Skip to main content
Springer Nature Link
Log in

An ensemble framework of deep neural networks for colorectal polyp classification

  • Track 2: Medical Applications of Multimedia
  • Published:
Multimedia Tools and Applications Aims and scope Submit manuscript

Abstract

Colorectal cancer (CRC) is caused by malignant polyps which must be resected and examined for accurate classification. Biopsy, the manual workflow of polyp classification is time-intensive task and requires an automated solution. The objective of this study is to develop an accurate virtual biopsy tool for polyp classification. Moreover, automated assessment of polyps is a challenging task due to the similarities in their patterns, and in contrast to existing studies on binary classification, the outcome of multi-class classification requires evaluation through advanced evaluation measures. The proposed method combined the strength of individual weak learner for an accurate weighted-average ensemble deep learning classification. At first, base-classifiers were pretrained on the ImageNet database. Second, an average ensemble was built and evaluated for enhancing the performance, an appropriate combination of weights was chosen through grid search and assigned to the models. The performance evaluation of the proposed method in terms of F1-micro (0.80), F1-macro (0.81), F1-weighted (0.84) metrics, model reliability using Cohen’s Kappa Coefficient (0.60) and Mathew Correlation Co-efficient value (0.49) for binary dataset shows the superiority over existing models. The higher rates of precision and recall show potential usage of the proposed system in the development of a virtual biopsy tool.

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

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

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
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10

Similar content being viewed by others

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

References

  1. Chan HP, Samala RK, Hadjiiski LM, Zhou C (2020) Deep learning in medical image analysis. In: Lee G, Fujita H (eds) Deep Learning in Medical Image Analysis. Advances in Experimental Medicine and Biology, vol 1213. Springer, Cham. https://doi.org/10.1007/978-3-030-33128-3.1

  2. Chen-Ming H, Chien-Chang H, Zhe-Ming H, Feng-Yu S, Meng-Lin C, Tsung-Hsing C (2021) Colorectal polyp image detection and classification through grayscale images and deep learning. Sensors 21(18):5995

    Article  Google Scholar 

  3. Corley DA, Jensen CD, Marks AR, Zhao WK, Lee JK, Doubeni CA, Zauber AG, de Boer J, Fireman BH, Schottinger JE, Quinn VP (2014) Adenoma detection rate and risk of colorectal cancer and death. New England J Med 370(14):1298–1306. https://doi.org/10.1056/NEJMoa1309086

    Article  Google Scholar 

  4. Geboes K, Geboes K, Jouret-Mourin A (2013) Endoscopy and histopathology. Endoscopy 1:3–32. https://doi.org/10.5772/52739

    Article  Google Scholar 

  5. Gomes HM, Barddal JP, Enembreck F, Bifet A (2017) A survey on ensemble learning for data stream classification. ACM Comput Surveys (CSUR) 50(2):1–36

    Article  Google Scholar 

  6. Guanghui, W (2021) Replication Data for: Colonoscopy Polyp Detection and Classification: Dataset Creation and Comparative Evaluations, Harvard Dataverse, v1, https://doi.org/10.7910/DVN/FCBUOR

  7. Ishaq S, Siau K, Harrison E, Tontini GE, Hoffman A, Gross S, Kiesslich R, Neumann H (2017) Technological advances for improving adenoma detection rates: the changing face of colonoscopy. Dig Liver Dis 49(7):721–727

    Article  Google Scholar 

  8. Jae KY, Pyo BJ, Jun-Won C, Dong KP, Kwang GK, Yoon Jae K (2021) New polyp image classification technique using transfer learning of network-in-network structure in endoscopic images. Sci Rep 11(1):1–8

    Google Scholar 

  9. Jason WW, Arief AS, Vaickus LJ, Bing R, Xiaoying L, Mikhail L, Naofumi To, Behnaz A, Adam SK, Dale CS (2020) Evaluation of a deep neural network for automated classification of colorectal polyps on histopathologic slides. JAMA Netw Open 3(4):e203398–e203398

    Article  Google Scholar 

  10. Kaminski MF, Regula J, Kraszewska E, Polkowski M, Wojciechowska U, Didkowska J, Zwierko M, Rupinski M, Nowacki MP, Butruk E (2010) Quality indicators for colonoscopy and the risk of interval cancer. N Engl J Med 362(19):1795–1803. https://doi.org/10.1056/NEJMoa0907667

    Article  Google Scholar 

  11. Kaminski MF, Thomas-Gibson S, Bugajski M, Bretthauer M, Rees CJ, Dekker E, Hoff G, Jover R, Suchanek S, Ferlitsch M, Anderson J (2017) Performance measures for lower gastrointestinal endoscopy: a European Society of Gastrointestinal Endoscopy (ESGE) quality improvement initiative. Endoscopy 49(04):378–397

    Article  Google Scholar 

  12. Kim NH, Jung YS, Jeong WS, Yang HJ, Park SK, Choi K, Park DI (2017) Miss rate of colorectal neoplastic polyps and risk factors for missed polyps in consecutive colonoscopies. Intestinal Res 15(3):411. https://doi.org/10.5217/ir.2017.15.3.411

