Abstract
Gastric or stomach cancer is one of the most common cancers in the world. It used to be the leading cause of cancer deaths before 1980s. Endoscopy is a less invasive method to screen gastric cancer than biopsy. In chromoendoscopy, one of endoscopy improvements, by spraying dyes over mucosal surface, abnormal regions are made more prominent visually. However, detection and classification of abnormal regions are not so easy tasks. Accuracy depends largerly on experience of doctors, physical status of doctors, and illumination variations. Nowaday, with computer-aided diagnosis (CAD) systems, gastric cancer can be detected and classified into different stages. In this paper, we propose using Block Difference of Inverse Probabilities (BDIP) and Support Vector Machine (SVM) to build an automatic and accurate yet simple classification algorithm for identifing whether a chromoendoscopy (CH) image is abnormal or not. Experimental results show that the proposed method has a classification accuracy of 87.3% and an area under the curve (AUC) value of 0.92 on the CH imageset obtained using an Olympus CV-180 endoscope at the Portuguese Institute of Oncology (IPO) Hospital in Porto, Portugal.
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
New Global Cancer Data: GLOBOCAN (2018). https://www.uicc.org/new-global-cancer-data-globocan-2018
Onji, K., Yoshida, S., Tanaka, S., Kawase, R., Takemura, Y., Oka, S., Tamaki, T., Raytchev, B., Kaneda, K., Yoshihara, M., Chayama, K.: Quantitative analysis of colorectal lesions observed on magnified endoscopy images. J. Gastroenterol. 46, 1382–1390 (2011)
Riaz, F., Silva, F., Ribeiro, M., Coimbra, M.: Invariant Gabor texture descriptors for classification of gastro enterology images. IEEE Trans. Biomed. Eng. 59(10), 2893–2904 (2012)
Kwitt, R., Vasconcelos, N., Rasiwasia, N., Uhl, A., Davis, B., Hafner, M., Wrba, F.: Endoscopic image analysis in semantic space. Med. Image Anal. 16(7), 1415–1422 (2012)
Sousa, R., Moura, D.C., Dinis-Ribeiro, M., Coimbra, M.T.: Local self similar descriptors: comparison and application to gastroenterology ımages. In: 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (2014)
Constantinescu, A.F., Ionescu, M., Rogoveanu, I., Ciurea, M.E., Streba, C.T., Iovanescu, V.F., Artene, S.A., Vere, C.C.: Analysis of wireless capsule endoscopy images using local binary patterns. Appl. Med. Inf. 36(2), 31–42 (2015)
Ali, H., Sharif, M., Yasmin, M., Rehmani, M.H.: Computer-based classification of chromoendoscopy images using homogeneous texture descriptors. Comput. Biol. Med. 88(1), 84–92 (2017)
Nguyen, V.D., Truong, T.H.: Speeded-up robust feature descriptor for endochromoscopy images. In: 34th International Technical Conference on Circuits/Systems, Computers and Communications (ITC-CSCC 2019) (2019)
So, H.J., Kim, M.H., Kim, N.C.: Texture classification using wavelet domain BDIP and BVLC features. In: 17th European Signal Processing Conference (EUSIPCO2009) (2009)
Nguyen, V.D., Nguyen, D.T., Nguyen, T.D., Truong, Q.D., Le, M.D.: Combination of block difference inverse probability features and support vector machine to reduce false positives in computer-aided detection for massive lesions in mammographic images. In: 6th International Conference on Biomedical Engineering and Informatics (BMEI 2013) (2013)
Boser, B.E., Guyon, I.M., Vapnik, V.N.: A training algorithm for optimal margin classifiers. In: 5th Annual Workshop on Computational Learning Theory (1992)
Sousa, A., Dinis-Ribeiro, M., Areia, M., Coimbra, M.: Identifying cancer regions in vital-stained magnification endoscopy images using adapted color histograms. In: 16th IEEE International Conference on Image Processing (ICIP) (2009)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG
About this chapter
Cite this chapter
Nguyen, V.D., Truong, T.H., Pho, H.A., Dao, L.T.T. (2021). Block Difference of Inverse Probabilities Features for Chromoendoscopy Image Classification. In: Kreinovich, V., Hoang Phuong, N. (eds) Soft Computing for Biomedical Applications and Related Topics. Studies in Computational Intelligence, vol 899. Springer, Cham. https://doi.org/10.1007/978-3-030-49536-7_24
Download citation
DOI: https://doi.org/10.1007/978-3-030-49536-7_24
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-49535-0
Online ISBN: 978-3-030-49536-7
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)