Ensemble-Based Deep Transfer Learning for Robust Gastrointestinal Endoscopy Image Classification

Abstract

Gastrointestinal (GI) diseases remain a significant global health challenge, particularly in low-income settings where diagnostic resources are often scarce. Endoscopic examination is essential for detecting and monitoring these diseases, yet the manual analysis of the resulting images is time-consuming, prone to observer variability, and demanding of clinical expertise. Recent advances in computer-aided diagnosis (CAD) using deep convolutional neural networks (CNNs) have shown promise in automating endoscopic image classification, but limited annotated data and the subtlety of GI findings continue to pose challenges. To address these constraints, this study proposes a two-level stacking ensemble framework that combines three pre-trained CNN architectures—ResNet50, DenseNet201, and MobileNetV3Large—with four classical machine-learning meta-classifiers (Logistic Regression, Random Forest, Support Vector Machine, and K-Nearest Neighbors). The KvasirV2 dataset, comprising 8,000 GI endoscopic images across eight classes, was used to train and evaluate the models. Results indicate that the stacking ensemble achieved a top accuracy of 94.33%, surpassing individual CNN baselines by 1–2%. Notably, this multi-level ensemble approach demonstrated improved diagnostic consistency for challenging classes like early-stage esophagitis and normal Z-line, suggesting that synergizing diverse CNN feature extractors can mitigate the limitations of single-network methods. These findings underscore the potential of ensemble-based transfer learning to enhance clinical decision support, reduce observer variability, and facilitate earlier, more accurate detection of GI diseases.

Keywords

• Ensemble Learning
• Transfer Learning
• Gastrointestinal Endoscopy
• Deep Convolutional Neural Networks
• Computer-Aided Diagnosis

References

1. [1] WHO, “The top 10 causes of death.” Accessed: Jan. 30, 2025. [Online]. Available: https://www.who.int/news-room/fact-sheets/detail/the-top-10-causes-of-death
2. [2] H. Gunasekaran, K. Ramalakshmi, D. K. Swaminathan, A. J, and M. Mazzara, “GIT-Net: An Ensemble Deep Learning-Based GI Tract Classification of Endoscopic Images,” Bioengineering, vol. 10, no. 7, p. 809, Jul. 2023, doi: 10.3390/bioengineering10070809.
3. [3] S. Mohapatra, J. Nayak, M. Mishra, G. K. Pati, B. Naik, and T. Swarnkar, “Wavelet Transform and Deep Convolutional Neural Network-Based Smart Healthcare System for Gastrointestinal Disease Detection,” Interdiscip. Sci. Comput. Life Sci., vol. 13, no. 2, pp. 212–228, Jun. 2021, doi: 10.1007/s12539-021-00417-8.
4. [4] A. KahsayGebreslassie, YaecobGirmayGezahegn, M. T. Hagos, AchimIbenthal, and Pooja, “Automated Gastrointestinal Disease Recognition for Endoscopic Images,” in 2019 International Conference on Computing, Communication, and Intelligent Systems (ICCCIS), Greater Noida, India: IEEE, Oct. 2019, pp. 312–316. doi: 10.1109/ICCCIS48478.2019.8974458.
5. [5] S. Poudel, Y. J. Kim, D. M. Vo, and S.-W. Lee, “Colorectal Disease Classification Using Efficiently Scaled Dilation in Convolutional Neural Network,” IEEE Access, vol. 8, pp. 99227–99238, 2020, doi: 10.1109/ACCESS.2020.2996770.
6. [6] Z. M. Lonseko et al., “Gastrointestinal Disease Classification in Endoscopic Images Using Attention-Guided Convolutional Neural Networks,” Appl. Sci., vol. 11, no. 23, p. 11136, Nov. 2021, doi: 10.3390/app112311136.
7. [7] A. Musha, R. Hasnat, A. A. Mamun, and T. Ghosh, “Deep Learning-Based Comparative Study to Detect Polyp Removal in Endoscopic Images,” in 2022 International Conference on Emerging Smart Computing and Informatics (ESCI), Pune, India: IEEE, Mar. 2022, pp. 1–5. doi: 10.1109/ESCI53509.2022.9758254.
8. [8] M. M. Auzine, P. Bissoonauth-Daiboo, M. H.-M. Khan, S. Baichoo, X. Gao, and N. G. Sahib, “Classification of artefacts in endoscopic images using deep neural network,” in 2022 3rd International Conference on Next Generation Computing Applications (NextComp), Flic-en-Flac, Mauritius: IEEE, Oct. 2022, pp. 1–5. doi: 10.1109/NextComp55567.2022.9932202.

