banner

LW-CNN-based extraction with optimized encoder-decoder model for detection of diabetic retinopathy

B. Gunapriya, T. Rajesh, Arunadevi Thirumalraj, Manjunatha B

Abstract


In the field of computer vision, automatic diabetic retinopathy (D.R.) screening is a well-established topic of study. It’s tough since the retinal vessels are hardly distinguishable from the backdrop in the fundus picture, and the structure is complicated. To learn data representations at numerous levels of abstraction, deep learning (DL) allows for the development of computational representations with several processing layers. Small, inconspicuous lesions generated by the disorder are hard to detect since they are tucked away beneath the eye’s structure. In this research, a lightweight convolutional neural network (LW-CNN) was used to extract structures from images of blood vessels, and different preprocessing methods were employed. The features are extracted, and then D.R. is classified using the suggested learning technique, which includes an encoder, dense branch. Effective categorization relies on the usage of multi-scale information collected from various nodes in the network. Grasshopper’s optimisation algorithm (GHOA) is used to fine-tune the recommended classifier’s hyper-parameters. The DIARETDB1 benchmark dataset is assessed using 80% training data and 20% testing data to get a diagnosis of the disease’s severity. The proposed model improved D.R. image classification with accuracy of 0.992 for DIARETDB1 database and 0.981 for APTOS 2019 blindness detection dataset. The state-of-the-art models for D.R. dataset images only achieved less accuracy and precision as compared with the proposed model.


Keywords


diabetic retinopathy; lightweight convolutional neural network; grasshopper optimization algorithm; encoder structure; blood vessel feature extraction; fundus image

Full Text:

PDF

References


1. Zhang J, Deng Y, Wan Y, et al. Diabetes duration and types of diabetes treatment in data-driven clusters of patients with diabetes. Frontiers in Endocrinology. 2022, 13. doi: 10.3389/fendo.2022.994836

2. Cole JB, Florez JC. Genetics of diabetes mellitus and diabetes complications. Nature Reviews Nephrology. 2020, 16(7): 377-390. doi: 10.1038/s41581-020-0278-5

3. Udler MS. Type 2 Diabetes: Multiple Genes, Multiple Diseases. Current Diabetes Reports. 2019, 19(8). doi: 10.1007/s11892-019-1169-7

4. Xiong X, Yang Y, Wei L, et al. Identification of two novel subgroups in patients with diabetes mellitus and their association with clinical outcomes: A two‐step cluster analysis. Journal of Diabetes Investigation. 2021, 12(8): 1346-1358. doi: 10.1111/jdi.13494

5. Tanabe H, Saito H, Kudo A, et al. Factors Associated with Risk of Diabetic Complications in Novel Cluster-Based Diabetes Subgroups: A Japanese Retrospective Cohort Study. Journal of Clinical Medicine. 2020, 9(7): 2083. doi: 10.3390/jcm9072083

6. Zaharia OP, Strassburger K, Strom A, et al. Risk of diabetes-associated diseases in subgroups of patients with recent-onset diabetes: A -year follow-up study. The Lancet Diabetes & Endocrinology. 2019, 7(9): 684-694. doi: 10.1016/s2213-8587(19)30187-1

7. Tong N, Wang L, Gong H, et al. Clinical Manifestations of Supra-Large Range Nonperfusion Area in Diabetic Retinopathy. International Journal of Clinical Practice. 2022, 2022: 1-7. doi: 10.1155/2022/8775641

8. Lin K, Hsih W, Lin Y, et al. Update in the epidemiology, risk factors, screening, and treatment of diabetic retinopathy. Journal of Diabetes Investigation. 2021, 12(8): 1322-1325. doi: 10.1111/jdi.13480

9. Takao T, Suka M, Yanagisawa H, et al. Combined effect of diabetic retinopathy and diabetic kidney disease on all‐cause, cancer, vascular and non‐cancer non‐vascular mortality in patients with type 2 diabetes: A real‐world longitudinal study. Journal of Diabetes Investigation. 2020, 11(5): 1170-1180. doi: 10.1111/jdi.13265

10. Gomułka K, Ruta M. The Role of Inflammation and Therapeutic Concepts in Diabetic Retinopathy—A Short Review. International Journal of Molecular Sciences. 2023, 24(2): 1024. doi: 10.3390/ijms24021024

11. Wang CY, Mukundan A, Liu YS, et al. Optical Identification of Diabetic Retinopathy Using Hyperspectral Imaging. Journal of Personalized Medicine. 2023, 13(6): 939. doi: 10.3390/jpm13060939

12. Serey J, Alfaro M, Fuertes G, et al. Pattern Recognition and Deep Learning Technologies, Enablers of Industry 4.0, and Their Role in Engineering Research. Symmetry. 2023, 15(2): 535. doi: 10.3390/sym15020535

13. Deshpande NM, Gite SS, Aluvalu R. Microscopic Analysis of Blood Cells for Disease Detection: A Review. Tracking and Preventing Diseases with Artificial Intelligence. 2021, 125-151. doi: 10.1007/978-3-030-76732-7_6

14. Gangwar AK, Ravi V. Diabetic Retinopathy Detection Using Transfer Learning and Deep Learning. Advances in Intelligent Systems and Computing. 2020, 679-689. doi: 10.1007/978-981-15-5788-0_64

15. Yi SL, Yang XL, Wang TW, et al. Diabetic Retinopathy Diagnosis Based on RA-EfficientNet. Applied Sciences. 2021, 11(22): 11035. doi: 10.3390/app112211035

16. Liu H, Yue K, Cheng S, et al. Hybrid Model Structure for Diabetic Retinopathy Classification. Journal of Healthcare Engineering. 2020, 2020: 1-9. doi: 10.1155/2020/8840174

