Abstract
Diabetic retinopathy (DR) is a complication of diabetes, and one of the major causes of vision impairment in the global population. As the early-stage manifestation of DR is usually very mild and hard to detect, an accurate diagnosis via eye-screening is clinically important to prevent vision loss at later stages. In this work, we propose an ensemble method to automatically grade DR using ultra-wide optical coherence tomography angiography (UW-OCTA) images available from Diabetic Retinopathy Analysis Challenge (DRAC) 2022. First, we adopt the state-of-the-art classification networks, i.e., ResNet, DenseNet, EfficientNet, and VGG, and train them to grade UW-OCTA images with different splits of the available dataset. Ultimately, we obtain 25 models, of which, the top 16 models are selected and ensembled to generate the final predictions. During the training process, we also investigate the multi-task learning strategy, and add an auxiliary classification task, the Image Quality Assessment, to improve the model performance. Our final ensemble model achieved a quadratic weighted kappa (QWK) of 0.9346 and an Area Under Curve (AUC) of 0.9766 on the internal testing dataset, and the QWK of 0.839 and the AUC of 0.8978 on the DRAC challenge testing dataset.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Wang, W., Lo, ACY.: Diabetic Retinopathy: Pathophysiology and Treatments. Int. J. Mol. Sci. 19(6), 1816 (2018). https://doi.org/10.3390/ijms19061816
Mookiah, M.R.K., Acharya, U.R.A., Chua, C.K., Lim, C.M., Ng, E.Y.K., Laude, A.: Computer-aided diagnosis of diabetic retinopathy: a review. Comput. Biol. Med. 43(12), 2136–2155 (2013). https://doi.org/10.1016/j.compbiomed.2013.10.007
Overview, Diabetic Retinopathy. https://www.nhs.uk/conditions/diabetic-retinopathy/
Khalili Pour, E., Rezaee, K., Azimi, H., et al.: Automated machine learning-based classification of proliferative and non-proliferative diabetic retinopathy using optical coherence tomography angiography vascular density maps. Graefes Arch. Clin. Exp. Ophthalmol. (2022). https://doi.org/10.1007/s00417-022-05818-z
Abdelsalam, M., Zahran, M.A.: A Novel approach of diabetic retinopathy early detection based on multifractal geometry analysis for OCTA macular images using support vector machine, pp. 22844–22858. IEEE Access (2021). https://doi.org/10.1109/ACCESS.2021.3054743
Selvathi, D., Suganya, K.: Support vector machine based method for automatic detection of diabetic eye disease using thermal images. In: 2019 1st International Conference on Innovations in Information and Communication Technology (ICIICT), pp. 1–6 (2019). https://doi.org/10.1109/ICIICT1.2019.8741450
Alzami, F., et al.: Diabetic retinopathy grade classification based on fractal analysis and random forest. In: 2019 International Seminar on Application for Technology of Information and Communication (iSemantic), pp. 272–276 (2019). https://doi.org/10.1109/ISEMANTIC.2019.8884217
Eladawi, N., et al.: Early signs detection of diabetic retinopathy using optical coherence tomography angiography scans based on 3D multi-path convolutional neural network. In: 2019 IEEE International Conference on Image Processing (ICIP), pp. 1390–1394 (2019). https://doi.org/10.1109/ICIP.2019.8803031
Abdelmaksoud, E., et al.: Automatic diabetic retinopathy grading system based on detecting multiple retinal lesions. IEEE Access. 9, 15939–15960 (2021). https://doi.org/10.1109/ACCESS.2021.3052870
Heisler, M. et al.: Ensemble deep learning for diabetic retinopathy detection using optical coherence tomography angiography. Transl. Vision Sci. Technol. 9(20), 15939–15960 (2021). https://doi.org/10.1167/tvst.9.2.20
Ryu, G., et al.: A deep learning model for identifying diabetic retinopathy using optical coherence tomography angiography. Sci. Rep. 11, 1–9 (2021). https://doi.org/10.1038/s41598-021-02479-6
Dai, L., Wu, L., Li, H., et al.: A deep learning system for detecting diabetic retinopathy across the disease spectrum. Nat. Commun. 12(1), 1–11 (2021). https://doi.org/10.1038/s41467-021-23458-5
Liu, R., Wang, X., Wu, Q., et al.: DeepDRiD: diabetic retinopathy-grading and image quality estimation challenge. Patterns 3(6), 100512 (2022). https://doi.org/10.1016/j.patter.2022.100512
