Deep Learning for Eye Disease Detection with Confidence Estimation and Explainable AI

References

[1] Bourne, R., Steinmetz, J.D., Flaxman, S., Briant, P.S., Taylor, H.R., Resnikoff, S., Casson, R.J., Abdoli, A., Abu-Gharbieh, E., Afshin, A. and Ahmadieh, H., 2021. Trends in prevalence of blindness and distance and near vision impairment over 30 years: an analysis for the Global Burden of Disease Study. The Lancet global health, 9(2), pp.e130-e143.thelancet.com

[2] Chalakkal, R. J., Abdulla, W. H., & Hong, S. C., 2020. Fundus retinal image analyses for screening and diagnosing diabetic retinopathy, macular edema, and glaucoma disorders. Diabetes and fundus OCT.HTML

[3] Fekrat, S., Glaser, T. S., & Feng, H. L., 2021. All about Your Eyes, revised and updated.dukeupress.edu

[4] Mélik Parsadaniantz, S., Réaux-le Goazigo, A., Sapienza, A., Habas, C. and Baudouin, C., 2020. Glaucoma: a degenerative optic neuropathy related to neuroinflammation?. Cells, 9(3), p.535.mdpi.com

[5] Thier, A. & Holmberg, C., 2022. The patients' view: age-related macular degeneration and its effects–a meta-synthesis. Disability and Rehabilitation.HTML

[6] Kropp, M., Golubnitschaja, O., Mazurakova, A., Koklesova, L., Sargheini, N., Vo, T.T.K.S., de Clerck, E., Polivka Jr, J., Potuznik, P., Polivka, J. and Stetkarova, I., 2023. Diabetic retinopathy as the leading cause of blindness and early predictor of cascading complications—Risks and mitigation. EPMA Journal, 14(1), pp.21-42.springer.com

[7] Wong, T. Y. & Sabanayagam, C., 2020. Strategies to tackle the global burden of diabetic retinopathy: from epidemiology to artificial intelligence. Ophthalmologica.karger.com

[8] Allison, K., Patel, D., & Alabi, O., 2020. Epidemiology of glaucoma: the past, present, and predictions for the future. Cureus.cureus.com

[9] Ramanathan, Gauri, et al. “Eye Disease Detection Using Machine Learning.” IEEE Xplore, 1 Oct. 2021, ieeexplore.ieee.org/abstract/document/9587740.

[10] Rahul Pahuja, et al. “A Dynamic Approach of Eye Disease Classification Using Deep Learning and Machine Learning Model.” Lecture Notes on Data Engineering and Communications Technologies, 1 Jan. 2022, pp. 719–736, https://doi.org/10.1007/978-981-16-6289-8_59. Accessed 6 Feb. 2024.

[11] Arunkumar, (2021) Arunkumar, K. MACHINE LEARNING MODELS for the DETECTION of HUMAN EYE DISEASE.

[12] Nouf B., Amal A., Ashwaq A. & Raouia M., 2022. Automatic Eye Disease Detection Using Machine Learning and Deep Learning Models.

[13] Zahraa N.A. & Abbas M AI-Bakry, 2023. Diagnose eye diseases using various features extraction approaches and machine learning algorithms.

[14] M. A. Rodr´ıguez, H. AlMarzouqi, & P. Liatsis, 2022. Multi-label Retinal Disease Classification Using Transformers.

[15] TensorFlow. (n.d.). Module: tf.keras | TensorFlow Core v2.4.1. [online] Available at: https://www.tensorflow.org/api_docs/python/tf/keras [Accessed 25 Feb. 2024].

[16] Tensorflow Library accessed at: https://www.tensorflow.org/api_docs/python/tf/keras/preprocessing/image/apply_affine_transform.

[17] Sun, T., Yin, B. and Bohté, S., 2023, September. Efficient Uncertainty Estimation in Spiking Neural Networks via MC-dropout. In International Conference on Artificial Neural Networks (pp. 393-406). Cham: Springer Nature Switzerland. [PDF]

[18] Silva, R.M., Sbrana, A., de Castro, P.A. and Soma, N.Y., 2023. Developing and Assessing a Human-Understandable Metric for Evaluating Local Interpretable Model-Agnostic Explanations. International Journal of Intelligent Engineering & Systems, 16(4). inass.org

[19] Allgaier, J., Mulansky, L., Draelos, R.L. and Pryss, R. (2023). How does the model make predictions? A systematic literature review on the explainability power of machine learning in healthcare. Artificial Intelligence in Medicine, [online] 143, p.102616. doi:https://doi.org/10.1016/j.artmed.2023.102616.

[20] Wang, S.-H. and Zhang, Y.-D. (2020). DenseNet-201-Based Deep Neural Network with Composite Learning Factor and Precomputation for Multiple Sclerosis Classification. ACM Transactions on Multimedia Computing, Communications, and Applications, 16(2s), pp.1–19. doi: https://doi.org/10.1145/3341095.

@article{1705719,
      author = {Adeyinka Mayowa-Majaro},
      title = {Deep Learning for Eye Disease Detection with Confidence Estimation and Explainable AI},
      journal = {Iconic Research And Engineering Journals},
      year = {2024},
      volume = {7},
      number = {10},
      pages = {204-212},
      issn = {2456-8880},
      url = {https://www.irejournals.com/formatedpaper/1705719.pdf},
      abstract = {This research made progress on not only identifying valid deep learning models that can detect various eye diseases but also making the diagnosis process easier for physicians. This study focuses on three eye diseases, Cataract, Glaucoma and Diabetic Retinopathy. These three diseases are the leading causes of eye disorders which have resulted in irreversible visual impairment. Also, these three diseases are at different locations of the eye, the detection of their symptoms and analysis of the fundus images have set up different challenges. Various models, including Convolutional Neural Network (CNN), transfer learning architectures such as VGG16, InceptionV3, ResNet152V2, InceptionResNetV2, and DenseNet201 were used for Eye disease detection from patients? retinal images.  DenseNet201 excelled, achieving a notable accuracy of 86.14%, a precision of 90.52%, a recall of 82.58%, and an AUC of 97.95%. To enhance model robustness, Monte Carlo (MC) dropout was integrated to estimate uncertainty levels, revealing the model's favourable performance under uncertainty. Furthermore, Local Interpretable Model-agnostic Explanations (LIME) was employed to elucidate the model's decision-making process, providing insights into how predictions were derived. This comprehensive approach showcases the efficacy of combining diverse models, leveraging transfer learning, and employing uncertainty estimation and explainability techniques for accurate eye disease detection.},
      month = {April},
  }