Development of machine learning models for predicting gastrointestinal diseases

The article addresses the problem of predicting pathological conditions of the gastrointestinal tract from endoscopic images using machine learning models. The relevance of the study is determined by the need to improve the reproducibility of preliminary assessment of endoscopic data and to reduce the risk of missing clinically significant images when processing large volumes of visual information. The aim of the study is to develop and experimentally evaluate a resource-efficient classification scheme for endoscopic images, taking into account not only the average recognition quality, but also the reliability of automatic decisions for pathological classes. The open Kvasir-v2 dataset containing 8000 images from eight classes was used as the experimental basis. A simple convolutional neural network, MobileNetV2, and EfficientNetB0 with transfer learning were compared. In addition, a selective scheme was proposed, combining the predictions of the two strongest models and sending uncertain images for manual review. The experiment showed that EfficientNetB0 achieved a macro-F-score of 0.8497 on the test set, while the combined prediction increased this value to 0.8681. The proposed selective scheme provided a macro-F-score of 0.9581 among automatically accepted decisions and reduced the number of dangerous automatic errors from 64 to 10. The obtained results demonstrate the potential of a clinically oriented approach in which automatic classification is supplemented by confidence control and assessment of the risk of missing a pathological condition.

1. Bray F., Laversanne M., Sung H., et al. Global cancer statistics 2022: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA: A Cancer Journal for Clinicians. 2024;74(3):229–263. https://doi.org/10.3322/caac.21834

2. Wu S., Zhang Y., Lin Z., et al. Global burden of colorectal cancer in 2022 and projections to 2050: incidence and mortality estimates from GLOBOCAN. BMC Cancer. 2025;25(1):1770. https://doi.org/10.1186/s12885-025-15138-0

3. Messmann H., Bisschops R., Antonelli G., et al. Expected value of artificial intelligence in gastrointestinal endoscopy: European Society of Gastrointestinal Endoscopy (ESGE) position statement. Endoscopy. 2022;54(12):1211–1231. https://doi.org/10.1055/a-1950-5694

4. Nie Z., Xu M., Wang Zh., et al. A review of application of deep learning in endoscopic image processing. Journal of Imaging. 2024;10(11):275. https://doi.org/10.3390/jimaging10110275

5. Zha B., Cai A., Wang G. Diagnostic accuracy of artificial intelligence in endoscopy: umbrella review. JMIR Medical Informatics. 2024;12:e56361. https://doi.org/10.2196/56361

6. Zubair Rahman A.M.J.M., Mythili R., Chokkanathan K., et al. Enhancing image-based diagnosis of gastrointestinal tract diseases through deep learning with EfficientNet and advanced data augmentation techniques. BMC Medical Imaging. 2024;24(1):306. https://doi.org/10.1186/s12880-024-01479-y

7. El-Sayed A., Lovat L.B., Ahmad O.F. Clinical implementation of artificial intelligence in gastroenterology: current landscape, regulatory challenges, and ethical issues. Gastroenterology. 2025;169(3):518–530. https://doi.org/10.1053/j.gastro.2025.01.254

8. Ali H., Muzammil M.A., Dahiya D.S., et al. Artificial intelligence in gastrointestinal endoscopy: a comprehensive review. Annals of Gastroenterology. 2024;37(2):133–141. https://doi.org/10.20524/aog.2024.0861

9. Theocharopoulos Ch., Davakis S., Ziogas D.C., et al. Deep learning for image analysis in the diagnosis and management of esophageal cancer. Cancers. 2024;16(19):3285. https://doi.org/10.3390/cancers16193285

10. Jahagirdar V., Bapaye J.A., Chandan S., et al. Diagnostic accuracy of convolutional neural network-based machine learning algorithms in endoscopic severity prediction of ulcerative colitis: a systematic review and meta-analysis. Gastrointestinal Endoscopy. 2023;98(2):145–154.e8. https://doi.org/10.1016/j.gie.2023.04.2074

11. Zavyalov D.V., Kashin S.V., Guseinova S.R. CAD EYE for real-time detection and differentiation of colorectal lesions. Russian Journal of Evidence-Based Gastroenterology. 2024;13(2):50–54. (In Russ.). https://doi.org/10.17116/dokgastro20241302150

12. Khryashchev V.V., Zavyalov D.V., Anderzanova A.S. Classification of endoscopic images of the orifice of the appendix on the basis of deep machine learning. Digital Signal Processing. 2023;(1):35–38. (In Russ.).

13. Kashin S.V., Zavyalov D.V., Guseinova S.R., et al. Assessing quality indicators of screening colonoscopy using an artificial intelligence system. Russian Journal of Evidence-Based Gastroenterology. 2025;14(4):56–64. (In Russ.). https://doi.org/10.17116/dokgastro20251404156

14. Pogorelov K., Randel K.R., Griwodz C., et al. KVASIR: a multi-class image dataset for computer aided gastrointestinal disease detection. In: Proceedings of the 8th ACM on Multimedia Systems Conference, 20–23 June 2017, Taipei, Taiwan. New York: ACM; 2017. P. 164–169. https://doi.org/10.1145/3083187.3083212

15. Sandler M., Howard A., Zhu M., et al. MobileNetV2: inverted residuals and linear bottlenecks. In: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 18–23 June 2018, Salt Lake City, UT, USA. IEEE; 2018. P. 4510–4520. https://doi.org/10.1109/CVPR.2018.00474

16. Tan M., Le Q.V. EfficientNet: rethinking model scaling for convolutional neural networks. In: Proceedings of the 36th International Conference on Machine Learning, 09–15 June 2019, Long Beach, CA, USA. PMLR; 2019. P. 6105–6114.

17. Kingma D.P., Ba J. Adam: a method for stochastic optimization. In: 3rd International Conference on Learning Representations, 07–09 May 2015, San Diego, CA, USA. 2015. URL: https://arxiv.org/abs/1412.6980

18. Selvaraju R.R., Cogswell M., Das A., et al. Grad-CAM: visual explanations from deep networks via gradient-based localization. International Journal of Computer Vision. 2020;128(8):336–359. https://doi.org/10.1007/s11263-019-01228-7