Computer-Aided Diagnostic System for Detection and Classification of Different Grades of Diabetic Retinopathy using Ensemble Learning and Deep Learning Techniques
Keywords:
Bagging, Ensemble Learning, EfficientNetB0, Deep Learning, Diabetic Retinopathy, MobileNetV2.Abstract
Diabetes, being a chronic condition, possesses the capacity to instigate a global healthcare catastrophe. Diabetes is a significant etiological agent in the development of numerous diseases and health conditions. Diabetic Retinopathy (DR) is an ocular illness that damages retinal blood vessels. If not recognized early, DR weakens vision and may result in blindness. This disease can be treated and potentially cured if diagnosed and treated promptly. Manual diagnosis of this condition (by clinicians) is time-consuming and prone to inaccuracy. Integrating machine learning technology with medical science enables precise prognosis of an individual's susceptibility to DR. The proposed work describes a Computer-Aided Diagnostic (CAD) Application for DR Prediction and Classification that employs Ensemble learning techniques and a combination of two pre-trained Deep Neural Network (DNN) models (MobileNetV2, EfficientNetB0). We create an Ensemble Stacking-based model (Ensemble Model) and an Ensemble Bagging-based model (Bagged Model), in addition to a regular Convolutional Neural Network (CNN). We study and analyse the performance of the CNN model, and DNN models (MobileNetV2, EfficientNetB0) individually, along with the Ensemble Model and Bagged Model. The Bagged Model outperforms the other models, with a training accuracy of 87.11%. Hence, this work determines the Bagged Model’s potential as a viable instrument for detecting DR and is used in the development of an efficient and effective Application for Predicting Diabetic Retinopathy.
Downloads
References
S. Jan, I. Ahmad, S. Karim, Z. Hussain, M. Rehman, and M. A. Shah, ‘‘Status of diabetic retinopathy and its presentation patterns in diabetics at ophthalmology clinics,’’ J. Postgraduate Med. Inst. (Peshawar-Pakistan), vol. 32, no. 1, pp. 24–27, Mar. 2018.
E. A. Lundeen, Z. Burke-Conte, D. B. Rein, "Prevalence of diabetic retinopathy in the US in 2021," JAMA, vol. 2023. jamanetwork.com, 2023. [HTML]
A. X. Chan, J. J. McDermott IV, T. C. Lee, G. Y. Ye, et al., "Associations between healthcare utilization and access and diabetic retinopathy complications using All of Us nationwide survey data," PloS one, vol. 2022, journals.plos.org, 2022. plos.org
W. R. Memon, B. Lal, and A. A. Sahto, ‘‘Diabetic retinopathy,’’ The Prof. Med. J., vol. 24, no. 2, pp. 234–238, 2017.
A. H. A. Ghamdi, "Clinical predictors of diabetic retinopathy progression; a systematic review," Current diabetes reviews, 2020. ingentaconnect.com
C. J. Flaxel, R. A. Adelman, S. T. Bailey, A. Fawzi, J. I. Lim, et al., "Diabetic retinopathy preferred practice pattern®," Ophthalmology, 2020. [Online]. Available: aaojournal.org. aaojournal.org
M. Kropp, O. Golubnitschaja, A. Mazurakova, et al., "Diabetic retinopathy as the leading cause of blindness and early predictor of cascading complications—risks and mitigation," Epma Journal, vol. 2023. Springer, 2023. springer.com
K.Y. Lin, W.H. Hsih, Y.B. Lin, C.Y. Wen, et al., "Update in the epidemiology, risk factors, screening, and treatment of diabetic retinopathy," Journal of Diabetes Investigation, vol. 2021, Wiley Online Library, 2021. wiley.com
N. Sikder, M. Masud, A. K. Bairagi, A. S. M. Arif, A. A. Nahid, "Severity classification of diabetic retinopathy using an ensemble learning algorithm through analyzing retinal images," Symmetry, 2021. [Online]. Available: mdpi.com mdpi.com
I. Odeh, M. Alkasassbeh, et al., "Diabetic retinopathy detection using ensemble machine learning," in Proc. ... Conference on Information ..., 2021. [PDF]