    Article  Google Scholar 

  13. Kim J, Hong J, Park H (2018) Prospects of deep learning for medical imaging. Precision Future Med 2(2):37–52

    Article  Google Scholar 

  14. Levin B, Lieberman DA, McFarland B, Andrews KS, Brooks D, Bond J, Dash C, Giardiello FM, Glick S, Johnson D, Johnson CD (2008) Screening and surveillance for the early detection of colorectal cancer and adenomatous polyps, 2008: a joint guideline from the American Cancer Society, the US multi-society task force on colorectal Cancer, and the American College of Radiology. Gastroenterology 134(5):15701595

    Article  Google Scholar 

  15. Lyon, F (2018) International Agency for Research on Cancer. Colorectal cancer factsheet, Int Agency Res Cancer

  16. McHugh ML (2012) Interrater reliability: the kappa statistic. Biochemia Med 22(3):276–282

    Article  MathSciNet  Google Scholar 

  17. Min JK, Kwak MS, Cha JM (2019) Overview of deep learning in gastrointestinal endoscopy. Gut Liver 13(4):388

    Article  Google Scholar 

  18. Nogueira-Rodríguez A, Domínguez-Carbajales R, López-Fernández H, Iglesias A, Cubiella J, Fdez-Riverola F, Reboiro-Jato M, Glez-Peña D (2021) Deep neural networks approaches for detecting and classifying colorectal polyps. Neurocomputing 423:721–734. https://doi.org/10.1016/j.neucom.2020.02.123

    Article  Google Scholar 

  19. Ozawa, T, Ishihara, S, Fujishiro, M, Kumagai, Y, Shichijo, S, Tada, T, (2020) Automated endoscopic detection and classification of colorectal polyps using convolutional neural networks Ther Adv Gastroenterol, 13

  20. Poudel S, Kim YJ, Vo DM, Lee SW (2020) Colorectal disease classification using efficiently scaled dilation in convolutional neural network. IEEE Access 8:99227–99238. https://doi.org/10.1109/ACCESS.2020.2996770

    Article  Google Scholar 

  21. Rahman, MM, Wadud, MAH, Hasan, MM (2021) Computerized classification of gastrointestinal polyps using stacking ensemble of convolutional neural network. Inf Med Unlocked, p.100603. https://doi.org/10.1016/j.imu.2021.100603.

  22. Sànchez-Peralta LF, Pagador JB, Picòn A, Calderòn AJ, Polo F, Andraka N, Bilbao R, Glover B, Saratxaga CL, Sànchez-Margallo FM (2020) PICCOLO white-light and narrowband imaging Colonoscopic dataset: A performance comparative of models and datasets. Appl Sci 10(23):8501. https://doi.org/10.3390/app10238501

    Article  Google Scholar 

  23. Sebastian P, Daniel S, Begonya G, Cristian C, Adel E (2020) Kudo’s classification for colon polyps assessment using a deep learning approach. Appl Sci 10(2):501

    Article  Google Scholar 

  24. Shen D, Wu G, Suk HI (2017) Deep learning in medical image analysis. Annu Rev Biomed Eng 19:221–248

    Article  Google Scholar 

  25. Siegel RL, Miller KD, Fuchs HE, Jemal A (2021) Cancer statistics, 2021. CA Cancer J Clin 71(1):7–33

    Article  Google Scholar 

  26. Sohail, A, Khan, A, Nisar, H, Tabassum, S, Zameer, A, (2021) Mitotic nuclei analysis in breast Cancer histopathology images using deep ensemble classifier. Med Image Anal, p.102121. https://doi.org/10.1016/j.media.2021.102121.

  27. Suzuki K (2012) A review of computer-aided diagnosis in thoracic and colonic imaging. Quant Imaging Med Surg 2(3):163. https://doi.org/10.3978/j.issn.2223-4292.2012.09.02

    Article  Google Scholar 

  28. Yoriaki K, Hisashi H, Tomohiro W, Takanobu N, Misaki K, Toshi- haru S., Ayana O., Tomohiro M., Masashi K., Tadaaki A. (2017) Computeraided diagnosis based on convolutional neural network sys- tem for colorectal polyp classification: preliminary experience. Oncology 93(Suppl. 1):30–34

    Article  Google Scholar 

  29. Zachariah R, Samarasena J, Luba D, Duh E, Dao T, Requa J, Ninh A, Karnes W (2020) Prediction of polyp pathology using convolutional neural networks achieves ‘resect and discard’ thresholds. Am J Gastroenterol 115(1):138

    Article  Google Scholar 

Download references

Acknowledgments

The authors would like to thank Basque Biobank who kindly provided us the access to their PICCOLO RGB/NBI database.

Author information

Author notes

  1. Muhammad Usman and Wei Qi Yan contributed equally to this work.

Authors and Affiliations

  1. Auckland University of Technology, 55 Wellesley Street East, Auckland CBD, Auckland, 1010, New Zealand

    Farah Younas, Muhammad Usman & Wei Qi Yan

  2. Shaheed Zulfikar Ali Bhutto Institute of Science and Technology, Islamabad, 44000, Pakistan

    Muhammad Usman

Authors
  1. Farah Younas
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Muhammad Usman
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. Wei Qi Yan
    View author publications

    You can also search for this author inPubMed Google Scholar

Corresponding author

Correspondence to Farah Younas.

Ethics declarations

Competing interests

The authors declare no known potential competing interests with respect to financial interests or the research, authorship, and publication of this article.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Younas, F., Usman, M. & Yan, W.Q. An ensemble framework of deep neural networks for colorectal polyp classification. Multimed Tools Appl 82, 18925–18946 (2023). https://doi.org/10.1007/s11042-022-14177-0

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-022-14177-0

Keywords