Skip to main content
Log in

An Adaptive Regularization Approach to Colonoscopic Polyp Detection Using a Cascaded Structure of Encoder–Decoders

  • Published:
International Journal of Fuzzy Systems Aims and scope Submit manuscript

Abstract

This research aims to segment colonoscopic images by automatically extracting polyp features by exploiting the strengths of convolution neural networks (CNN). The proposed model employs deep learning and adaptive regularization techniques. The model is structurally composed of two cascaded encoder–decoder networks, each of which is constructed by four CNN layers and two full connection layers. The front model is built on backpropagation learning for segmenting a colonoscopic polyp image. The output images from the precedent hetero-encoder are regarded as corrupted labeled images, especially during the time period close to the end of learning, and are selectively fed into the successive auto-encoder for denoising learning to enhance its discriminative power and relieve the problem of a lack of labeled data for medical image tasks. The performance of the proposed model can be further improved by a simple fuzzy logic approach setting the regularization parameter in the loss function. The proposed method utilizes features learned from some open medical datasets and our own collected dataset. The performance of the proposed architecture is compared with a state-of-the-art network. The evaluation shows the performances of the proposed method are consistent across all the datasets and often outperform the state-of-art model.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5

Similar content being viewed by others

References

  1. New Global Cancer Data: GLOBOCAN 2018. https://www.uicc.org/new-global-cancer-data-globocan-2018

  2. Brenner, H., Chang-Claude, J., Jansen, L., et al.: Reduced risk of colorectal cancer up to 10 years after screening, surveillance, or diagnostic colonoscopy. Gastroenterology 146(3), 709–717 (2014)

    Article  Google Scholar 

  3. Zauber, A.G., Winawer, S.J., O’Brien, M.J., et al.: Colonoscopic polypectomy and long-term prevention of colorectal-cancer deaths. N. Engl. J. Med. 366(8), 687–696 (2012)

    Article  Google Scholar 

  4. Winawer, S.J., Zauber, A.G., Ho, M.N., et al.: Prevention of colorectal cancer by colonoscopic polypectomy. N. Engl. J. Med. 329(27), 1977–1981 (1993)

    Article  Google Scholar 

  5. Leufkens, A., van Oijen, M., Vleggaar, F., Siersema, P.D.: Factors influencing the miss rate of polyps in a back-to-back colonoscopy study. Endoscopy 44(05), 470–475 (2012)

    Article  Google Scholar 

  6. Mahmud, N., Cohen, J., Tsourides, K., et al.: Computer vision and augmented reality in gastrointestinal endoscopy. Gastroenterol. Rep. 3(3), 179–184 (2015)

    Article  Google Scholar 

  7. Ahn, S.B., Han, D.S., Bae, J.H., et al.: The miss rate for colorectal adenoma determined by quality-adjusted, back-to-back colonoscopies. Gut Liver. 6(1), 64–70 (2012)

    Article  Google Scholar 

  8. Aslanian, H.R., Shieh, F.K., Chan, F.W., et al.: Nurse observation during colonoscopy increases polyp detection: a randomized prospective study. Am. J. Gastroenterol. 108(2), 166 (2013)

    Article  Google Scholar 

  9. Lee, C.K., Park, D.I., Lee, S.H., et al.: Participation by experienced endoscopy nurses increases the detection rate of colon polyps during screening colonoscopy: a multicenter, prospective, randomized study. Gastrointest. Endosc. 74(5), 1094–1102 (2011)

    Article  Google Scholar 

  10. Buchner, A.M., Shahid, M.W., Heckman, M.G., et al.: Trainee participation is associated with increased small adenoma detection. Gastrointest. Endosc. 73(6), 1223–1231 (2011)

    Article  Google Scholar 

  11. Coimbra, M.T., Cunha, J.P.S.: Mpeg-7 visual descriptors contributions for automated feature extraction in capsule endoscopy. IEEE Trans. Circuits Syst. Video Technol. 16, 628–637 (2006)

    Article  Google Scholar 

  12. Silva, J., Histace, A., Romain, O., Dray, X., Granado, B., Pinna, A.: Towards real-time in situ polyp detection in wce images using a boosting-based approach. In: Proc. IEEE World Congress on Intell. Control and Autom. pp. 5711–5714. IEEE, Piscataway (2013)

  13. Yuan, Y., Li, B., Meng, M.Q.-H.: Improved bag of feature for automatic polyp detection in wireless capsule endoscopy images. IEEE Trans Autom Sci Eng. 13, 529–535 (2016)

    Article  Google Scholar 

  14. El Khatib, A., Werghi, N., Al-Ahmad, H.: Automatic polyp detection: a comparative study. In: Proc. IEEE Annu. Int. Conf. Eng. Med. Biol. Soc., EMBC. pp. 2669–2672 IEEE, Piscataway (2015)

