Abstract
This report presents the technical details of the approach of Team AIfuture for the Myopic Maculopathy Analysis Challenge Task 3. The approach focuses on the following two aspects: the shift in data distribution between pre-trained and competition datasets, and the diversity of data sample. The ResNet-50 backbone is used to establish a strong baseline, and the first two-stage blocks are frozen. To alleviate the problem of data distribution shift, publicly available medical data is used for self-supervised learning, utilizing the well-known DINO algorithm. Various data augmentation techniques are employed to increase the diversity of data samples. Additionally, it has been observed that using a portion of the training data can significantly improve performance. Finally, test-time data augmentation is used for ensemble prediction, which greatly enhances model performance. The achieved \(R^2\) score of 0.8636 and MAE score of 0.7326 on the test data result in the final rank of 2.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Abdulhussein, D., Hussein, M.A.: Who vision 2020: have we done it? Ophthalmic Epidemiol. 30(4), 331–339 (2023). https://doi.org/10.1080/09286586.2022.2127784. pMID: 36178293
Caron, M., et al.: Emerging properties in self-supervised vision transformers. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 9650–9660 (2021)
Dai, L., Wu, L.H., et al.: A deep learning system for detecting diabetic retinopathy across the disease spectrum. Nat. Commun. 12(1), 1–11 (2021)
Foreman, J., et al.: Association between digital smart device use and myopia: a systematic review and meta-analysis. Lancet Digit. Health 3(12), e806–e818 (2021)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)
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. https://www.sciencedirect.com/science/article/pii/S2666389922001040
Resnikoff, S., et al.: Myopia-a 21st century public health issue. Invest. Ophthalmol. Vis. Sci. 60(3), Mi–Mii (2019)
de Vente, C., et al.: AIROGS: artificial intelligence for robust glaucoma screening challenge. arXiv preprint arXiv:2302.01738 (2023)
Wang, Y.M., Lu, S.Y., Zhang, X.J., Chen, L.J., Pang, C.P., Yam, J.C.: Myopia genetics and heredity. Children 9(3), 382 (2022)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Liu, D., Wei, L., Yang, B. (2024). Self-supervised Learning and Data Diversity Based Prediction of Spherical Equivalent. In: Sheng, B., Chen, H., Wong, T.Y. (eds) Myopic Maculopathy Analysis. MICCAI 2023. Lecture Notes in Computer Science, vol 14563. Springer, Cham. https://doi.org/10.1007/978-3-031-54857-4_10
Download citation
DOI: https://doi.org/10.1007/978-3-031-54857-4_10
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-54856-7
Online ISBN: 978-3-031-54857-4
eBook Packages: Computer ScienceComputer Science (R0)