Abstract
Deep learning strategies have become the mainstream for computer-assisted diagnosis tools development since they outperform other machine learning techniques. However, these systems can not reach their full potential since the lack of understanding of their operation and questionable generalizability provokes mistrust from the users, limiting their application. In this paper, we generate a Convolutional Neural Network (CNN) using a genetic algorithm for hyperparameter optimization. Our CNN has state-of-the-art classification performance, delivering higher evaluation metrics than other recent papers that use AI models to classify images from the same dataset. We provide visual explanations of the classifications made by our model implementing Grad-CAM and analyze the behavior of our model on misclassifications using this technique.
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
Similar content being viewed by others
References
Alagappan, M., Brown, J., Mori, Y., Berzin, T.: Artificial intelligence in gastrointestinal endoscopy: the future is almost here. World J. Gastrointest. Endosc. 10, 239–249 (2018). https://doi.org/10.4253/wjge.v10.i10.239
Alzubaidi, L., et al.: Review of deep learning: concepts, CNN architectures, challenges, applications, future directions. J. Big Data 8(1), 53 (2021). https://doi.org/10.1186/s40537-021-00444-8, https://journalofbigdata.springeropen.com/articles/10.1186/s40537-021-00444-8
Berzin, T., Parasa, S., Wallace, M., Gross, S., Repici, A., Sharma, P.: Position statement on priorities for artificial intelligence in gi endoscopy: a report by the asge task force. Gastrointest. Endosc. 92 (2020). https://doi.org/10.1016/j.gie.2020.06.035
Chahal, D., Byrne, M.: A primer on artificial intelligence and its application to endoscopy. Gastrointest. Endosc. 92 (2020). https://doi.org/10.1016/j.gie.2020.04.074
Fujita, H.: AI-based computer-aided diagnosis (AI-CAD): the latest review to read first. Radiol. Phys. Technol. 13(1), 6–19 (2020). https://doi.org/10.1007/s12194-019-00552-4
García-Aguirre, R., et al.: Automatic generation of optimized convolutional neural networks for medical image classification using a genetic algorithm (2022). https://doi.org/10.2139/ssrn.4167905
Gross, S., Sharma, P., Pante, A.: Artificial intelligence in endoscopy. Gastrointest. Endosc. 91 (2019). https://doi.org/10.1016/j.gie.2019.12.018
Hicks, S., et al.: Dissecting deep neural networks for better medical image classification and classification understanding. In: 2018 IEEE 31st International Symposium on Computer-Based Medical Systems (CBMS), pp. 363–368 (2018). https://doi.org/10.1109/CBMS.2018.00070
Jha, D., et al.: A comprehensive analysis of classification methods in gastrointestinal endoscopy imaging. Med. Image Anal. 70, 102007 (2021)
Kochhar, G.S., Carleton, N.M., Thakkar, S.: Assessing perspectives on artificial intelligence applications to gastroenterology. Gastrointest. Endosc. 93(4), 971–975.e2 (2021). https://doi.org/10.1016/j.gie.2020.10.029
Lafraxo, S., El Ansari, M.: Gastronet: abnormalities recognition in gastrointestinal tract through endoscopic imagery using deep learning techniques. In: 2020 8th International Conference on Wireless Networks and Mobile Communications (WINCOM), pp. 1–5 (2020). https://doi.org/10.1109/WINCOM50532.2020.9272456
Lipton, Z.C.: The mythos of model interpretability (2016). https://arxiv.org/abs/1606.03490. https://doi.org/10.48550/ARXIV.1606.03490
Luo, H., et al.: Real-time artificial intelligence for detection of upper gastrointestinal cancer by endoscopy: a multicentre, case-control, diagnostic study. Lancet Oncol. 20 (2019). https://doi.org/10.1016/S1470-2045(19)30637-0
Maddox, T., Rumsfeld, J., Payne, P.: Questions for artificial intelligence in health care. JAMA 321 (2018). https://doi.org/10.1001/jama.2018.18932
