Skip to main content
Springer Nature Link
Log in

Ensemble learning for retinal disease recognition under limited resources

  • Original Article
  • Published:
Medical & Biological Engineering & Computing Aims and scope Submit manuscript

Abstract

Retinal optical coherence tomography (OCT) images provide crucial insights into the health of the posterior ocular segment. Therefore, the advancement of automated image analysis methods is imperative to equip clinicians and researchers with quantitative data, thereby facilitating informed decision-making. The application of deep learning (DL)-based approaches has gained extensive traction for executing these analysis tasks, demonstrating remarkable performance compared to labor-intensive manual analyses. However, the acquisition of retinal OCT images often presents challenges stemming from privacy concerns and the resource-intensive labeling procedures, which contradicts the prevailing notion that DL models necessitate substantial data volumes for achieving superior performance. Moreover, limitations in available computational resources constrain the progress of high-performance medical artificial intelligence, particularly in less developed regions and countries. This paper introduces a novel ensemble learning mechanism designed for recognizing retinal diseases under limited resources (e.g., data, computation). The mechanism leverages insights from multiple pre-trained models, facilitating the transfer and adaptation of their knowledge to retinal OCT images. This approach establishes a robust model even when confronted with limited labeled data, eliminating the need for an extensive array of parameters, as required in learning from scratch. Comprehensive experimentation on real-world datasets demonstrates that the ensemble models constructed by the proposed ensemble method show superior performance over the baseline models under sparse labeled data, especially the triple ensemble model, which achieves the accuracy of 92.06%, which is 8.27%, 7.99%, and 11.14% better than the three baseline models, respectively. In addition, compared with the three baseline models learned from scratch, the triple ensemble model has fewer trainable parameters, only 3.677M, which is lower than the three baseline models of 8.013M, 4.302M, and 20.158M, respectively.

Graphical abstract

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

Similar content being viewed by others

Notes

  1. A large-scale image dataset comprising real-life images.

References

  1. Lim LS, Mitchell P, Seddon JM, Holz FG, Wong TY (2012) Age-related macular degeneration. The Lancet 379(9827):1728–1738

    Article  Google Scholar 

  2. Pead E, Megaw R, Cameron J, Fleming A, Dhillon B, Trucco E, MacGillivray T (2019) Automated detection of age-related macular degeneration in color fundus photography: a systematic review. Surv Ophthalmol 64(4):498–511

    Article  PubMed  PubMed Central  Google Scholar 

  3. Bhagat N, Grigorian RA, Tutela A, Zarbin MA (2009) Diabetic macular edema: pathogenesis and treatment. Surv Ophthalmol 54(1):1–32

    Article  PubMed  Google Scholar 

  4. Moreira-Neto CA, Moult EM, Fujimoto JG, Waheed NK, Ferrara D et al (2018) Choriocapillaris loss in advanced age-related macular degeneration. J Ophthalmol 2018

  5. Shao Y, Li X-R (2008) Effects of diabetic retinopathy on quality of life. [Zhonghua yan ke za Zhi] Chin J Ophthalmol 44(7):660–663

  6. Drexler W, Fujimoto JG (2008) State-of-the-art retinal optical coherence tomography. Prog Retinal Eye Res 27(1):45–88

    Article  Google Scholar 

  7. Drexler W, Sattmann H, Hermann B, Ko TH, Stur M, Unterhuber A, Scholda C, Findl O, Wirtitsch M, Fujimoto JG et al (2003) Enhanced visualization of macular pathology with the use of ultrahigh-resolution optical coherence tomography. Arch Ophthalmol 121(5):695–706

  8. Hee MR, Puliafito CA, Duker JS, Reichel E, Coker JG, Wilkins JR, Schuman JS, Swanson EA, Fujimoto JG (1998) Topography of diabetic macular edema with optical coherence tomography. Ophthalmology 105(2):360–370

    Article  PubMed  CAS  Google Scholar 

  9. Bowd C, Zangwill LM, Berry CC, Blumenthal EZ, Vasile C, Sanchez-Galeana C, Bosworth CF, Sample PA, Weinreb RN (2001) Detecting early glaucoma by assessment of retinal nerve fiber layer thickness and visual function. Invest Ophthalmol Vis Sci 42(9):1993–2003

    PubMed  CAS  Google Scholar 

  10. Ergun E, Hermann B, Wirtitsch M, Unterhuber A, Ko TH, Sattmann H, Scholda C, Fujimoto JG, Stur M, Drexler W (2005) Assessment of central visual function in Stargardt’s disease/fundus flavimaculatus with ultrahigh-resolution optical coherence tomography. Invest Ophthalmol Vis Sci 46(1):310–316

