A Stacking Ensemble Federated Deep Learning Model with Optimization for the Efficient Ocular Pathology Detection

Download Article

DOI: 10.21522/TIJPH.2013.13.02.Art056

Authors : S. Geethamani, L. Sankari

Abstract:

One major challenge in healthcare is utilizing Fundus Images (FI) to diagnose ocular pathology (OP). An ocular disorder disrupts the eye's regular functioning or adversely impacts the eye's visual acuity. Almost everyone experiences eye-sight issues throughout their lives, ranging from minor problems that can be managed at home to more severe conditions requiring specialized medical care. While certain kids require specialized care, others are minors who do not show up to support requests or who can be handled at home with ease. Ocular pathology detection approaches depend on Stacking Ensemble Federated (DL)Deep Learning (SEFDL), which was suggested in this work. First, an adaptive weight (AW)-based median filter (MF) is applied to image resizing and removing noise. Then, the data augmentation, coupled with the Synthetic Minority Over-sampling Technique (SMOTE), z, is employed to address data imbalance, a common issue in medical datasets. Finally, SEFDL is proposed for disease detection (DD). Adaptive TSO (Tuna-Swarm Optimization) Technique adjusted hyperparameters (HP) for 4 pre-trained models: CNN, VGG16, Inceptionv2, and ResNet50. DL models trained centrally have been compared with the enhanced algorithms in a federated framework. The proposed SEFDL model demonstrates superior accuracy and robustness when benchmarked against existing methods, highlighting its potential as a reliable diagnostic tool. Finally, the result must be compared with existing approaches to improve ocular pathology detection while addressing data privacy concerns in healthcare applications.

References:

[1].   Elsawy, A., Abdel-Mottaleb, M., and AbouShousha, M., 2020, Diagnosis of corneal pathologies using deep learning. In Ophthalmic Technologies XXX, vol. 11218, 150-160.

[2].   Rauf, N., Gilani, S. O., and Waris, A., 2021, Automatic Detection of pathological myopia using machine learning. Scientific Reports, col. 11, no. 1, 16570.

[3].   Ting, D. S., Peng, L., Varadarajan, A. V., Keane, P. A., Burlina, P. M., Chiang, M. F., and Wong, T. Y., 2019, Deep learning in ophthalmology: the technical and clinical considerations. Progress in retinal and eye research, vol. 72, 100759.

[4].   Akil, M., Elloumi, Y., and Kachouri, R., 2021, Detection of retinal abnormalities in fundus image using CNN deep learning networks. In State of the Art in Neural Networks and their Applications, 19-61.

[5].   Perdomo Charry, O. J., and González, F. A., 2020, A systematic review of deep learning methods applied to ocular images. Ciencia e IngenieriaNeogranadina, vol. 30, no. 1, 9-26.

[6].   Gargeya, R., andLeng, T., 2017, Automated identification of diabetic retinopathy using deep learning. Ophthalmology, vol. 124, no. 7, 962-969.

[7].   Liu, T. A., Wei, J., Zhu, H., Subramanian, P. S., Myung, D., Paul, H. Y., and Miller, N. R., 2021, Detection of optic disc abnormalities in color fundus photographs using deep learning. Journal of Neuro-Ophthalmology, vol. 41, no. 3, 368-374.

[8].   Kazi, K. S., 2024, Computer-Aided Diagnosis in Ophthalmology: A Technical Review of Deep Learning Applications. Transformative Approaches to Patient Literacy and Healthcare Innovation, 112-135.

[9].   Grewal, P. S., Oloumi, F., Rubin, U., and Tennant, M. T., 2018, Deep learning in ophthalmology: a review. Canadian Journal of Ophthalmology, vol. 53. No. 4, 309-313.

[10].  Balyen, L., and Peto, T., 2019, Promising artificial intelligence-machine learning-deep learning algorithms in ophthalmology. The Asia-Pacific Journal of Ophthalmology, vol. 8, no. 3, 264-272.

[11].  Moraru, A. D., Costin, D., Moraru, R. L., and Branisteanu, D. C., 2020, Artificial intelligence and deep learning in ophthalmology-present and future. Experimental and Therapeutic Medicine, vol. 20, no. 4, 3469-3473.

[12].  Sujatha, K., Thivya, K. S., Anand, M., Jayachitra, N., Durgadevi, G., Bhavani, N. P. G., and Srividhya, V., 2020, Vision machine learning for Detection of ocular pathologies from iris images. Journal of Discrete Mathematical Sciences and Cryptography, vol. 23, no. 1, 145-155.

