Artificial Intelligence Approach for Diabetic Retinopathy Severity Detection

Shalini Rajamani, S Sasikala

Abstract


Identifying the diabetic retinopathy (DR) severity in the retina images taken under a variety of imaging conditions is more challenging. There are five classes that are commonly classified on retinal images based on severity of DR disease such as No DR, mild NPDR (non proliferative diabetic retinopathy), moderate NPDR, severe NPDR and PDR (proliferative diabetic retinopathy). Artificial intelligence is an emerging area in the medical diagnosis industry, in specific, deep learning algorithms are used for classifying retina images for accurate diagnosis of disease. The proposed work acquired retina images from publicly available Kaggle repository and loaded into improved grid search Convolutional Neural Network model for accurate diagnosis on retina images with five different classes. This novel model helps ophthalmologists to classify DR as five stages based on severity from No DR to PDR. The Experimental study showed that the proposed model has performed better than the existing Convolutional Neural Network model with the accuracy of 89%.

Full Text:

PDF

References


https://elsevier.health/en-US/preview/diabetic-retinopathy-co

Wu L, Fernandez-Loaiza P, Sauma J, Hernandez-Bogantes E, Masis M. Classification of diabetic retinopathy and diabetic macular edema. World J Diabetes. 2013;4(6):290-294. doi:10.4239/wjd.v4.i6.290

Zheng, Yingfeng et al. “The worldwide epidemic of diabetic retinopathy.” Indian journal of ophthalmology vol. 60,5 (2012): 428-31. doi:10.4103/0301-4738.100542

Teo ZL, Tham YC, Yu M, Chee ML, Rim TH, Cheung N, Bikbov MM, Wang YX, Tang Y, Lu Y, Wong IY, Ting DSW, Tan GSW, Jonas JB, Sabanayagam C, Wong TY, Cheng CY. Global Prevalence of Diabetic Retinopathy and Projection of Burden through 2045: Systematic Review and Meta-analysis. Ophthalmology. 2021 Nov;128(11):1580-1591. doi: 10.1016/j.ophtha.2021.04.027. Epub 2021 May 1. PMID: 33940045.

Shukla UV, Tripathy K. Diabetic Retinopathy. [Updated 2021 Aug 29]. In: StatPearls [Internet]. Treasure Island (FL): StatPearls Publishing; 2022 Jan-. Available from: https://www.ncbi.nlm.nih.gov/books/NBK560805/

Sarwinda, Devvi & Siswantining, Titin & Bustamam, Alhadi. (2018). Classification of Diabetic Retinopathy Stages using Histogram of Oriented Gradients and Shallow Learning. 83-87. 10.1109/IC3INA.2018.8629502.

Q. Li and X. Wang, "Image Classification Based on SIFT and SVM," 2018 IEEE/ACIS 17th International Conference on Computer and Information Science (ICIS), 2018, pp. 762-765, doi: 10.1109/ICIS.2018.8466432.

Colomer, Adrián et al. “Detection of Early Signs of Diabetic Retinopathy Based on Textural and Morphological Information in Fundus Images.” Sensors (Basel, Switzerland) vol. 20,4 1005. 13 Feb. 2020, doi:10.3390/s20041005

Morales, Y & Nuñez, R & Suarez, J & Torres Moreno, Cesar. (2017). Digital tool for detecting diabetic retinopathy in retinography image using gabor transform. Journal of Physics: Conference Series. 792. 012083. 10.1088/1742-6596/792/1/012083.

Tsiknakis, Nikos & Theodoropoulos, Dimitris & Manikis, Georgios & Ktistakis, Emmanouil & Boutsora, Ourania & Berto, Alexa & Scarpa, Fabio & Scarpa, Alberto & Fotiadis, Dimitrios & Marias, Kostas. (2021). Deep Learning for Diabetic Retinopathy Detection and Classification Based on Fundus Images: A Review. Computers in Biology and Medicine. 135. 104599. 10.1016/j.compbiomed.2021.104599.

