Papers
Topics
Authors
Recent
Search
2000 character limit reached

Robust deep learning for eye fundus images: Bridging real and synthetic data for enhancing generalization

Published 25 Mar 2022 in eess.IV, cs.CV, and cs.LG | (2203.13856v2)

Abstract: Deep learning applications for assessing medical images are limited because the datasets are often small and imbalanced. The use of synthetic data has been proposed in the literature, but neither a robust comparison of the different methods nor generalizability has been reported. Our approach integrates a retinal image quality assessment model and StyleGAN2 architecture to enhance Age-related Macular Degeneration (AMD) detection capabilities and improve generalizability. This work compares ten different Generative Adversarial Network (GAN) architectures to generate synthetic eye-fundus images with and without AMD. We combined subsets of three public databases (iChallenge-AMD, ODIR-2019, and RIADD) to form a single training and test set. We employed the STARE dataset for external validation, ensuring a comprehensive assessment of the proposed approach. The results show that StyleGAN2 reached the lowest Frechet Inception Distance (166.17), and clinicians could not accurately differentiate between real and synthetic images. ResNet-18 architecture obtained the best performance with 85% accuracy and outperformed the two human experts (80% and 75%) in detecting AMD fundus images. The accuracy rates were 82.8% for the test set and 81.3% for the STARE dataset, demonstrating the model's generalizability. The proposed methodology for synthetic medical image generation has been validated for robustness and accuracy, with free access to its code for further research and development in this field.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (63)
  1. Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs. Jama, 316(22):2402–2410, 2016.
  2. Deep image mining for diabetic retinopathy screening. Medical image analysis, 39:178–193, 2017.
  3. Automated identification of diabetic retinopathy using deep learning. Ophthalmology, 124(7):962–969, 2017.
  4. Clinically applicable deep learning for diagnosis and referral in retinal disease. Nature medicine, 24(9):1342–1350, 2018.
  5. Introducing a novel layer in convolutional neural network for automatic identification of diabetic retinopathy. In 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), pages 5938–5941. IEEE, 2018.
  6. Automated diagnosis of plus disease in retinopathy of prematurity using deep convolutional neural networks. JAMA ophthalmology, 136(7):803–810, 2018.
  7. Exudate detection in fundus images using deeply-learnable features. Computers in biology and medicine, 104:62–69, 2019.
  8. Assessment of deep generative models for high-resolution synthetic retinal image generation of age-related macular degeneration. JAMA ophthalmology, 137(3):258–264, 2019.
  9. Automated grading of age-related macular degeneration from color fundus images using deep convolutional neural networks. JAMA ophthalmology, 135(11):1170–1176, 2017.
  10. Utility of deep learning methods for referability classification of age-related macular degeneration. JAMA ophthalmology, 136(11):1305–1307, 2018.
  11. Use of deep learning for detailed severity characterization and estimation of 5-year risk among patients with age-related macular degeneration. JAMA ophthalmology, 136(12):1359–1366, 2018.
  12. A deep learning algorithm for prediction of age-related eye disease study severity scale for age-related macular degeneration from color fundus photography. Ophthalmology, 125(9):1410–1420, 2018.
  13. A guide to deep learning in healthcare. Nature medicine, 25(1):24–29, 2019.
  14. Adam: Automatic detection challenge on age-related macular degeneration. IEEE Dataport, 2020.
  15. Fundus images analysis using deep features for detection of exudates, hemorrhages and microaneurysms. BMC ophthalmology, 18(1):1–13, 2018.
  16. A novel color space of fundus images for automatic exudates detection. Biomedical signal processing and control, 49:240–249, 2019.
  17. A close look at deep learning with small data. In 2020 25th International Conference on Pattern Recognition (ICPR), pages 2490–2497. IEEE, 2021.
  18. The effectiveness of data augmentation in image classification using deep learning. arXiv preprint arXiv:1712.04621, 2017.
  19. Generative adversarial networks. arXiv preprint arXiv:1406.2661, 2014.
  20. Gan-based synthetic medical image augmentation for increased cnn performance in liver lesion classification. Neurocomputing, 321:321–331, 2018.
  21. Assisting barrett’s esophagus identification using endoscopic data augmentation based on generative adversarial networks. Computers in Biology and Medicine, page 104029, 2020.
  22. Fine-tuning generative adversarial networks using metaheuristics: A case study on barrett’s esophagus identification. In Bildverarbeitung für die Medizin 2021. Proceedings, German Workshop on Medical Image Computing, Regensburg, March 7-9, 2021, pages 205–210. Springer Vieweg, 2021.
  23. Generalization of deep neural networks for chest pathology classification in x-rays using generative adversarial networks. In 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 990–994. IEEE, 2018.
  24. Esrgan: Enhanced super-resolution generative adversarial networks. In Proceedings of the European conference on computer vision (ECCV) workshops, pages 0–0, 2018.
  25. Enhancing portable oct image quality via gans for ai-based eye disease detection. In International Workshop on Distributed, Collaborative, and Federated Learning, pages 155–167. Springer, 2022.
  26. Unsupervised super-resolution of oct images using generative adversarial network for improved age-related macular degeneration diagnosis. IEEE Sensors Journal, 20(15):8746–8756, 2020.