[13].  Hossain, M. R., Afroze, S., Siddique, N., and Hoque, M. M., 2020, Automatic Detection of eye cataract using deep convolution neural networks (DCNNs). In 2020 IEEE region 10 symposium (TENSYMP), 1333-1338.

[14].  Rauf, N., Gilani, S. O., and Waris, A., 2021, Automatic Detection of pathological myopia using machine learning. Scientific Reports, vol. 11, no. 1, 16570.

[15].  Pérez, A. D., Perdomo, O., and González, F. A., 2020, A lightweight deep learning model for mobile eye fundus image quality assessment. In 15th international symposium on medical information processing and analysis, vol. 11330, 151-158.

[16].  Junayed, M. S., Islam, M. B., Sadeghzadeh, A., and Rahman, S., 2021, CataractNet: An automated cataract detection system using deep learning for fundus images. IEEE access, vol. 9, 128799-128808.

[17].  Sharma, P., Ninomiya, T., Omodaka, K., Takahashi, N., Miya, T., Himori, N., and Nakazawa, T., 2022, A lightweight deep learning model for automatic segmentation and analysis of ophthalmic images. Scientific reports, vol. 12, no. 1, 8508.

[18].  Sunija, A. P., Kar, S., Gayathri, S., Gopi, V. P., and Palanisamy, P., 2021, Octnet: A lightweight cnn for retinal disease classification from optical coherence tomography images. Computer methods and programs in biomedicine, vol. 200, 105877.

[19].  Teikari, P., Najjar, R. P., Schmetterer, L., and Milea, D., 2019, Embedded deep learning in ophthalmology: making ophthalmic imaging smarter. Therapeutic advances in ophthalmology, vol. 11, 2515841419827172.

[20].  Song, Z., Xu, L., Wang, J., Rasti, R., Sastry, A., Li, J. D., and Farsiu, S., 2021, Lightweight learning-based automatic segmentation of subretinal blebs on microscope-integrated optical coherence tomography images. American journal of ophthalmology, vol. 221, 154-168.

[21].  Wang, H., Yang, J., Wu, Y., Du, W., Fong, S., Duan, Y., and Wu, F., 2021, A fast lightweight based deep fusion learning for detecting macula fovea using ultra-widefield Fundus images.

[22].  Xie, R., Liu, J., Cao, R., Qiu, C. S., Duan, J., Garibaldi, J., and Qiu, G., 2020, End-to-end fovea localization in colour fundus images with a hierarchical deep regression network. IEEE Transactions on Medical Imaging, vol. 40, no. 1, 116-128.

[23].  Kotsiantis, S. B., Kanellopoulos, D., and Pintelas, P. E., 2006, Data preprocessing for supervised leaning. International journal of computer science, vol. 1, no. 2, 111-117.

[24].  Jin, F., Fieguth, P., Winger, L., and Jernigan, E., 2003, Adaptive Wiener filtering of noisy images and image sequences. In Proceedings 2003 International Conference on Image Processing (Cat. No. 03CH37429), vol. 3, III-349.

[25].  Shorten, C., andKhoshgoftaar, T. M., 2019, A survey on image data augmentation for deep learning. Journal of big data, vol. 6, no. 1, 1-48.

[26].  Chawla, N. V., Bowyer, K. W., Hall, L. O., and Kegelmeyer, W. P., 2002, SMOTE: synthetic minority over-sampling technique. Journal of artificial intelligence research, vol. 16, 321-357.

[27].  Zhu, H., Zhang, H., andJin, Y., 2021, From federated learning to federated neural architecture search: a survey. Complex and Intelligent Systems, vol. 7, no. 2, 639-657.

[28].  O'Shea, K., and Nash, R., 2015, An introduction to convolutional neural networks. arXiv preprint arXiv:1511.08458.

[29].  Iqbal, H., Chawla, H., Varma, A., Brouns, T., Badar, A., Arani, E., and Zonooz, B., 2022, AI-Driven Road Maintenance Inspection v2: Reducing Data Dependency and Quantifying Road Damage. arXiv preprint arXiv:2210.03570.

[30].  Koonce, B., andKoonce, B., 2021, ResNet 50. Convolutional neural networks with swift for tensorflow: image recognition and dataset categorization, 63-72.

[31].  Xie, L., Han, T., Zhou, H., Zhang, Z. R., Han, B., and Tang, A., 2021, Tuna swarm optimization: a novel swarm-based metaheuristic algorithm for global optimization. Computational intelligence and Neuroscience, vol. 2021, 1-22.

[32].  Obayya, M., Arasi, M. A., Alruwais, N., Alsini, R., Mohamed, A., andYaseen, I., 2023, Biomedical image analysis for colon and lung cancer detection using tuna swarm algorithm with deep learning model. IEEE Access.