Importance of Preprocessing in Histopathology Image Classification Using Deep Convolutional Neural Network

Abstract

The aim of this study is to propose an alternative and hybrid solution method for diagnosing the disease from histopathology images taken from animals with paratuberculosis and intact intestine. In detail, the hybrid method is based on using both image processing and deep learning for better results. Reliable disease detection from histopathology images is known as an open problem in medical image processing and alternative solutions need to be developed. In this context, 520 histopathology images were collected in a joint study with Burdur Mehmet Akif Ersoy University, Faculty of Veterinary Medicine, Department of Pathology. Manually detecting and interpreting these images requires expertise and a lot of processing time. For this reason, veterinarians, especially newly recruited physicians, have a great need for imaging and computer vision systems in the development of detection and treatment methods for this disease. The proposed solution method in this study is to use the CLAHE method and image processing together. After this preprocessing, the diagnosis is made by classifying a convolutional neural network supported by the VGG-16 architecture. This method uses completely original dataset images. Two types of systems were applied for the evaluation parameters. While the F1 Score was 93% in the method classified without data preprocessing, it was 98% in the method that was preprocessed with the CLAHE method.

Keywords

• artifical intelligence
• CLAHE
• Deep learning
• Histopathology Images

References

1. V. Santhi, D. P. Acharjya, M. Ezhilarasan, 2016, Biomedical Imaging Techniques, Book: Emerging Technologies in Intelligent Applications for Image and Video Processing, , https://doi.org/10.4018/978-1-4666-9685-3.ch016.
2. Garcia, A.B., Shalloo, L., 2015. Invited review: The economic impact and control of paratuberculosis in cattle. J. Dairy Sci. 98, 5019–5039. https://doi.org/10.3168/jds.2014-9241.
3. Wolf, R., Barkema, H.W., De Buck, J., Slomp, M., Flaig, J., Haupstein, D., Pickel, C., Orsel, K., 2014. High herd-level prevalence of Mycobacterium avium subspecies paratuberculosis in Western Canadian dairy farms, based on environmental sampling. J. Dairy Sci. 97, 6250–6259. https://doi.org/10.3168/jds.2014-8101.
4. Dufour, B., Pouillot, R., Durand, B., 2004. A cost/benefit study of paratuberculosis certification in French cattle herds. Vet. Res. 35, 69–81. https://doi.org/10.1051/vetres:2003045.
5. Cocito, C., Gilot, P., Coene, M. andKesel, M. 1994 ‘Paratuberculosis’, Clinical Microbiology,Vol. 7,No. 3, pp.328–345.
6. Whittington, R., Donat, K., Weber, M.F., Kelton, D., Nielsen, S.S., et al., 2019. Control of paratuberculosis: who, why and how. A review of 48 countries. BMC Vet. Res. 15, 198. https://doi.org/10.1186/s12917-019-1943-4.
7. Feller, M., Huwiler, K., Stephan, R., Altpeter, E., Shang, A., Furrer, H., Pfyffer, G.E., Jemmi, T., Baumgartner, A., Egger, M., 2007. Mycobacterium avium subspecies paratuberculosis and Crohn’s disease: a systematic review and meta-analysis. Lancet Infect. Dis. 7, 607–613. https://doi.org/10.1016/S1473-3099(07)70211-6.
8. OIE (Office International des Epizooties), 2019. Paratuberculosis (accessed 19 December 2019). https://www.oie.int/en/animal-health-in-the-world/animal-diseases/Paratuberculosis/

9. Özturk D, Pehlivanoğlu F, Tok AA, Gunlu S, Guldali Y, Turutoglu H., Seroprevalence of paratuberculosis in the Burdur province (Turkey), in dairy cattle using the enzyme linked immunosorbent assay (ELISA). Israel J Vet Med, 65, 53-57.
10. Alom, M.Z.; Taha, T.M.; Yakopcic, C.; Westberg, S.; Sidike, P.; Nasrin, M.S.; Hasan, M.; Van Essen, B.C.; Awwal, A.A.; Asari, V.K. A state-of-the-art survey on deep learning theory and architectures. Electronics 2019, 8, 292.
11. M. D. Zeiler and R. Fergus, “Visualizing and understanding convolutional networks,” in European Conference on Computer Vision, pp. 818–833, Springer, 2014.
12. A. Krizhevsky, I. Sutskever, and G. E. Hinton, “Imagenet classification with deep convolutional neural networks,” in Advances in Neural Information Processing Systems, pp. 1097–1105, 2012.
13. K. Simonyan and A. Zisserman, “Very deep convolutional networks for largescale image recognition,” arXiv preprint arXiv:1409.1556, 2014.
14. C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke, and A. Rabinovich, “Going deeper with convolutions,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1–9, 2015.
15. R. Girshick, J. Donahue, T. Darrell, and J. Malik, “Rich feature hierarchies for accurate object detection and semantic segmentation,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 580– 587, 2014.
16. Y. Gao, W. Rong, Y. Shen, and Z. Xiong, “Convolutional neural network based sentiment analysis using adaboost combination,” in Neural Networks (IJCNN), 2016 International Joint Conference on, pp. 1333–1338, IEEE, 2016.
17. J. Long, E. Shelhamer, and T. Darrell, “Fully convolutional networks for semantic segmentation,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3431–3440, 2015.
18. Yoon H, Han Y, and Hahn H. Image Contrast Enhancement based Sub-histogram Equalization Technique without Over-equalization Noise. International Journal of Computer Science and Engineering 2009 : 3 (2).
19. Teo CK. Digital Enhancement of Night Vision and Thermal Images. Thesis, Naval Postgraduate School, California, 2003.