Miotto, R., Wang, F., Wang, S., Jiang, X., Dudley, J.T.: Deep learning for healthcare: review, opportunities and challenges. Brief. Bioinf. 19(6), 1236–1246 (2018)
Mori, Y., et al.: Artificial intelligence and upper gastrointestinal endoscopy: current status and future perspective. Digest. Endosc. 31 (2018). https://doi.org/10.1111/den.13317
Öztürk, S., Özkaya, U.: Gastrointestinal tract classification using improved LSTM based CNN. Multimedia Tools Appl. 79(39–40), 28825–28840 (2020). https://doi.org/10.1007/s11042-020-09468-3
Pogorelov, K., et al.: Kvasir: a multi-class image dataset for computer aided gastrointestinal disease detection. In: Proceedings of the 8th ACM on Multimedia Systems Conference, MMSys 2017, pp. 164–169. ACM, New York (2017). https://doi.org/10.1145/3083187.3083212
Prevedello, L., et al.: Challenges related to artificial intelligence research in medical imaging and the importance of image analysis competitions. Radiol. Artif. Intell. 1, e180031 (2019). https://doi.org/10.1148/ryai.2019180031
Quinn, T.P., Jacobs, S., Senadeera, M., Le, V., Coghlan, S.: The three ghosts of medical ai: can the black-box present deliver? Artif. Intell. Med., 102158 (2021). https://doi.org/10.1016/j.artmed.2021.102158. https://www.sciencedirect.com/science/article/pii/S0933365721001512
Reyes, M., et al.: On the interpretability of artificial intelligence in radiology: challenges and opportunities. Radiol. Artif. Intell. 2, e190043 (2020). https://doi.org/10.1148/ryai.2020190043
Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-CAM: visual explanations from deep networks via gradient-based localization. Int. J. Comput. Vision 128(2), 336–359 (2019). https://doi.org/10.1007/s11263-019-01228-7
Shin, Y., Balasingham, I.: Automatic polyp frame screening using patch based combined feature and dictionary learning. Comput. Med. Imaging Graph. 69, 33–42 (2018). https://doi.org/10.1016/j.compmedimag.2018.08.001
Stead, W.W.: Clinical implications and challenges of artificial intelligence and deep learning. JAMA 320(11), 1107–1108 (2018)
Thambawita, V., et al.: An extensive study on cross-dataset bias and evaluation metrics interpretation for machine learning applied to gastrointestinal tract abnormality classification. ACM Trans. Comput. Healthcare 1(3) (2020). https://doi.org/10.1145/3386295
van der Velden, B.H., Kuijf, H.J., Gilhuijs, K.G., Viergever, M.A.: Explainable artificial intelligence (XAI) in deep learning-based medical image analysis. Med. Image Anal. 79, 102470 (2022). https://doi.org/10.1016/j.media.2022.102470
Yao, A., Cheng, D., Pan, I., Kitamura, F.: Deep learning in neuroradiology: a systematic review of current algorithms and approaches for the new wave of imaging technology. Radiol. Artif. Intell. 2, e190026 (2020). https://doi.org/10.1148/ryai.2020190026
Yasuda, T., et al.: Potential of automatic diagnosis system with linked color imaging for diagnosis of Helicobacter pylori infection. Digest. Endosc. 32(3), 373–381 (2020). https://doi.org/10.1111/den.13509
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
García-Aguirre, R., Torres-Treviño, L., Navarro-López, E.M., González-González, J.A. (2022). Towards an Interpretable Model for Automatic Classification of Endoscopy Images. In: Pichardo Lagunas, O., Martínez-Miranda, J., Martínez Seis, B. (eds) Advances in Computational Intelligence. MICAI 2022. Lecture Notes in Computer Science(), vol 13612. Springer, Cham. https://doi.org/10.1007/978-3-031-19493-1_24
Download citation
DOI: https://doi.org/10.1007/978-3-031-19493-1_24
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-19492-4
Online ISBN: 978-3-031-19493-1
eBook Packages: Computer ScienceComputer Science (R0)