Enhanced Diabetic Retinopathy Detection through Deep Learning Ensemble Models for Early Diagnosis

Authors

  • Deepak Dembla Department of Computer Application, JECRC: Jaipur Engineering College and Research Centre University, Jaipur, 303905, Rajasthan, India
  • Amita Meshram Department of Computer Science and Engineering, Yashwantrao Chavhan College of Engineering,Wanadongri, Nagpur, Maharashtra, India.
  • Anooja A. Department of Computer Application, JECRC: Jaipur Engineering College and Research Centre University, Jaipur, 303905, Rajasthan, India

Keywords:

Diabetic Retinopathy(DR), MobileNet, XceptionNet, ResNet50V2, DenseNet201, DenseNet169, InceptionV3

Abstract

One of the most prevalent and primary causes of blindness associated with diabetes is diabetic retinopathy (DR). An early diagnosis of DR can stop the disease's progression. Vision impairment results from missed opportunities for diagnosis and treatment due to differences in the distribution of medical facilities. It is more effective and less expensive to classify and diagnose DR with better accuracy using neural network models. In order to enhance the functionality of DR classification models, This proposed model is an ensemble model that includes Transfer Learning algorithms that are Mobile Net, Xception, ResNet50V2, DenseNet201, DenseNet169, InceptionV3, and InceptionResNetV2   were added in this study for the detection of DR classification in fundus photographs. For that the APTOS and eyepacs dataset of a total of 5236 images are taken.This model taken 90% of images for training and 10% of images taken for testing on 30 epochs. The performance of DR classification can also be enhanced by adding extra 4 dense layers in each model and then ensemble that models. The output of the ensemble is applied for majority voting. The proposed ensemble model detected DR stages accurately and correctly. Hence  proposed Ensemble model accuracy is 92.23%.

Downloads

Download data is not yet available.

References

F. Alzami, R. Aria Megantara, A. Zainul Fanani, P. Nurtantio Andono, and M. Arief Soeleman, “Exudates Detection for Multiclass Diabetic Retinopathy Grade Detection using Ensemble,” 2020.

L. Wang, Z. Chen, M. Wang, T. Wang, W. Zhu, and X. Chen, “Cycle adaptive multi-target weighting network for automated diabetic retinopathy segmentation,” in Proceedings - International Symposium on Biomedical Imaging, Apr. 2021, vol. 2021-April, pp. 1141–1144. doi: 10.1109/ISBI48211.2021.9433917.

T. R. Gadekallu, N. Khare, S. Bhattacharya, S. Singh, P. K. R. Maddikunta, and G. Srivastava, “Deep neural networks to predict diabetic retinopathy,” Journal of Ambient Intelligence and Humanized Computing, 2020, doi: 10.1007/s12652-020-01963-7.

A. G. Priya Henry and A. Jude, “Convolutional neural-network-based classification of retinal images with different combinations of filtering techniques,” Open Computer Science, vol. 11, no. 1, pp. 480–490, Jan. 2021, doi: 10.1515/comp-2020-0177.

W. L. Alyoubi, W. M. Shalash, and M. F. Abulkhair, “Diabetic retinopathy detection through deep learning techniques: A review,” Informatics in Medicine Unlocked, vol. 20. Elsevier Ltd, Jan. 01, 2020. doi: 10.1016/j.imu.2020.100377.

V. Sudha and T. R. Ganeshbabu, “A convolutional neural network classifier VGG-19 architecture for lesion detection and grading in diabetic retinopathy based on deep learning,” Computers, Materials and Continua, vol. 66, no. 1, pp. 827–842, 2021, doi: 10.32604/cmc.2020.012008.

J. G. K. L. J. P. ´ cov ˇ a Slavom´ır Kajan, “Detection of Diabetic Retinopathy Using Pretrained Deep Neural Networks,” 978-1-7281-4381-1/20/$31.00 © 2020 IEEE.

S. K. J. L. Z. M. T. Y. S. W. D. M. M. F. B. E. V. N. and M. V. S. Morgan Heisler1, “Ensemble Deep Learning for Diabetic Retinopathy Detection Using Optical Coherence Tomography Angiography,” . Trans Vis Sci Tech. 2020;9(2):20, https://doi.org/10.1167/tvst.9.2.20, vol. Vol. 9, no. Special Issue, 2022.

J. Raja, P. Shanmugam, and R. Pitchai, “An Automated Early Detection of Glaucoma using Support Vector Machine Based Visual Geometry Group 19 (VGG-19) Convolutional Neural Network,” Wireless Personal Communications, vol. 118, no. 1, pp. 523–534, May 2021, doi: 10.1007/s11277-020-08029-z.

M. H. Mahmoud, S. Alamery, H. Fouad, A. Altinawi, and A. E. Youssef, “An automatic detection system of diabetic retinopathy using a hybrid inductive machine learning algorithm,” Personal and Ubiquitous Computing, 2021, doi: 10.1007/s00779-020-01519-8.

N. S. Murthy and B. Arunadevi, “An effective technique for diabetic retinopathy using hybrid machine learning technique,” Statistical Methods in Medical Research, vol. 30, no. 4, pp. 1042–1056, Apr. 2021, doi: 10.1177/0962280220983541.

L. M. H. H. and K. A. AATILA Mustapha1, “Diabetic Retinopathy Classification Using ResNet50 and VGG-16 Pretrained Networks,” :International Journal of Computer Engineering and Data Science (ISSN:2737-8543) Volume 1– Issue 1, 20/07/2021, 2021.

S. Valarmathi and R. Vijayabhanu, “A Survey on Diabetic Retinopathy Disease Detection and Classification using Deep Learning Techniques,” Mar. 2021. doi: 10.1109/ICBSII51839.2021.9445163.