  15. Iwahori, Y., Hattori, A., Adachi, Y., Bhuyan, M., Woodham, R.J., Kasugai, K.: Automatic detection of polyp using hessian filter and hog features. Procedia Computer Sci. 60, 730–739 (2015)

    Article  Google Scholar 

  16. Bae, S.-H., Yoon, K.-J.: Polyp detection via imbalanced learning and discriminative feature learning. IEEE Trans. Med. Imag. 34, 2379–2393 (2015)

    Article  Google Scholar 

  17. LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521, 436–444 (2015)

    Article  Google Scholar 

  18. Krizhevsky, A., Sutskever, I., Hinton, G. E.: ImageNet classification with deep convolutional neural networks. In: Proc. Neural Inf. Process. Syst. pp. 1097–1105 (2012)

  19. Roth, H., R., et al.: Anatomy-specific classification of medical images using deep convolutional nets. In: Proc. IEEE Int. Symp. Biomed. Imag. pp. 101–104. IEEE, New York (2015)

  20. Tajbakhsh, N., et al.: Convolutional neural networks for medical image analysis: full training or fine tuning? IEEE Trans. Med. Imaging 35(5), 1299–1312 (2016)

    Article  Google Scholar 

  21. Jia, Y., et al.: Caffe: Convolutional architecture for fast feature embedding. In: Proc. 22nd ACM Int. Conf. Multimedia, pp. 675–678 (2014)

  22. Chatfield, K., Simonyan, K., Vedaldi, A., et al. Return of the devil in the details: Delving deep into convolutional nets. arXiv preprint, pp. 1405.3531 (2014)

  23. Shin, Y., Balasingham, I.: Comparison of hand-craft feature based SVM and CNN based deep learning framework for automatic polyp classification,” in Engineering in Medicine and Biology Society (EMBC). In: Proc. 39th Annual International Conference of the IEEE, pp. 3277–3280 (2017)

  24. Urban, G., Tripathi, P., Alkayali, T., Mittal, M., Jalali, F., Karnes, W., Baldi, P.: Deep learning localizes and identifies Polyps in real time with 96% accuracy in screening colonoscopy. Gastroenterology. (2018). https://doi.org/10.1053/j.gastro.2018.06.037

    Google Scholar 

  25. Zhang, R., Zheng, Y., Mak, T.W., Yu, R., Wong, S.H., Lau, J.Y., Poon, C.C.: Automatic detection and classification of colorectal polyps by transferring low-level CNN features from nonmedical domain. IEEE J. Biomed. Health Inform. 21(1), 41–47 (2017)

    Article  Google Scholar 

  26. Ranzato, F. J. H., Boureau, Y. L., LeCun, Y.: Unsupervised learning of invariant feature hierarchies with applications to object recognition. In: Proc. IEEE Conf. Comput. Vis. Pattern Recognit. pp. 1–8 (2007)

  27. Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 3431–3440 (2015)

  28. Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical, pp. 234–241. Springer, Cham (2015)

    Google Scholar 

  29. Badrinarayanan, V., Kendall, A., Cipolla, R.: SegNet: a deep convolutional encoder–decoder architecture for image segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 39(12), 2481–2495 (2017)

    Article  Google Scholar 

  30. Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv, pp. 1409.1556 (2014)

  31. Lin, H., Zhang, T., Chen, Z., Song, H., Yang, C.: Adaptive fuzzy gaussian mixture models for shape approximation in robot grasping. Int. J. Fuzzy Syst. 21(4), 1026–1037 (2019)

    Article  MathSciNet  Google Scholar 

  32. Pan, W., Qu, R., Hwang, K.S., Lin, H.S.: An ensemble fuzzy approach for inverse reinforcement learning. Int. J. Fuzzy Syst. 21(1), 95–103 (2019)

    Article  MathSciNet  Google Scholar 

  33. Bernal, J. et al.: Comparative validation of polyp detection methods in video colonoscopy: results from the MICCAI 2015 Endoscopic vision challenge. IEEE Trans. Med. Imaging. 36(6), 1231–1249 (2017)

    Article  Google Scholar 

Download references

Acknowledgement

This work was supported in part by the Key Technology Research and Development Program of Zhejiang Province (2017C03017), the National Natural Science Foundation of China (81672916) and (LQ17H160008), and the National Key R&D Program of China (2017YFC0908200).

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Kefeng Ding.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Hwang, M., Wang, D., Jiang, WC. et al. An Adaptive Regularization Approach to Colonoscopic Polyp Detection Using a Cascaded Structure of Encoder–Decoders. Int. J. Fuzzy Syst. 21, 2091–2101 (2019). https://doi.org/10.1007/s40815-019-00694-y

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s40815-019-00694-y

Keywords

Navigation