Advertisement

Block Difference of Inverse Probabilities Features for Chromoendoscopy Image Classification

  • Viet Dung NguyenEmail author
  • Thanh Hien Truong
  • Ha Anh Pho
  • Le Thu Thao Dao
Chapter
  • 4 Downloads
Part of the Studies in Computational Intelligence book series (SCI, volume 899)

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.

Keywords

Gastric cancer Chromoendoscopy BDIP Classification 

References

  1. 1.
    New Global Cancer Data: GLOBOCAN (2018). https://www.uicc.org/new-global-cancer-data-globocan-2018
  2. 2.
    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)CrossRefGoogle Scholar
  3. 3.
    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)CrossRefGoogle Scholar
  4. 4.
    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)CrossRefGoogle Scholar
  5. 5.
    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)Google Scholar
  6. 6.
    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)Google Scholar
  7. 7.
    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)CrossRefGoogle Scholar
  8. 8.
    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)Google Scholar
  9. 9.
    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)Google Scholar
  10. 10.
    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)Google Scholar
  11. 11.
    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)Google Scholar
  12. 12.
    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)Google Scholar

Copyright information

© The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG 2021

Authors and Affiliations

  • Viet Dung Nguyen
    • 1
    Email author
  • Thanh Hien Truong
    • 1
  • Ha Anh Pho
    • 1
  • Le Thu Thao Dao
    • 1
  1. 1.Hanoi University of Science and TechnologyHanoiVietnam

Personalised recommendations