Abstract
The number of patients with inflammatory bowel disease (IBD) has been increasing. The diagnosis is a difficult task for the gastroenterologist performing the endoscopic examination. However, in order to prescribe medical treatment and provide quality of life to the patient, the diagnosis must be quick and accurate. Therefore, it is important to develop tools that, based on the characteristics of the inflammation present in the mucosa, automatically recognise the type of inflammatory bowel disease. This paper presents a study where the objective was to collect and analyse endoscopic images referring to Crohn’s disease and Ulcerative colitis using six deep learning architectures: AlexNet, ResNet50, InceptionV3, VGG-16, ResNet50+MobileNetV2, and a hybrid model. The hybrid model consists of the combination of two architectures, a CNN and a LSTM. This work also presents techniques that can be used to pre-process the images before the training to remove accessory elements from the image. The obtained results demonstrate that it is possible to automate the process of diagnosing patients with IBD using convolutional networks for processing images collected during an endoscopic examination, and thus develop tools to help the medical specialist diagnose the disease.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Borgli, H., Riegler, M., Thambawita, V., Jha, D., Hicks, S., Halvorsen, P.: The HyperKvasir Dataset. OSF (2019)
Borgli, H., et al.: HyperKvasir, a comprehensive multi-class image and video dataset for gastrointestinal endoscopy. Sci. Data 7, 283 (2020)
Cardoso, J.S., Sousa, R., Domingues, I.: Ordinal data classification using kernel discriminant analysis: a comparison of three approaches. In: 11th International Conference on Machine Learning and Applications. vol. 1, pp. 473–477 (2012)
Chicco, D., Jurman, G.: The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation. BMC Genomics 21, 6 (2020)
Chierici, M., et al.: Automatically detecting Crohn’s disease and ulcerative colitis from endoscopic imaging. BMC Med. Inf. Decis. Making 22, 300 (2022)
CrohnIPI. https://crohnipi.ls2n.fr/en/crohn-ipi-project/. Accessed 21 Feb 2023
Doença inflamatória do intestino CUF. https://www.cuf.pt/saude-a-z/doenca-inflamatoria-do-intestino. Accessed 21 Feb 2023
Domingues, I., Cardoso, J.S.: Max-ordinal learning. IEEE Trans. Neural Netw. Learn. Syst. 25(7), 1384–1389 (2014)
Dray, X., et al.: CAD-CAP: une base de données française à vocation internationale, pour le développement et la validation d’outils de diagnostic assisté par ordinateur en vidéocapsule endoscopique du grêle. In: Endoscopy, pp. s-0038-1623358 (2018)
Fatema, K., Montaha, S., Rony, M.A.H., Azam, S., Hasan, M.Z., Jonkman, M.: A robust framework combining image processing and deep learning hybrid model to classify cardiovascular diseases using a limited number of paper-based complex ECG images. Biomedicines 10, 2835 (2022)
Ghouri, Y.A., Tahan, V., Shen, B.: Secondary causes of inflammatory bowel diseases. World J. Gastroenterol. 26, 3998–4017 (2020)
Khan, M.N., Hasan, M.A., Anwar, S.: Improving the robustness of object detection through a multi-camera-based fusion algorithm using fuzzy logic. Front. Artif. Intell. 4, 638951 (2021)
Maissin, A., et al.: Multi-expert annotation of Crohn’s disease images of the small bowel for automatic detection using a convolutional recurrent attention neural network. Endoscopy Int. Open 09, E1136–E1144 (2021)
Polat, G., Kani, H.T., Ergenc, I., Alahdab, Y.O., Temizel, A., Atug, O.: Improving the computer-aided estimation of ulcerative colitis severity according to mayo endoscopic score by using regression-based deep learning. Inflamm. Bowel Dis., izac226 (2022)
Polat, G., Kani, H.T., Ergenc, I., Alahdab, Y.O., Temizel, A., Atug, O.: Labeled Images for Ulcerative Colitis (LIMUC) Dataset (2022)
Sairenji, T., Collins, K.L., Evans, D.V.: An update on inflammatory bowel disease. Prim. Care: Clin. Off. Pract. 44, 673–692 (2017)
Seyedian, S.S., Nokhostin, F., Malamir, M.D.: A review of the diagnosis, prevention, and treatment methods of inflammatory bowel disease. J. Med. Life 12, 113–122 (2019)
Shahzadi, I., Tang, T.B., Meriadeau, F., Quyyum, A.: CNN-LSTM: cascaded framework for brain tumour classification. In: IEEE-EMBS Conference on Biomedical Engineering and Sciences (IECBES), pp. 633–637 (2018)
Stidham, R.W., et al.: Performance of a deep learning model vs human reviewers in grading endoscopic disease severity of patients with ulcerative colitis. JAMA Netw. Open 2(5), e193963 (2019)
Turan, M., Durmus, F.: UC-NfNet: deep learning-enabled assessment of ulcerative colitis from colonoscopy images. Med. Image Anal. 82, 102587 (2022)
Udristoiu, A.L., et al.: Deep learning algorithm for the confirmation of mucosal healing in Crohn’s disease, based on confocal laser endomicroscopy images. J. Gastroint. Liver Dis. 30, 59–65 (2021)
Vallée, R., Coutrot, A., Normand, N., Mouchère, H.: Accurate small bowel lesions detection in wireless capsule endoscopy images using deep recurrent attention neural network. In: IEEE 21st International WS on Multimedia Signal Proceedings (MMSP) (2019)
Vallée, R., Coutrot, A., Normand, N., Mouchère, H.: Influence of expertise on human and machine visual attention in a medical image classification task. In: European Conference on Visual Perception (2021)
Vallée, R., Maissin, A., Coutrot, A., Mouchère, H., Bourreille, A., Normand, N.: CrohnIPI: an endoscopic image database for the evaluation of automatic Crohn’s disease lesions recognition algorithms. In: Medical Imaging: Biomedical Applications in Molecular, Structural, and Functional Imaging, p. 61. SPIE (2020)
Vankdothu, R., Hameed, M.A., Fatima, H.: A brain tumor identification and classification using deep learning based on CNN-LSTM method. Comput. Electr. Eng. 101, 107960 (2022)
Wehkamp, J., Götz, M., Herrlinger, K., Steurer, W., Stange, E.F.: Inflammatory bowel disease: Crohn’s disease and ulcerative colitis. Deutsches Ärzteblatt Int. 113, 72 (2016)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Maurício, J., Domingues, I. (2023). Deep Neural Networks to Distinguish Between Crohn’s Disease and Ulcerative Colitis. In: Pertusa, A., Gallego, A.J., Sánchez, J.A., Domingues, I. (eds) Pattern Recognition and Image Analysis. IbPRIA 2023. Lecture Notes in Computer Science, vol 14062. Springer, Cham. https://doi.org/10.1007/978-3-031-36616-1_42
Download citation
DOI: https://doi.org/10.1007/978-3-031-36616-1_42
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-36615-4
Online ISBN: 978-3-031-36616-1
eBook Packages: Computer ScienceComputer Science (R0)