Abstract
Precancerous conditions such as intestinal metaplasia (IM) have a key role in gastric cancer development and can be detected during endoscopy. During upper gastrointestinal endoscopy (UGIE), misdiagnosis can occur due to technical and human factors or by the nature of the lesions, leading to a wrong diagnosis which can result in no surveillance/treatment and impairing the prevention of gastric cancer. Deep learning systems show great potential in detecting precancerous gastric conditions and lesions by using endoscopic images and thus improving and aiding physicians in this task, resulting in higher detection rates and fewer operation errors. This study aims to develop deep learning algorithms capable of detecting IM in UGIE images with a focus on model explainability and interpretability. In this work, white light and narrow-band imaging UGIE images collected in the Portuguese Institute of Oncology of Porto were used to train deep learning models for IM classification. Standard models such as ResNet50, VGG16 and InceptionV3 were compared to more recent algorithms that rely on attention mechanisms, namely the Vision Transformer (ViT), trained in 818 UGIE images (409 normal and 409 IM). All the models were trained using a 5-fold cross-validation technique and for validation, an external dataset will be tested with 100 UGIE images (50 normal and 50 IM). In the end, explainability methods (Grad-CAM and attention rollout) were used for more clear and more interpretable results. The model which performed better was ResNet50 with a sensitivity of 0.75 (±0.05), an accuracy of 0.79 (±0.01), and a specificity of 0.82 (±0.04). This model obtained an AUC of 0.83 (±0.01), where the standard deviation was 0.01, which means that all iterations of the 5-fold cross-validation have a more significant agreement in classifying the samples than the other models. The ViT model showed promising performance, reaching similar results compared to the remaining models.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
ASGE Standards of Practice Committee, et al.: Appropriate use of GI endoscopy. Gastrointest. Endosc. 75(6), 1127–1131 (2012). https://doi.org/10.1016/j.gie.2012.01.011
Evans, J.A., et al.: The role of endoscopy in the management of premalignant and malignant conditions of the stomach. Gastrointest. Endosc. 82(1), 1–8 (2015). https://doi.org/10.1016/j.gie.2015.03.1967
Peixoto, A., Silva, M., Pereira, P., Macedo, G.: Biopsies in gastrointestinal endoscopy: when and how. GE Port. J. Gastroenterol. 23(1), 19–27 (2016). https://doi.org/10.1016/j.jpge.2015.07.004
Pimentel-Nunes, P., et al.: Management of epithelial precancerous conditions and lesions in the stomach (MAPS II): European Society of Gastrointestinal Endoscopy (ESGE), European Helicobacter and Microbiota Study Group (EHMSG), European Society of Pathology (ESP), and Sociedade Portuguesa de Endoscopia Digestiva (SPED) guideline update 2019. Endoscopy 51(04), 365–388 (2019). https://doi.org/10.1055/a-0859-1883
Sitarz, R., Skierucha, M., Mielko, J., Offerhaus, G.J.A., Maciejewski, R., Polkowski, W.P.: Gastric cancer: epidemiology, prevention, classification, and treatment. Cancer Manag. Res. 10, 239–248 (2018). https://doi.org/10.2147/CMAR.S149619
Moon, H.S.: Improving the endoscopic detection rate in patients with early gastric cancer. Clin. Endosc. 48(4), 291 (2015). https://doi.org/10.5946/ce.2015.48.4.291
e Gonçalves, W.G., Dos Santos, M.H.D.P., Lobato, F.M.F., Ribeiro-dos-Santos, Â., de Araújo, G.S.: Deep learning in gastric tissue diseases: a systematic review. BMJ Open Gastroenterol. 7(1), e000371 (2020). https://doi.org/10.1136/bmjgast-2019-000371
Renna, F., et al.: Artificial intelligence for upper gastrointestinal endoscopy: a roadmap from technology development to clinical practice. Diagnostics 12(5), 1278 (2022). https://doi.org/10.3390/diagnostics12051278
Arribas, J., et al.: Standalone performance of artificial intelligence for upper GI neoplasia: a meta-analysis. Gut 70(8), 1458–1468 (2021). https://doi.org/10.1136/gutjnl-2020-321922
Li, H., et al.: A multi-feature fusion method for image recognition of gastrointestinal metaplasia (GIM). Biomed. Signal Process. Control 69, 102909 (2021). https://doi.org/10.1016/j.bspc.2021.102909
Yan, T., Wong, P.K., Choi, I.C., Vong, C.M., Yu, H.H.: Intelligent diagnosis of gastric intestinal metaplasia based on convolutional neural network and limited number of endoscopic images. Comput. Biol. Med. 126, 104026 (2020). https://doi.org/10.1016/j.compbiomed.2020.104026
Lin, N., et al.: Simultaneous recognition of atrophic gastritis and intestinal metaplasia on white light endoscopic images based on convolutional neural networks: a multicenter study. Clin. Transl. Gastroenterol. 12(8), e00385 (2021). https://doi.org/10.14309/ctg.0000000000000385
Xu, M., et al.: Artificial intelligence in the diagnosis of gastric precancerous conditions by image-enhanced endoscopy: a multicenter, diagnostic study (with video). Gastrointest. Endosc. 94(3), 540–548 (2021). https://doi.org/10.1016/j.gie.2021.03.013
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. arXiv: arXiv:1512.03385 (2015). http://arxiv.org/abs/1512.03385. Accessed 05 Jun 2022
Ali, L., Alnajjar, F., Jassmi, H.A., Gocho, M., Khan, W., Serhani, M.A.: Performance evaluation of deep CNN-based crack detection and localization techniques for concrete structures. Sensors 21(5), 1688 (2021). https://doi.org/10.3390/s21051688
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition, p. 14 (2015)
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2818–2826. Las Vegas, NV, USA (2016). https://doi.org/10.1109/CVPR.2016.308
Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv: arXiv:2010.11929 (2021). http://arxiv.org/abs/2010.11929. Accessed 02 Jun 2022
Linardatos, P., Papastefanopoulos, V., Kotsiantis, S.: Explainable AI: a review of machine learning interpretability methods. Entropy 23(1), 1–45 (2021). https://doi.org/10.3390/e23010018
Abnar, S., Zuidema, W.: Quantifying attention flow in transformers. arXiv (2020). http://arxiv.org/abs/2005.00928. Accessed 18 Jul 2022
Pimentel-Nunes, P., et al.: A multicenter prospective study of the real-time use of narrow-band imaging in the diagnosis of premalignant gastric conditions and lesions. Endoscopy 48(08), 723–730 (2016). https://doi.org/10.1055/s-0042-108435
Acknowledgements
This work is financed by National Funds through the Portuguese funding agency, FCT - Fundação para a Ciência e a Tecnologia, within project PTDC/EEI-EEE/5557/2020.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering
About this paper
Cite this paper
Neto, A., Ferreira, S., Libânio, D., Dinis-Ribeiro, M., Coimbra, M., Cunha, A. (2023). Preliminary Study of Deep Learning Algorithms for Metaplasia Detection in Upper Gastrointestinal Endoscopy. In: Cunha, A., M. Garcia, N., Marx Gómez, J., Pereira, S. (eds) Wireless Mobile Communication and Healthcare. MobiHealth 2022. Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, vol 484. Springer, Cham. https://doi.org/10.1007/978-3-031-32029-3_4
Download citation
DOI: https://doi.org/10.1007/978-3-031-32029-3_4
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-32028-6
Online ISBN: 978-3-031-32029-3
eBook Packages: Computer ScienceComputer Science (R0)