Samanta, Abhishek & Saha, Aheli & Satapathy, Suresh & Fernandes, Steven & Zhang, Yu-Dong. (2020). Automated Detection of Diabetic Retinopathy using Convolutional Neural Networks on a Small Dataset. Pattern Recognition Letters. 135.

1016/j.patrec.2020.04.026.

Pratt, Harry & Coenen, Frans & Broadbent, Deborah & Harding, Simon & Zheng, Yalin. (2016). Convolutional Neural Networks for Diabetic Retinopathy. Procedia Computer Science. 90. 200-205. 10.1016/j.procs.2016.07.014.

Mehdi Torabian Esfahani, Mahsa Ghaderi, Raheleh Kafiyeh (2018), Classification of diabetic and normal fundus images using new deep learning method, Leonardo Electronic Journal of Practices and Technologies, ISSN 1583-1078

S. Qummar et al., "A Deep Learning Ensemble Approach for Diabetic Retinopathy Detection," in IEEE Access, vol. 7, pp. 150530-150539, 2019, doi: 10.1109/ACCESS.2019.2947484.

Akram, M. & Khalid, Shehzad & Tariq, Anam & Khan, Shoab & Azam, Farooque. (2014). Detection and classification of retinal lesions for grading of diabetic retinopathy. Computers in biology and medicine. 45C. 161-171. 10.1016/j.compbiomed.2013.11.014.

L. Qiao, Y. Zhu and H. Zhou, "Diabetic Retinopathy Detection Using Prognosis of Microaneurysm and Early Diagnosis System for Non-Proliferative Diabetic Retinopathy Based on Deep Learning Algorithms," in IEEE Access, vol. 8, pp. 104292-104302, 2020, doi: 10.1109/ACCESS.2020.2993937.

M. M. Abdelsalam and M. A. Zahran, "A Novel Approach of Diabetic Retinopathy Early Detection Based on Multifractal Geometry Analysis for OCTA Macular Images Using Support Vector Machine," in IEEE Access, vol. 9, pp. 22844-22858, 2021, doi: 10.1109/ACCESS.2021.3054743.

X. Zeng, H. Chen, Y. Luo and W. Ye, "Automated Diabetic Retinopathy Detection Based on Binocular Siamese-Like Convolutional Neural Network," in IEEE Access, vol. 7, pp. 30744-30753, 2019, doi: 10.1109/ACCESS.2019.2903171.

A. Herliana, T. Arifin, S. Susanti and A. B. Hikmah, "Feature Selection of Diabetic Retinopathy Disease Using Particle Swarm Optimization and Neural Network," 2018 6th International Conference on Cyber and IT Service Management (CITSM), 2018, pp. 1-4, doi: 10.1109/CITSM.2018.8674295.

Elangovan, Aarthi, and S. Sasikala. "A Multi-label Classification of Disaster-Related Tweets with Enhanced Word Embedding Ensemble Convolutional Neural Network Model." Informatica 46.7 (2022).

Zhang, Qiu-ming, Jing Luo, and Korhan Cengiz. "An Optimized Deep Learning based Technique for Grading and Extraction of Diabetic Retinopathy Severities." Informatica 45.5 (2021).

Guernine, Akram, and Mohamed Tahar Kimour. "Optimized Training for Convolutional Neural Network Using Enhanced Grey Wolf Optimization Algorithm." Informatica 45.5 (2021).

Jena, Manaswini, et al. "Exploring the Parametric Impact on a Deep Learning Model and proposal of a 2-Branch CNN for Diabetic Retinopathy Classification with Case Study in IoT-Blockchain based Smart Healthcare System." Informatica 46.2 (2022).

https://www.kaggle.com/competitions/diabetic-retinopathy-detection/data




DOI: https://doi.org/10.31449/inf.v46i8.4425

Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.