17. Das S, Kharbanda K, M S, et al. Deep learning architecture based on segmented fundus image features for classification of diabetic retinopathy. Biomedical Signal Processing and Control. 2021, 68: 102600. doi: 10.1016/j.bspc.2021.102600

18. Yi D, Baltov P, Hua Y, et al. Compound Scaling Encoder-Decoder (CoSED) Network for Diabetic Retinopathy Related Bio-marker Detection. IEEE Journal of Biomedical and Health Informatics. 2023, 1-12. doi: 10.1109/jbhi.2023.3313785

19. Manan MA, Jinchao F, Khan TM, et al. Semantic segmentation of retinal exudates using a residual encoder–decoder architecture in diabetic retinopathy. Microscopy Research and Technique. 2023, 86(11): 1443-1460. doi: 10.1002/jemt.24345

20. Sadeghzadeh A, Junayed MS, Aydin T, et al. Hybrid CNN+Transformer for Diabetic Retinopathy Recognition and Grading. 2023 Innovations in Intelligent Systems and Applications Conference (ASYU). 2023. doi: 10.1109/asyu58738.2023.10296789

21. Chetoui M, Akhloufi MA. Federated Learning for Diabetic Retinopathy Detection Using Vision Transformers. BioMedInformatics. 2023, 3(4): 948-961. doi: 10.3390/biomedinformatics3040058

22. Wang Z, Lu H, Yan H, et al. Vison Transformer Adapter-based Hyperbolic Embeddings for Multi-lesion Segmentation in Diabetic Retinopathy. 2023. doi: 10.21203/rs.3.rs-2728770/v1

23. Dihin RA, AlShemmary E, Al-Jawher W. Diabetic Retinopathy Classification Using Swin Transformer with Multi Wavelet. Journal of Kufa for Mathematics and Computer. 2023, 10(2): 167-172. doi: 10.31642/jokmc/2018/100225

24. Dinpajhouh M, Seyyedsalehi SA. Automated detecting and severity grading of diabetic retinopathy using transfer learning and attention mechanism. Neural Computing and Applications. 2023, 35(33): 23959-23971. doi: 10.1007/s00521-023-09001-1

25. Ullah Z, Usman M, Latif S, et al. SSMD-UNet: semi-supervised multi-task decoders network for diabetic retinopathy segmentation. Scientific Reports. 2023, 13(1). doi: 10.1038/s41598-023-36311-0

26. Nahiduzzaman Md, Robiul Islam Md, Omaer Faruq Goni Md, et al. Diabetic retinopathy identification using parallel convolutional neural network based feature extractor and ELM classifier. Expert Systems with Applications. 2023, 217: 119557. doi: 10.1016/j.eswa.2023.119557

27. Alwakid G, Gouda W, Humayun M. Deep Learning-Based Prediction of Diabetic Retinopathy Using CLAHE and ESRGAN for Enhancement. Healthcare. 2023, 11(6): 863. doi: 10.3390/healthcare11060863

28. Ishtiaq U, Abdullah ERMF, Ishtiaque Z. A Hybrid Technique for Diabetic Retinopathy Detection Based on Ensemble-Optimized CNN and Texture Features. Diagnostics. 2023, 13(10): 1816. doi: 10.3390/diagnostics13101816

29. Sarathi MP, Dutta MK, Singh A, et al. Blood vessel inpainting based technique for efficient localization and segmentation of optic disc in digital fundus images. Biomedical Signal Processing and Control. 2016, 25: 108-117. doi: 10.1016/j.bspc.2015.10.012

30. Thirumalraj A, Asha V, Kavin BP. AI and IoT-Based Technologies for Precision Medicine. 2023

31. Wang P, Patel VM, Hacihaliloglu I. Simultaneous Segmentation and Classification of Bone Surfaces from Ultrasound Using a Multi-feature Guided CNN. Lecture Notes in Computer Science. 2018, 134-142. doi: 10.1007/978-3-030-00937-3_16

32. Das R M, Thirumalraj A, Rajesh T. An Improved ARO Model for Task Offloading in Vehicular Cloud Computing in VANET. 2023.

33. Saremi S, Mirjalili S, Lewis A. Grasshopper Optimisation Algorithm: Theory and application. Advances in Engineering Software. 2017, 105: 30-47. doi: 10.1016/j.advengsoft.2017.01.004

34. Kauppi T, Kalesnykiene V, Kamarainen JK, et al. the DIARETDB1 diabetic retinopathy database and evaluation protocol. Procedings of the British Machine Vision Conference 2007. 2007. doi: 10.5244/c.21.15

35. DIARETDB1. Diaretdb1 Diabetic Retinopathy Database and Evaluation Protocol. Available online: https://academictorrents.com/details/817b91fd639263f6f644de4ccc9575c20b005c6c (accessed on 30 May 2023).

36. Mohanty C, Mahapatra S, Acharya B, et al. Using Deep Learning Architectures for Detection and Classification of Diabetic Retinopathy. Sensors. 2023, 23(12): 5726. doi: 10.3390/s23125726

37. Baswaraju S, Maheswari VU, Chennam K, et al. Future Food Production Prediction Using AROA Based Hybrid Deep Learning Model in Agri-Sector. Human-Centric Intelligent Systems. 2023, 1-16.




DOI: https://doi.org/10.32629/jai.v7i3.1095

Refbacks

  • There are currently no refbacks.


Copyright (c) 2023 B. Gunapriya, T. Rajesh, Arunadevi Thirumalraj, Manjunatha B

License URL: https://creativecommons.org/licenses/by-nc/4.0/