Abstract

Diabetic retinopathy (DR) is a leading cause of vision loss, making early detection and classification vital for effective management. Despite advancements in machine learning and deep learning techniques, these methods often require substantial computational resources and specialized domain knowledge, which are not always readily available. To address these challenges, a robust and computationally efficient methodology is proposed for early-stage DR detection, leveraging classical image enhancement and multi-stage segmentation techniques. Utilizing publicly available datasets—DRIVE, CHASEDB1, and DIARETDB1, our study applied data augmentation techniques to bolster the training set and mitigate overfitting. The framework employs a range of image enhancement methods, including Median Filter, Weiner Filter, and contrast limited adaptive histogram equalization (CLAHE), followed by lesion segmentation techniques. Accurate isolation of critical features like blood vessels (BVs) and the optic disc is achieved through principal component analysis (PCA) and iterative self-organizing data analysis technique algorithm (ISODATA). The experimental analysis demonstrates that the proposed methodology achieves high performance, with sensitivity, specificity, and accuracy rates of 91.50%, 88.20%, and 90.40% for microaneurysms (MA); 92.20%, 89.10%, and 91.30% for hemorrhages (HE); and 93.10%, 90.20%, and 92.60% for exudates, respectively. The image enhancement techniques improved the peak signal-to-noise ratio (PSNR) to 21.80 and the normalized cross-correlation (NCC) to 0.812. These results indicate the effectiveness of the proposed methods in accurately detecting and classifying lesions in retinal images.

Keyword

Diabetic retinopathy, Lesions detection, Retinal image segmentation, Contrast limited adaptive histogram equalization (CLAHE), Data augmentation.

Cite this article

B. S, Rao MK, K. CH.Advancing retinal image analysis: from preprocessing to lesion identification in diabetic retinopathy. International Journal of Advanced Technology and Engineering Exploration. 2024;11(119):1449-1468. DOI:10.19101/IJATEE.2023.10102323

Refference

[1]Forghani R. Machine learning and other artificial intelligence applications, an issue of neuroimaging clinics of North America, E-book: machine learning and other artificial intelligence applications. Elsevier Health Sciences; 2020.

[2]Changhez J, James S, Jamala F, Khan S, Khan MZ, Gul S, et al. Evaluating the efficacy and accuracy of AI-assisted diagnostic techniques in endometrial carcinoma: a systematic review. Cureus. 2024; 16(5):1-11.

[3]Wilder B, Pinedo A, Abusin S, Ansell D, Bacong AM, Calvin J, et al. A global perspective on socioeconomic determinants of cardiovascular health. Canadian Journal of Cardiology. 2024.

[4]Ismail R, Ismail NH, Tamil AM, Jaafar MH, Isa ZM, Nasir NM, et al. Prevalence and factors associated with prediabetes and diabetes mellitus among adults: baseline findings of pure Malaysia cohort study. Clinical Epidemiology and Global Health. 2023; 21:101279.

[5]Kropp M, Golubnitschaja O, Mazurakova A, Koklesova L, Sargheini N, Vo TT, et al. Diabetic retinopathy as the leading cause of blindness and early predictor of cascading complications—risks and mitigation. Epma Journal. 2023; 14(1):21-42.

[6]Hou X, Wang L, Zhu D, Guo L, Weng J, Zhang M, et al. Prevalence of diabetic retinopathy and vision-threatening diabetic retinopathy in adults with diabetes in China. Nature Communications. 2023; 14(1):4296.

[7]Chaurasia S, Thool AR, Ansari KK, Saifi AI. Advancement in understanding diabetic retinopathy: a comprehensive review. Cureus. 2023; 15(11):1-11.

[8]Li Z, Han Y, Yang X. Multi-fundus diseases classification using retinal optical coherence tomography images with swin transformer V2. Journal of Imaging. 2023; 9(10):1-18.

[9]Zhang J, Ma K, Luo Z, Wang G, Feng Z, Huang Y, et al. Combining functional and morphological retinal vascular characteristics achieves high-precision diagnosis of mild non-proliferative diabetic retinopathy. Journal of Translational Medicine. 2024; 22(1):798.

[10]Rajput Y, Gaikwad S, Dhumal R, Gaikwad J. The development of a tool for the detection of cotton wool spots, haemorrhage, and exudates using multi-resolution analysis. In international conference on network security and blockchain technology 2023 (pp. 299-310). Singapore: Springer Nature Singapore.

[11]Sandhya SG, Suhasini A. An efficient detection of micro aneurysms from fundus images with CDLNN algorithm. Materials Today: Proceedings. 2023; 81:553-62.

