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

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.