    Article  PubMed  Google Scholar 

  11. Chen S, Shu T, Zhao H, Tang YY (2023) Mask-CNN-transformer for real-time multi-label weather recognition. Knowl Based Syst 278:110881

  12. Chen S, Shu T, Zhao H, Zhong G, Chen X (2023) TempEE: temporal-spatial parallel transformer for radar echo extrapolation beyond auto-regression. IEEE Trans Geosci Rem Sens

  13. Chen S, Long G, Shen T, Zhou T, Jiang J (2023) Spatial-temporal prompt learning for federated weather forecasting. arXiv preprint arXiv:2305.14244

  14. Usman M, Fraz MM, Barman SA (2017) Computer vision techniques applied for diagnostic analysis of retinal oct images: a review. Arch Comput Methods Eng 24:449–465

    Article  Google Scholar 

  15. Sunnetci KM, Alkan A (2023) Biphasic majority voting-based comparative COVID-19 diagnosis using chest X-ray images. Expert Syst App 216:119430

  16. Chen S, Ren S, Wang G, Huang M, Xue C (2023) Interpretable CNN-multilevel attention transformer for rapid recognition of pneumonia from chest X-ray images. IEEE J Biomed Health Informat

  17. Peng H, Chen S, Niu N, Wang J, Yao Q, Wang L, Wang Y, Tang J, Wang G, Huang M et al (2023) Diffusion model in semi-supervised scleral segmentation. In: 2023 IEEE 6th International conference on pattern recognition and artificial intelligence (PRAI), pp 376–382. IEEE

  18. Lee CS, Baughman DM, Lee AY (2017) Deep learning is effective for classifying normal versus age-related macular degeneration OCT images. Ophthalmol Retina 1(4):322–327

    Article  PubMed  PubMed Central  Google Scholar 

  19. Huang L, He X, Fang L, Rabbani H, Chen X (2019) Automatic classification of retinal optical coherence tomography images with layer guided convolutional neural network. IEEE Signal Process Lett 26(7):1026–1030

    Article  Google Scholar 

  20. Mohan R, Ganapathy K, Arunmozhi R (2022) Comparison of the proposed DCNN model with standard cnn architectures for retinal diseases classification. Journal of Population Therapeutics and Clinical Pharmacology= Journal de la Therapeutique des Populations et de la Pharmacologie Clinique 29(3):112–122

  21. Sunija A, Kar S, Gayathri S, Gopi VP, Palanisamy P (2021) Octnet: a lightweight CNN for retinal disease classification from optical coherence tomography images. Comput Methods Prog Biomed 200:105877

  22. Thomas A, Harikrishnan P, Krishna AK, Ponnusamy P, Gopi VP (2021) Automated detection of age-related macular degeneration from oct images using multipath CNN. J Comput Sci Eng 15(1):34–46

    Article  Google Scholar 

  23. He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770–778

  24. Huang G, Liu Z, Van Der Maaten L, Weinberger KQ (2017) Densely connected convolutional networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4700–4708

  25. Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A (2015) Going deeper with convolutions. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1–9

  26. Lee T, Yoo S (2021) Augmenting few-shot learning with supervised contrastive learning. Ieee Access 9:61466–61474

    Article  Google Scholar 

  27. Chen J, Zhuo L, Wei Z, Zhang H, Fu H, Jiang Y-G (2023) Knowledge driven weights estimation for large-scale few-shot image recognition. Pattern Recogn 142:109668

  28. Zheng Z, Feng X, Yu H, Gao M (2022) Cooperative density-aware representation learning for few-shot visual recognition. Neurocomputing 471:208–218

    Article  Google Scholar 

  29. Kim J, Chi M (2021) SAFFNet: self-attention-based feature fusion network for remote sensing few-shot scene classification. Remote Sens 13(13):2532

    Article  CAS  Google Scholar 

  30. Zhu Y, Min W, Jiang S (2020) Attribute-guided feature learning for few-shot image recognition. IEEE Trans Multimed 23:1200–1209

  31. Lim JY, Lim KM, Ooi SY, Lee CP (2021) Efficient-prototypicalnet with self knowledge distillation for few-shot learning. Neurocomputing 459:327–337

    Article  Google Scholar 

  32. Wei M, Wu Q, Ji H, Wang J, Lyu T, Liu J, Zhao L (2023) A skin disease classification model based on densenet and convnext fusion. Electronics 12(2):438