[12]Care D. Standards of care in diabetes-2023. Diabetes care. 2023; 46:S1-267.

[13]Sugandh FN, Chandio M, Raveena FN, Kumar L, Karishma FN, Khuwaja S, et al.. Advances in the management of diabetes mellitus: a focus on personalized medicine. Cureus. 2023; 15(8):1-13.

[14]Wolf RM, Channa R, Liu TA, Zehra A, Bromberger L, Patel D, et al. Autonomous artificial intelligence increases screening and follow-up for diabetic retinopathy in youth: the access randomized control trial. Nature communications. 2024; 15(1):421.

[15]Naz H, Ahuja NJ, Nijhawan R. Diabetic retinopathy detection using supervised and unsupervised deep learning: a review study. Artificial Intelligence Review. 2024; 57(5):1-66.

[16]Abushawish IY, Modak S, Abdel-raheem E, Mahmoud SA, Hussain AJ. Deep learning in automatic diabetic retinopathy detection and grading systems: a comprehensive survey and comparison of methods. IEEE Access. 2024; 12:84785-802.

[17]Hemalakshmi GR, Santhi D, Mani VR, Geetha A, Prakash NB. Classification of retinal fundus image using MS-DRLBP features and CNN-RBF classifier. Journal of Ambient Intelligence and Humanized Computing. 2021; 12:8747-62.

[18]Agughasi VI. Leveraging transfer learning for efficient diagnosis of COPD using CXR images and explainable AI techniques. Inteligencia artificial. 2024; 27(74):133-51.

[19]Agughasi VI. The superiority of fine-tuning over full-training for the efficient diagnosis of COPD from CXR images. Inteligencia Artificial. 2024; 27(74):62-79.

[20]Soares I, Castelo-branco M, Pinheiro A. Microaneurysms detection in retinal images using a multi-scale approach. Biomedical Signal Processing and Control. 2023; 79:104184.

[21]Bhimavarapu U, Chintalapudi N, Battineni G. Automatic detection and classification of hypertensive retinopathy with improved convolution neural network and improved SVM. Bioengineering. 2024; 11(1):56.

[22]Medhi JP, Sandeep R, Datta P, Nizami TK. Intelligent identification and classification of diabetic retinopathy using fuzzy inference system. Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization. 2023; 11(6):2386-99.

[23]Luo X, Wang W, Xu Y, Lai Z, Jin X, Zhang B, et al. A deep convolutional neural network for diabetic retinopathy detection via mining local and long‐range dependence. CAAI Transactions on Intelligence Technology. 2024; 9(1):153-66.

[24]Özbay E. An active deep learning method for diabetic retinopathy detection in segmented fundus images using artificial bee colony algorithm. Artificial Intelligence Review. 2023; 56(4):3291-318.

[25]Nahiduzzaman M, Islam MR, Goni MO, Anower MS, Ahsan M, Haider J, et al. Diabetic retinopathy identification using parallel convolutional neural network based feature extractor and ELM classifier. Expert Systems with Applications. 2023; 217:119557.

[26]Phridviraj MS, Bhukya R, Madugula S, Manjula A, Vodithala S, Waseem MS. A bi-directional long short-term memory-based diabetic retinopathy detection model using retinal fundus images. Healthcare Analytics. 2023; 3:100174.

[27]Hu D, Pan L, Chen X, Xiao S, Wu Q. A novel vessel segmentation algorithm for pathological en-face images based on matched filter. Physics in Medicine & Biology. 2023; 68(5):055014.

[28]Mousavi N, Monemian M, Ghaderi DP, Mirmohammadsadeghi M, Zekri M, Rabbani H. Cyst identification in retinal optical coherence tomography images using hidden markov model. Scientific Reports. 2023; 13(1):1-15.

[29]Akram MU, Khalid S, Tariq A, Khan SA, Azam F. Detection and classification of retinal lesions for grading of diabetic retinopathy. Computers in Biology and Medicine. 2014; 45:161-71.

[30]Ikechukwu AV, Murali S, Deepu R, Shivamurthy RC. ResNet-50 vs VGG-19 vs training from scratch: a comparative analysis of the segmentation and classification of Pneumonia from chest X-ray images. Global Transitions Proceedings. 2021; 2(2):375-81.

[31]Ikechukwu AV, Murali S. i-Net: a deep CNN model for white blood cancer segmentation and classification. International Journal of Advanced Technology and Engineering Exploration. 2022; 9(95):1448-64.

[32]Krizhevsky A, Sutskever I, Hinton GE. Imagenet classification with deep convolutional neural networks. Advances in Neural Information Processing Systems. 2012.

