An Interpretable Hybrid Deep Learning Framework for Computer-Aided Detection of Gastrointestinal Diseases in Endoscopic Imaging
DOI:
https://doi.org/10.4108/airo.12566Keywords:
Medical Imaging, Gastrointestinal Disease, Endoscopic Image Analysis, Deep learning, Explainable AIAbstract
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.
Downloads
References
[1] Milivojevic, V., & Milosavljevic, T. (2020). Burden of gastroduodenal diseases from the global perspective. Current Treatment Options in Gastroenterology, 18, 148-157.
[2] Sharma, N., & Srivastava, S. (2025). Transforming Pancreatic Cancer Diagnosis: Conventional Methods, Challenges, and Future Innovations. Exon, 2(2), 86-111.
[3] Jain, R., & Chetty, R. (2009). Gastric hyperplastic polyps: a review. Digestive diseases and sciences, 54, 1839-1846.
[4] Wang, F. W., Young, S. C., Chen, R. Y., Lin, K. H., Chen, Y. H., Hsu, P. I., & Yu, H. C. (2018). The prevalence and risk factors of gastric polyp in asymptomatic patients receiving health examination. Gastroenterology research and practice, 2018(1), 9451905.
[5] Wong, B. C., & Kinoshita, Y. (2006). Systematic review on epidemiology of gastroesophageal reflux disease in Asia. Clinical gastroenterology and hepatology, 4(4), 398-407.
[6] Cortegoso Valdivia, P., Deding, U., Bjørsum-Meyer, T., Baatrup, G., Fernández-Urién, I., Dray, X., ... & Koulaouzidis, A. (2022). Inter/intra-observer agreement in video-capsule endoscopy: are we getting it all wrong? A systematic review and meta-analysis. Diagnostics, 12(10), 2400.
[7] Badruzzaman Biplob, K. B., Sammak, M. H., Bitto, A. K., & Mahmud, I. (2024). COVID-19 and Suicide Tendency: Prediction and Risk Factor Analysis Using Machine Learning and Explainable AI. EAI Endorsed Transactions on Pervasive Health & Technology, 10(1).
[8] Ringky, N. A., Bitto, A. K., Md Badruzzaman Biplob, K. B., Elahe, M. F., Sammak, M. H., & Toma, T. R. (2024). Enhancing Skin Disease Diagnosis Through Fine-Tune Convolutional Neural Network: A Comparative Study with Multi-class Approach. Journal of ICT Research & Applications, 18(2).
[9] Li, X., Zhang, L., Yang, J., & Teng, F. (2024). Role of artificial intelligence in medical image analysis: A review of current trends and future directions. Journal of Medical and Biological Engineering, 44(2), 231-243.
[10] Ozawa, T., Ishihara, S., Fujishiro, M., Kumagai, Y., Shichijo, S., & Tada, T. (2020). Automated endoscopic detection and classification of colorectal polyps using convolutional neural networks. Therapeutic advances in gastroenterology, 13, 1756284820910659.
[11] Bitto, A. K., & Mahmud, I. (2022). Multi categorical of common eye disease detect using convolutional neural network: a transfer learning approach. Bulletin of Electrical Engineering and Informatics, 11(4), 2378-2387.
[12] Urban, G., Tripathi, P., Alkayali, T., Mittal, M., Jalali, F., Karnes, W., & Baldi, P. (2018). Deep learning localizes and identifies polyps in real time with 96% accuracy in screening colonoscopy. Gastroenterology, 155(4), 1069-1078.
[13] Kavitha, M. S., Gangadaran, P., Jackson, A., Venmathi Maran, B. A., Kurita, T., & Ahn, B. C. (2022). Deep neural network models for colon cancer screening. Cancers, 14(15), 3707.
[14] Wang, P., Berzin, T. M., Brown, J. R. G., Bharadwaj, S., Becq, A., Xiao, X., ... & Liu, X. (2019). Real-time automatic detection system increases colonoscopic polyp and adenoma detection rates: a prospective randomised controlled study. Gut, 68(10), 1813-1819.
[15] Wong, M. W., Hung, J. S., Lei, W. Y., Liu, T. T., Yi, C. H., Liang, S. W., ... & Chen, C. L. (2023). Esophageal secondary peristalsis following acid infusion and chemical clearance correlate with mucosal integrity and acid sensitivity in GERD patients. Therapeutic Advances in Gastroenterology, 16, 17562848231179329.
[16] Aziz, M., Haghbin, H., Lee-Smith, W., Goyal, H., Nawras, A., & Adler, D. G. (2020). Gastrointestinal predictors of severe COVID-19: systematic review and meta-analysis. Annals of Gastroenterology, 33(6), 615.
