203, India. akellar@srmist.edu.in.
  • Department of Computer Science and Engineering (Data Science), Institute of Aeronautical Engineering, Hyderabad, Telangana, 500043, India.
  • Department of Computer Science and Engineering, School of Engineering, Anurag University, Hyderabad, India.
  • Department of Information Technology (IT), Aditya University, Surampalem, Andhra Pradesh, 533437, India.
  • Department of Computer Science and Engineering (AI & ML), Institute of Aeronautical Engineering, Hyderabad, Telangana, 500043, India.
  • Department of Computer Science and Engineering at TKR College of Engineering and Technology (TKRCET), Hyderabad, Telangana, 500097, India.

Zitieren

APA

Raju, A. S. N., Gatla, R. K., Sucharitha, G., Rajababu, M., Hussain, S. J., Lakshmi, C. B. N., Venkatesh, K., Alqahtani, S., Ghouse, M., & Abass, K. S. (2026). ColoXAI-RecomNet: Explainable Recommender Framework for Colorectal Cancer Classification Using Integrated CNN Ensemble and LIME Interpretability. Journal of Imaging Informatics in Medicine. https://doi.org/10.1007/s10278-026-02007-w

Vancouver

Raju ASN, Gatla RK, Sucharitha G, Rajababu M, Hussain SJ, Lakshmi CBN, et al. ColoXAI-RecomNet: Explainable Recommender Framework for Colorectal Cancer Classification Using Integrated CNN Ensemble and LIME Interpretability. Journal of Imaging Informatics in Medicine. 2026. doi:10.1007/s10278-026-02007-w

BibTeX
@article{Raju2026,
  author = {Raju, Akella S Narasimha and Gatla, Ranjith Kumar and Sucharitha, G and Rajababu, M and Hussain, Shaik Jakeer and Lakshmi, Chaganti B N and Venkatesh, K and Alqahtani, Salem and Ghouse, Mohamed and Abass, Kasim Sakran},
  title = {ColoXAI-RecomNet: Explainable Recommender Framework for Colorectal Cancer Classification Using Integrated CNN Ensemble and LIME Interpretability},
  journal = {Journal of Imaging Informatics in Medicine},
  year = {2026},
  doi = {10.1007/s10278-026-02007-w}
}
Kostenlos starten →