[33]Dieleman S, De FJ, Kavukcuoglu K. Exploiting cyclic symmetry in convolutional neural networks. In international conference on machine learning 2016 (pp. 1889-98). PMLR.

[34]Agughasi VI, Srinivasiah M. Semi-supervised labelling of chest x-ray images using unsupervised clustering for ground-truth generation. Applied Engineering and Technology. 2023; 2(3):188-202.

[35]Melinscak M, Prentasic P, Loncaric S. Retinal vessel segmentation using deep neural networks. In VISAPP 2015 (pp. 577-582). Scite Press.

[36]Liskowski P, Krawiec K. Segmenting retinal blood vessels with deep neural networks. IEEE Transactions on Medical Imaging. 2016; 35(11):2369-80.

[37]Zhang Y, He M, Chen Z, Hu K, Li X, Gao X. Bridge-net: context-involved U-net with patch-based loss weight mapping for retinal blood vessel segmentation. Expert Systems with Applications. 2022; 195:116526.

[38]Wang B, Qiu S, He H. Dual encoding u-net for retinal vessel segmentation. In medical image computing and computer assisted intervention: 22nd international conference, Shenzhen, China, 2019 (pp. 84-92). Springer International Publishing.

[39]Ronneberger O, Fischer P, Brox T. U-net: convolutional networks for biomedical image segmentation. In medical image computing and computer-assisted intervention: 18th international conference, Munich, Germany, 2015 (pp. 234-41). Springer International Publishing.

[40]Guo C, Szemenyei M, Yi Y, Wang W, Chen B, Fan C. Sa-unet: spatial attention u-net for retinal vessel segmentation. In 25th international conference on pattern recognition 2021 (pp. 1236-42). IEEE.

[41]Ikechukwu AV, Murali S. CX-Net: an efficient ensemble semantic deep neural network for ROI identification from chest-x-ray images for COPD diagnosis. Machine Learning: Science and Technology. 2023; 4(2):025021.

[42]Wu Y, Xia Y, Song Y, Zhang D, Liu D, Zhang C, et al. Vessel-net: retinal vessel segmentation under multi-path supervision. In medical image computing and computer assisted intervention: 22nd international conference, Shenzhen, China, 2019 (pp. 264-72). Springer International Publishing.

[43]Zhang S, Fu H, Yan Y, Zhang Y, Wu Q, Yang M, et al. Attention guided network for retinal image segmentation. In medical image computing and computer assisted intervention: 22nd international conference, Shenzhen, China, 2019 (pp. 797-805). Springer International Publishing.

[44]Xu Y, Fan Y. Dual-channel asymmetric convolutional neural network for an efficient retinal blood vessel segmentation in eye fundus images. Biocybernetics and Biomedical Engineering. 2022; 42(2):695-706.

[45]Kumar KS, Singh NP. Analysis of retinal blood vessel segmentation techniques: a systematic survey. Multimedia Tools and Applications. 2023; 82(5):7679-733.

[46]Remeseiro B, Mendonça AM, Campilho A. Automatic classification of retinal blood vessels based on multilevel thresholding and graph propagation. The Visual Computer. 2021; 37(6):1247-61.

[47]https://drive.grand-challenge.org/DRIVE/. Accessed 05 September 2024.

[48]Yang B, Zhao H, Cao L, Liu H, Wang N, Li H. Retinal image enhancement with artifact reduction and structure retention. Pattern Recognition. 2023; 133:108968.

[49]Sanjani SS, Boin JB, Bergen K. Blood vessel segmentation in retinal fundus images. Stanford University. 2013.

[50]Tamim N, Elshrkawey M, Abdel AG, Nassar H. Retinal blood vessel segmentation using hybrid features and multi-layer perceptron neural networks. Symmetry. 2020; 12(6):1-27.

[51]Cervantes J, Cervantes J, García-lamont F, Yee-rendon A, Cabrera JE, Jalili LD. A comprehensive survey on segmentation techniques for retinal vessel segmentation. Neurocomputing. 2023; 556:126626.

[52]Jena PK, Khuntia B, Palai C, Nayak M, Mishra TK, Mohanty SN. A novel approach for diabetic retinopathy screening using asymmetric deep learning features. Big Data and Cognitive Computing. 2023; 7(1):1-16.

[53]Kauppi T, Kalesnykiene V, Kamarainen JK, Lensu L, Sorri I, Raninen A, et al. The diaretdb1 diabetic retinopathy database and evaluation protocol. In BMVC 2007 (pp. 1-18).