A. Deshpande and J. Pardhi, “Automated detection of Diabetic Retinopathy using VGG-16 architecture,” International Research Journal of Engineering and Technology, 2021, [Online]. Available: www.irjet.net

A. Bora et al., “Predicting the risk of developing diabetic retinopathy using deep learning,” The Lancet Digital Health, vol. 3, no. 1, pp. e10–e19, Jan. 2021, doi: 10.1016/S2589-7500(20)30250-8.

M. E. Hoque et al., “A deep learning approach for retinal image feature extraction,” Pertanika Journal of Science and Technology, vol. 29, no. 4, pp. 2543–2563, Oct. 2021, doi: 10.47836/PJST.29.4.17.

G. U. Nneji, J. Cai, J. Deng, H. N. Monday, M. A. Hossin, and S. Nahar, “Identification of Diabetic Retinopathy Using Weighted Fusion Deep Learning Based on Dual-Channel Fundus Scans,” Diagnostics, vol. 12, no. 2, Feb. 2022, doi: 10.3390/diagnostics12020540.

G. Mushtaq and F. Siddiqui, “Detection of diabetic retinopathy using deep learning methodology,” IOP Conference Series: Materials Science and Engineering, vol. 1070, no. 1, p. 012049, Feb. 2021, doi: 10.1088/1757-899x/1070/1/012049.

Hanan Saleh Alghamdi,” Towards Explainable Deep Neural Networks for the Automatic Detection of Diabetic Retinopathy” Appl. Sci. 2022, 12, 9435. https://doi.org/10.3390/ app12199435

Ch. Usha Kumari et al.,” Deep Learning Based Detection of Diabetic Retinopathy using Retinal Fundus Images,” 2022 Third International Conference on Intelligent Computing, Instrumentation and Control Technologies (ICICICT)

Brahami Menaouer et al.,” Diabetic Retinopathy Classifcation Using Hybrid Deep Learning Approach” SN Computer Science (2022) 3:357 https://doi.org/10.1007/s42979-022-01240-8

Sambit S. Mondal et,al.,” EDLDR: An Ensemble Deep Learning Technique for Detection and Classification of Diabetic Retinopathy”, Diagnostics 2023, 13, 124. https:// doi.org/10.3390/diagnostics13010124

Hao Liu et al.,” Hybrid Model Structure for Diabetic Retinopathy Classification”, Hindawi Journal of Healthcare Engineering Volume 2020, Article ID 8840174, 9 pages https://doi.org/10.1155/2020/8840174

Muhammad Mohsin Butt et al.,” Diabetic Retinopathy Detection from Fundus Images of the Eye Using Hybrid Deep Learning Features”, Diagnostics 2022, 12, 1607. https://doi.org/10.3390/ diagnostics12071607.

Wei Wang et al.,” A New Image Classification Approach via Improved MobileNet Models with Local Receptive Field Expansion in Shallow Layers”, Hindawi Computational Intelligence and Neuroscience Volume 2020, Article ID 8817849, 10 pages https://doi.org/10.1155/2020/8817849.

Sohaib Asif et al.,”Improving Effectiveness of Different Deep Transfer Learning-Based Models for Detecting Brain Tumors From MR Images”,IEEE Access volume 10 ,2022.

Moctar Abdoul Latif Sawadogo et al.”PTSD in the Wild: A Video Database for Studying Post-Traumatic Stress Disorder Recognition in Unconstrained Environments”, arXiv:2209.14085v1 [cs.HC] 28 Sep 2022.

Hemant Kumar et al.,”Transfer Learning and Supervised Machine Learning Approach for Detection of Skin Cancer: Performance Analysis and Comparison”, Drugs and Cell Therapies in Hematology (ISSN: 2281-4876) Volume 10 Issue 1 (2021).

Adarsh Vulli et al.,”Fine-Tuned DenseNet-169 for Breast Cancer Metastasis Prediction Using FastAI and 1-Cycle Policy”, Sensors 2022, 22, 2988. https://doi.org/10.3390/s22082988.

Christian Szegedy et al.,Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning”, arXiv:1602.07261v2 [cs.CV] 23 Aug 2016.

N. Dong et al.,”Inception v3 based cervical cell classification combined with artificially extracted features” Applied Soft Computing Volume 93, August 2020, 106311.

Meshram, A., Dembla, D. (2023). Multistage Classification of Retinal Images for Prediction of Diabetic Retinopathy-Based Deep Learning Model. In: Rathore, V.S., Piuri, V., Babo, R., Ferreira, M.C. (eds) Emerging Trends in Expert Applications and Security. ICETEAS 2023. Lecture Notes in Networks and Systems, vol 682. Springer, Singapore. https://doi.org/10.1007/978-981-99-1946-8_20

Meshram, A., Dembla, D. “Mcbm: Implementation Of Multiclass And Transfer Learning Algorithm Based On Deep Learning Model For Early Detection Of Diabetic Retinopathy” Asean Engineering Journal, 2023, 13(3), Pp. 107–116.

Meshram, A., Dembla, D., Anooja, A.,” Development And Analysis Of Deep Learning Model Based On Multiclass Classification Of Retinal Image For Early Detection Of Diabetic Retinopathy” Asean Engineering Journal, 2023, 13(3), Pp. 89–97

Downloads

Published

07.02.2024

How to Cite

Dembla, D. ., Meshram, A. ., & A., A. . (2024). Enhanced Diabetic Retinopathy Detection through Deep Learning Ensemble Models for Early Diagnosis. International Journal of Intelligent Systems and Applications in Engineering, 12(15s), 26–38. Retrieved from https://ijisae.org/index.php/IJISAE/article/view/4706

Issue

Section

Research Article