[17] Souaidi, M., & El Ansari, M. (2022). A new automated polyp detection network MP-FSSD in WCE and colonoscopy images based fusion single shot multibox detector and transfer learning. IEEE access, 10, 47124-47140.
[18] Belabbes, M. A., Oukdach, Y., Souaidi, M., Koutti, L., & Charfi, S. (2024). Advancements in polyp detection: a developed single shot multibox detector approach. IEEE Access, 12, 19199-19215.
[19] Shin, Y., Qadir, H. A., Aabakken, L., Bergsland, J., & Balasingham, I. (2018). Automatic colon polyp detection using region based deep CNN and post learning approaches. IEEE access, 6, 40950-40962.
[20] Mohammed Jasim, M. J., Hussan, B. K., Zeebaree, S. R., & Ageed, Z. S. (2023). Automated Colonic Polyp Detection and Classification Enabled Northern Goshawk Optimization with Deep Learning. Computers, Materials & Continua, 75(2).
[21] Charmet, F., Tanuwidjaja, H. C., Ayoubi, S., Gimenez, P. F., Han, Y., Jmila, H., ... & Zhang, Z. (2022). Explainable artificial intelligence for cybersecurity: a literature survey. Annals of Telecommunications, 77(11), 789-812.
[22] Moreno-Sánchez, P. A. (2023). Data-driven early diagnosis of chronic kidney disease: development and evaluation of an explainable AI model. IEEE Access, 11, 38359-38369.
[23] Zhang, R., Luo, X., Lv, J., Cao, J., Zhu, Y., Wang, J., & Zheng, B. (2025). Enhancing Medical Image Classification with Context Modulated Attention and Multi-scale Feature Fusion. IEEE Access.
[24] Li, S., Guo, X., Zhu, B., Ye, S., Ye, J., Zhuang, Y., & He, X. (2025). Multi-classification of colorectal polyps with fused residual attention. Signal, Image and Video Processing, 19(1), 144.
[25] Bitto, A. K., Bijoy, M. H. I., Shakil, K. H., Das, A., Biplob, K. B. B., Mahmud, I., & Hossain, S. M. M. (2025). GastroEndoNet: Comprehensive Endoscopy Image Dataset for GERD and Polyp Detection. Data in Brief, 111572.
[26] Pogorelov, K., Randel, K. R., Griwodz, C., Eskeland, S. L., de Lange, T., Johansen, D., ... & Halvorsen, P. (2017, June). Kvasir: A multi-class image dataset for computer aided gastrointestinal disease detection. In Proceedings of the 8th ACM on Multimedia Systems Conference (pp. 164-169).
[27] Deng, Jia, et al. "Imagenet: A large-scale hierarchical image database." 2009 IEEE conference on computer vision and pattern recognition. Ieee, 2009.
[28] Bansal, Monika, et al. "Transfer learning for image classification using VGG19: Caltech-101 image data set." Journal of ambient intelligence and humanized computing 14.4 (2023): 3609-3620.
[29] Wang, Cheng, et al. "Pulmonary image classification based on inception-v3 transfer learning model." IEEE Access 7 (2019): 146533-146541.
[30] Chollet, François. "Xception: Deep learning with depthwise separable convolutions." Proceedings of the IEEE conference on computer vision and pattern recognition. 2017.
[31] Jahid Hassan Akash, Mia R, Bitto A.K. et al. (2026) A Stacking Based Ensemble Learning Approach for Accurate Identification of Tumor Homing Peptides in Precision Cancer Therapeutics. EAI Endorsed Trans AI Robotics, 5. Available from: https://publications.eai.eu/index.php/airo/article/view/10265
[32] Mia R, Hasan T, Bitto A.K. et al. (2025) Enhancing the Prediction of IL-4 Inducing Peptides Using Stacking Ensemble Model. EAI Endorsed Trans AI Robotics, 4. Available from: https://publications.eai.eu/index.php/airo/article/view/9867
[33] Abu Kowshir Bitto, Rezwana Karim, Begum M.H. et al. (2025) Explainable AI Based Deep Ensemble Convolutional Learning for Multi-Categorical Ocular Disease Prediction. EAI Endorsed Trans AI Robotics, 4. Available from: https://publications.eai.eu/index.php/airo/article/view/9234
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Shafiqul Islam Talukder, Md Jobaer Ahmed, Farhad Uddin Mahmud, Md Fokrul Islam Khan, Emon Hasan, Abu Kowshir Bitto
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
This is an open access article distributed under the terms of the CC BY-NC-SA 4.0, which permits copying, redistributing, remixing, transformation, and building upon the material in any medium so long as the original work is properly cited.