  27. Applications of deep learning in fundus images: A review. Medical Image Analysis, 69:101971, 2021.
  28. Generative adversarial networks (gans) for retinal fundus image synthesis. In Asian Conference on Computer Vision, pages 289–302. Springer, 2018.
  29. Progressive growing of gans for improved quality, stability, and variation. arXiv preprint arXiv:1710.10196, 2017.
  30. Fundusgan: Fundus image synthesis based on semi-supervised learning. Biomedical Signal Processing and Control, 86:105289, 2023.
  31. An empirical study of preprocessing techniques with convolutional neural networks for accurate detection of chronic ocular diseases using fundus images. Applied Intelligence, 53(2):1548–1566, 2023.
  32. Synthetic artificial intelligence using generative adversarial network for retinal imaging in detection of age-related macular degeneration. Frontiers in Medicine, 10:1184892, 2023.
  33. Syntheye: Investigating the impact of synthetic data on artificial intelligence-assisted gene diagnosis of inherited retinal disease. Ophthalmology Science, 3(2):100258, 2023.
  34. Jost B Jonas. Global prevalence of age-related macular degeneration. The Lancet Global Health, 2(2):e65–e66, 2014.
  35. Global prevalence of age-related macular degeneration and disease burden projection for 2020 and 2040: a systematic review and meta-analysis. The Lancet Global Health, 2(2):e106–e116, 2014.
  36. Patricia T Harvey. Common eye diseases of elderly people: identifying and treating causes of vision loss. Gerontology, 49(1):1–11, 2003.
  37. Evaluation of retinal image quality assessment networks in different color-spaces. In International Conference on Medical Image Computing and Computer-Assisted Intervention, pages 48–56. Springer, 2019.
  38. Training generative adversarial networks with limited data. In Proc. NeurIPS, 2020.
  39. Retinal fundus multi-disease image dataset (rfmid): A dataset for multi-disease detection research. Data, 6(2):14, 2021.
  40. Gans trained by a two time-scale update rule converge to a local nash equilibrium. Advances in neural information processing systems, 30, 2017.
  41. Unsupervised representation learning with deep convolutional generative adversarial networks. arXiv preprint arXiv:1511.06434, 2015.
  42. Least squares generative adversarial networks. In Proceedings of the IEEE international conference on computer vision, pages 2794–2802, 2017.
  43. Wasserstein generative adversarial networks. In International conference on machine learning, pages 214–223. PMLR, 2017.
  44. Improved training of wasserstein gans. arXiv preprint arXiv:1704.00028, 2017.
  45. On convergence and stability of gans. arXiv preprint arXiv:1705.07215, 2017.
  46. Energy-based generative adversarial network. arXiv preprint arXiv:1609.03126, 2016.
  47. Began: Boundary equilibrium generative adversarial networks. arXiv preprint arXiv:1703.10717, 2017.
  48. Conditional generative adversarial nets. arXiv preprint arXiv:1411.1784, 2014.
  49. Conditional image synthesis with auxiliary classifier gans. In International conference on machine learning, pages 2642–2651. PMLR, 2017.
  50. Adam: A method for stochastic optimization, 2017.
  51. Imagenet: A large-scale hierarchical image database. In 2009 IEEE conference on computer vision and pattern recognition, pages 248–255. Ieee, 2009.
  52. Squeezenet: Alexnet-level accuracy with 50x fewer parameters and¡ 0.5 mb model size. arXiv preprint arXiv:1602.07360, 2016.
  53. Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems, 25:1097–1105, 2012.
  54. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 770–778, 2016.
  55. Weighted random sampling. In Ming-Yang Kao, editor, Encyclopedia of Algorithms, pages 1024–1027, Boston, MA, 2008. Springer US.
  56. Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems, 32, 2019.
  57. Grad-cam: Visual explanations from deep networks via gradient-based localization. In Proceedings of the IEEE international conference on computer vision, pages 618–626, 2017.
  58. Automated detection of age-related macular degeneration in color fundus photography: a systematic review. survey of ophthalmology, 64(4):498–511, 2019.
  59. Deep learning for detection of age-related macular degeneration: A systematic review and meta-analysis of diagnostic test accuracy studies. Plos one, 18(4):e0284060, 2023.
  60. A new and improved method for automated screening of age-related macular degeneration using ensemble deep neural networks. In 2018 40th Annual international conference of the IEEE engineering in medicine and biology society (EMBC), pages 702–705. IEEE, 2018.
  61. Development and validation of a deep-learning algorithm for the detection of neovascular age-related macular degeneration from colour fundus photographs. Clinical & Experimental Ophthalmology, 47(8):1009–1018, 2019.
  62. Artificial intelligence to stratify severity of age-related macular degeneration (amd) and predict risk of progression to late amd. Translational vision science & technology, 9(2):25–25, 2020.
  63. Diffusion models in vision: A survey. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023.
Citations (6)
View on Semantic Scholar

Summary

No one has generated a summary of this paper yet.

Sign Up to Summarize

Paper to Video (Beta)

No one has generated a video about this paper yet.

Sign Up to Generate All Videos Subscribe on YouTube

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Sign Up to Generate

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Generate Now

Continue Learning

We haven't generated follow-up questions for this paper yet.

Generate Now

Collections

Sign up for free to add this paper to one or more collections.

Sign Up