G.T. Reddy, S. Bhattacharya, et al., "An ensemble-based machine learning model for diabetic retinopathy classification," in Proc. ... on emerging trends ..., 2020. [HTML]
E. AbdelMaksoud, S. Barakat, and M. Elmogy, "A comprehensive diagnosis system for early signs and different diabetic retinopathy grades using fundus retinal images based on pathological changes detection," Computers in Biology and Medicine, vol. 2020, Elsevier, 2020. [HTML]
S. Gayathri, V.P. Gopi, and P. Palanisamy, "A lightweight CNN for Diabetic Retinopathy classification from fundus images," in Biomedical Signal Processing and Control, vol. 55, 2020, Elsevier. [HTML]
M. Akil, Y. Elloumi, and R. Kachouri, "Detection of retinal abnormalities in fundus image using CNN deep learning networks," in State of the Art in Neural Networks and their Applications, Elsevier, 2021. hal.science
L. P. Cen, J. Ji, J. W. Lin, S. T. Ju, H. J. Lin, T. P. Li, et al., "Automatic detection of 39 fundus diseases and conditions in retinal photographs using deep neural networks," Nature, 2021. nature.com
Kannan, Rajeswari, S. R. Vispute, Reena Kharat, Dipti Salunkhe, and N. Vivekanandan. 2023. “Early Detection of Diabetic Retinopathy Using Deep Convolutional Neural Network”. Communications in Mathematics and Applications 14 (3):1283-92. https://doi.org/10.26713/cma.v14i3.2413.
Sahlsten, J., Jaskari, J., Kivinen, J. et al. “Deep Learning Fundus Image Analysis for Diabetic Retinopathy and Macular Edema Grading”. Sci Rep 9, 10750 (2019). https://doi.org/10.1038/s41598-019-47181-w
Oh, K., Kang, H.M., Leem, D. et al. “Early detection of diabetic retinopathy based on deep learning and ultra-wide-field fundus images”. Sci Rep 11, 1897 (2021). https://doi.org/10.1038/s41598-021-81539-3
Wejdan L. Alyoubi *, Wafaa M. Shalash, Maysoon F. Abulkhair Information Technology Department, University of King Abdul Aziz, Jeddah, Saudi Arabia https://doi.org/10.1016/j.imu.2020.100377
Hamid Safi, MD, MPHa , Sare Safi, PhDb , Ali Hafezi-Moghadam, MD, PhDc , Hamid Ahmadieh, MDa, * a Ophthalmic Research Center, Shahid Beheshti University of Medical Sciences, Tehran, Iran b Ophthalmic Epidemiology Research Center, Shahid Beheshti University of Medical Sciences, Tehran, Iran c Molecular Biomarkers Nano-Imaging Laboratory, Brigham and Women’s Hospital, Department of Radiology, Harvard Medical School, Boston, Massachusetts, USA https://www.scribd.com/document/526413601/safi2018
S. Qummaret al., "A Deep Learning Ensemble Approach for Diabetic Retinopathy Detection," in IEEE Access, vol. 7, pp. 150530-150539, 2019, doi: 10.1109/ACCESS.2019.2 947484.
Bilal A, Imran A, Baig TI, Liu X, Long H, et al. (2024) Improved Support Vector Machine based on CNN-SVD for vision-threatening diabetic retinopathy detection and classification. PLOS ONE 19(1): e0295951. https://doi.org/10.1371/journal.pone.0295951
Michael D. Abràmoff MD, PhD Joseph M., Reinhardt PhD ,Stephen R. Russell MD, James C.Folk MD, Vinit B. Mahajan MD, PhD, Meindert Niemeijer PhD and Gwénolé Quellec PhD. Ophthalmology, 2010-06-01, Volume 117, Issue 6, Pages 1147-1154, Copyright © 2010 American Academy of Ophthalmology https://doi.org/10.1016/j.ophtha.2010.03.046
Borys Tymchenko1 a , Philip Marchenko2 b and Dmitry Spodarets3 “Deep Learning Approach to Diabetic Retinopathy Detection” arXiv:2003.02261v1 [cs.LG] 3 Mar 2020 https://arxiv.org/
Mishra, S., Hanchate, S., & Saquib, Z. (2020). Diabetic Retinopathy Detection using Deep Learning. 2020 International Conference on Smart Technologies in Computing, Electrical and Electronics (ICSTCEE). https://doi.org/10.1109/icstcee49637.2020.9277506
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