Sheng, B., Chen, X., Li, T., Ma, T., Yang, Y., Bi, L., Zhang, X.: An overview of artificial intelligence in diabetic retinopathy and other ocular diseases. Front. Public Health (2022). https://doi.org/10.3389/fpubh.2022.971943
Sechidis, K., Tsoumakas, G., Vlahavas, I.: On the stratification of multi-label data. In: Gunopulos, D., Hofmann, T., Malerba, D., Vazirgiannis, M. (eds.) ECML PKDD 2011. LNCS (LNAI), vol. 6913, pp. 145–158. Springer, Heidelberg (2011). https://doi.org/10.1007/978-3-642-23808-6_10
He, K., Zhang, X., Ren, S., Sun, J.: Deep Residual Learning for Image Recognition. CoRR (2015). arXiv:1512.03385
Huang, G., Liu, Z., Maaten, L., Weinberger, K.: Densely Connected Convolutional Networks. CoRR(2016). arXiv:1608.06993
Tan, M., Le, Q.: EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks. CoRR(2019). arXiv:1905.11946
Simonyan, K., Zisserman, A: Very deep convolutional networks for large-scale image recognition. In: ICLR (2015). arxiv:1409.1556
Dhodapkar, R.M., et al.: Deep learning for quality assessment of optical coherence tomography angiography images. Sci. Rep. (2022). https://doi.org/10.1038/s41598-022-17709-8
Jin, K., et al.: Multimodal deep learning with feature level fusion for identification of choroidal neovascularization activity in age-related macular degeneration. Acta Ophthalmologica. 100(2), 512–520 (2021). https://doi.org/10.1111/aos.14928
Padmasini, N. et al.: Automated detection of multiple structural changes of diabetic macular oedema in SDOCT retinal images through transfer learning in CNNs. IET Image Process. 14(16), 4067–4075 (2021). https://doi.org/10.1049/iet-ipr.2020.0612
Le, D., et al.: Transfer learning for automated OCTA detection of diabetic retinopathy. Transl. Vision Sci. Technol. 9(2) (2020). https://doi.org/10.1167/tvst.9.2.35
Pham, K.: Ensemble learning-based classification models for slope stability analysis. CATENA 196 (2021). https://doi.org/10.1016/j.catena.2020.104886
Mu, X., Watta, P., Hassoun, M.: Analysis of a plurality voting-based combination of classifiers. Neural Process. Lett. 29, 89–107 (2009)
Ruder, S.: An Overview of Multi-Task Learning in Deep Neural Networks. CoRR (2017). arXiv:1706.05098
Deng, J., et al.: ImageNet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248–255 (2009). CVPR.2009.5206848
Cawley, G.C., Talbot, N.L.C.: On over-fitting in model selection and subsequent selection bias in performance evaluation. J. Mach. Learn. Res. 11, 2079–2107 (2010)
Bourigault, E., et al.: Multimodal PET/CT tumour segmentation and prediction of progression-free survival using a full-scale UNet with attention. In: Andrearczyk, V., Oreiller, V., Hatt, M., Depeursinge, A. (eds.) Head and Neck Tumor Segmentation and Outcome Prediction. HECKTOR 2021. LNCS, vol. 13209, pp. 189–201. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-98253-9_18
Liu, S., et al.: Auto-Lambda: Disentangling Dynamic Task Relationships. CoRR (2022). arxiv:2202.03091
Fifty, C., et al.: Efficiently Identifying Task Groupings for Multi-Task Learning. CoRR (2021). arxiv:2109.04617
Ruder, S.: An Overview of Multi-Task Learning in Deep Neural Networks. CoRR (2017). arxiv:1706.05098
Sheng, B., et al.: Diabetic retinopathy analysis challenge 2022. In: 25th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI 2022) (2022). https://doi.org/10.5281/zenodo.6362349
Acknowledgment
The authors acknowledge the DRAC2022 challenge for available UW-OCTA images for this study [34]. The authors would like to thank Dr. Le Zhang from University of Oxford for helpful comments on our manuscript.
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Zheng, Y., Wu, F., Papież, B.W. (2023). An Ensemble Method to Automatically Grade Diabetic Retinopathy with Optical Coherence Tomography Angiography Images. In: Sheng, B., Aubreville, M. (eds) Mitosis Domain Generalization and Diabetic Retinopathy Analysis. MIDOG DRAC 2022 2022. Lecture Notes in Computer Science, vol 13597. Springer, Cham. https://doi.org/10.1007/978-3-031-33658-4_6
Download citation
DOI: https://doi.org/10.1007/978-3-031-33658-4_6
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-33657-7
Online ISBN: 978-3-031-33658-4
eBook Packages: Computer ScienceComputer Science (R0)