9. [9] D. Gupta, G. Anand, P. Kirar, and P. Meel, “Classification of Endoscopic Images and Identification of Gastrointestinal diseases,” in 2022 International Conference on Machine Learning, Big Data, Cloud and Parallel Computing (COM-IT-CON), Faridabad, India: IEEE, May 2022, pp. 231–235. doi: 10.1109/COM-IT-CON54601.2022.9850571.
10. [10] D. Mukhtorov, M. Rakhmonova, S. Muksimova, and Y.-I. Cho, “Endoscopic Image Classification Based on Explainable Deep Learning,” Sensors, vol. 23, no. 6, p. 3176, Mar. 2023, doi: 10.3390/s23063176.
11. [11] A. A. Demirbaş, H. Üzen, and H. Fırat, “Spatial-attention ConvMixer architecture for classification and detection of gastrointestinal diseases using the Kvasir dataset,” Health Inf. Sci. Syst., vol. 12, no. 1, p. 32, Apr. 2024, doi: 10.1007/s13755-024-00290-x.
12. [12] E. Ayan, “Classification of Gastrointestinal Diseases in Endoscopic Images: Comparative Analysis of Convolutional Neural Networks and Vision Transformers,” Iğdır Üniversitesi Fen Bilim. Enstitüsü Derg., vol. 14, no. 3, pp. 988–999, Sep. 2024, doi: 10.21597/jist.1501787.
13. [13] X. Huo, S. Tian, Y. Yang, L. Yu, W. Zhang, and A. Li, “SPA: Self-Peripheral-Attention for central–peripheral interactions in endoscopic image classification and segmentation,” Expert Syst. Appl., vol. 245, p. 123053, Jul. 2024, doi: 10.1016/j.eswa.2023.123053.
14. [14] K. Pogorelov et al., “KVASIR: A Multi-Class Image Dataset for Computer Aided Gastrointestinal Disease Detection.” Association for Computing Machinery, Haziran 2017. doi: 10.1145/3193289.
15. [15] Kaggle, “Kvasir v2.” Accessed: Jan. 30, 2025. [Online]. Available: https://www.kaggle.com/datasets/plhalvorsen/kvasir-v2-a-gastrointestinal-tract-dataset
16. [16] N. Tajbakhsh et al., “Convolutional Neural Networks for Medical Image Analysis: Full Training or Fine Tuning?,” IEEE Trans. Med. Imaging, vol. 35, no. 5, pp. 1299–1312, May 2016, doi: 10.1109/TMI.2016.2535302.
17. [17] S. J. Pan and Q. Yang, “A Survey on Transfer Learning,” IEEE Trans. Knowl. Data Eng., vol. 22, no. 10, pp. 1345–1359, Oct. 2010, doi: 10.1109/TKDE.2009.191.
18. [18] G. Litjens et al., “A survey on deep learning in medical image analysis,” Med. Image Anal., vol. 42, pp. 60–88, Dec. 2017, doi: 10.1016/j.media.2017.07.005.
19. [19] K. He, X. Zhang, S. Ren, and J. Sun, “Deep Residual Learning for Image Recognition,” in 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA: IEEE, Jun. 2016, pp. 770–778. doi: 10.1109/CVPR.2016.90.
20. [20] G. Huang, Z. Liu, L. Van Der Maaten, and K. Q. Weinberger, “Densely Connected Convolutional Networks,” in 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI: IEEE, Jul. 2017, pp. 2261–2269. doi: 10.1109/CVPR.2017.243.
21. [21] A. Howard et al., “Searching for MobileNetV3,” in 2019 IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, Korea (South): IEEE, Oct. 2019, pp. 1314–1324. doi: 10.1109/ICCV.2019.00140.
22. [22] J. Yogapriya, V. Chandran, M. G. Sumithra, P. Anitha, P. Jenopaul, and C. Suresh Gnana Dhas, “Gastrointestinal Tract Disease Classification from Wireless Endoscopy Images Using Pretrained Deep Learning Model,” Comput. Math. Methods Med., vol. 2021, pp. 1–12, Sep. 2021, doi: 10.1155/2021/5940433.