    Article  Google Scholar 

  33. Li W, Du L, Liao J, Yin D, Xu X (2021) Classification of COVID-19 images based on transfer learning and feature fusion. Imaging Sci J 69(1–4):133–142

    Article  Google Scholar 

  34. Liu W, Ouyang H, Liu Q, Cai S, Wang C, Xie J, Hu W (2022) Image recognition for garbage classification based on transfer learning and model fusion. Math Prob Eng 2022

  35. Ai Z, Huang X, Feng J, Wang H, Tao Y, Zeng F, Lu Y (2022) FN-OCT: disease detection algorithm for retinal optical coherence tomography based on a fusion network. Front Neuroinformat 16:876927

  36. Latha V, Ashok L, Sreeni K (2021) Automated macular disease detection using retinal optical coherence tomography images by fusion of deep learning networks. In: 2021 National conference on communications (NCC), pp 1–6. IEEE

  37. Kermany DS, Goldbaum M, Cai W, Valentim CC, Liang H, Baxter SL, McKeown A, Yang G, Wu X, Yan F et al (2018) Identifying medical diagnoses and treatable diseases by image-based deep learning. cell 172(5):1122–1131

  38. Deng J, Dong W, Socher R, Li L-J, Li K, Fei-Fei L (2009) Imagenet: a large-scale hierarchical image database. In: 2009 IEEE Conference on computer vision and pattern recognition, pp 248–255. Ieee

  39. Glorot X, Bordes A, Bengio Y (2011) Deep sparse rectifier neural networks. In: Proceedings of the fourteenth international conference on artificial intelligence and statistics, pp 315–323. JMLR Workshop and Conference Proceedings

  40. Kingma DP, Ba J (2014) Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980

  41. Loshchilov I, Hutter F (2016) SGDR: stochastic gradient descent with warm restarts. arXiv preprint arXiv:1608.03983

  42. Sokolova M, Lapalme G (2009) A systematic analysis of performance measures for classification tasks. Inf Process Manag 45(4):427–437

    Article  Google Scholar 

  43. Powers DM (2020) Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation. arXiv preprint arXiv:2010.16061

  44. Davis J, Goadrich M (2006) The relationship between precision-recall and ROC curves. In: Proceedings of the 23rd international conference on machine learning, pp 233–240

  45. Oğuz FE, Alkan A, Schöler T (2023) Emotion detection from ECG signals with different learning algorithms and automated feature engineering. SIViP 1–9

  46. El-Nouby A, Izacard G, Touvron H, Laptev I, Jegou H, Grave E (2021) Are large-scale datasets necessary for self-supervised pre-training? arXiv preprint arXiv:2112.10740

  47. Chen H, Wang Y, Guo T, Xu C, Deng Y, Liu Z, Ma S, Xu C, Xu C, Gao W (2021) Pre-trained image processing transformer. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 12299–12310

  48. Malla S, Alphonse P (2021) COVID-19 outbreak: an ensemble pre-trained deep learning model for detecting informative tweets. Appl Soft Comput 107:107495

  49. Noor FA, Munzerin I, Iqbal AA, Islam T, Hossain E (2021) An ensemble learning based approach to autonomous COVID19 detection using transfer learning with the help of pre-trained deep neural network models. In: 2021 24th International conference on computer and information technology (ICCIT), pp 1–6. IEEE

  50. Rahman Z, Hossain MS, Islam MR, Hasan MM, Hridhee RA (2021) An approach for multiclass skin lesion classification based on ensemble learning. Inform Med Unlocked 25:100659

Download references

Author information

Authors and Affiliations

  1. School of Information and Communication Engineering, Hainan University, Haikou, 570228, China

    Jiahao Wang, Hong Peng & Sufen Ren

  2. Australian AI Institute, School of Computer Science, FEIT, University of Technology Sydney, Sydney, 2008, NSW, Australia

    Shengchao Chen

Authors
  1. Jiahao Wang
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Hong Peng
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. Shengchao Chen
    View author publications

    You can also search for this author inPubMed Google Scholar

  4. Sufen Ren
    View author publications

    You can also search for this author inPubMed Google Scholar

Corresponding authors

Correspondence to Shengchao Chen or Sufen Ren.

Ethics declarations

Conflict of interest

The authors declare no competing interests.

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

Wang, J., Peng, H., Chen, S. et al. Ensemble learning for retinal disease recognition under limited resources. Med Biol Eng Comput 62, 2839–2852 (2024). https://doi.org/10.1007/s11517-024-03101-3

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11517-024-03101-3

Keywords