Skip to main content
SpringerLink
Log in

Comparative study of different machine learning models for automatic diabetic retinopathy detection using fundus image

  • Published:
Multimedia Tools and Applications Aims and scope Submit manuscript

Abstract

Diabetics suffer from an eye condition called diabetic retinopathy (DR), which can lead to vision loss. The main region affected is the blood vessels in the retina. A large proportion of the world's population is suffering from the harmful effects of diabetes, and most of them are not recognized early. Severe vision loss can be reduced through early detection, diagnosis, and treatment efficiency. The manual errors and tedious work of ophthalmologists can be reduced by using computer-assisted automatic diagnosis of DR. This paper provides a comparative study and analysis of different segmentation, feature extraction and classification methods used for the automatic detection of DR. The fundus images from the Kaggle data set will be used to evaluate these techniques. The best results were obtained when Watershed Transform (WT) and Triplet Half Band Filter Bank (THFB) based segmentation and Haralick, and ADTCWT (Anisotropic Dual Tree Complex Wavelet Transform) based feature extraction together with machine learning based SVM (Support Vector Machine) classifier. The performance of the classifiers was evaluated in terms of accuracy, precision, F-Score, TPR (True Positive Rate), TNR (True Negative Rate), Kappa, FPR (False Positive Rate), FNR (False Negative rate), pixel accuracy, Jaccard similarity, cube coefficient, VOE (volumetric overlap error) and SVD (symmetric volume difference). The SVM model obtained a training accuracy of (98.42%).

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14

Similar content being viewed by others

Data availability

Data sharing does not apply to this article.

References

  1. Sankaran S, Murugan PR, Britto PI, Thiyagarajan A and Govindaraj V (2021) A guidance system to read and analyze the traffic rules for the visually impaired human. In Electronic Devices, Circuits, and Systems for Biomedical Applications, Academic Press, Elsevier 17:365–377

  2. Lawrenson JG, Bourmpaki E, BunceC Stratton IM, Gardner P, Anderson J (2021) EROS Study Group. Trends in diabetic retinopathy screening attendance and associations with vision impairment attributable to diabetes in a large nationwide cohort. Diabet Med 38(4):1–11

    Google Scholar 

  3. Tönnies T, Röckl S, Hoyer A, Heidemann C, Baumert J, Du Y, Scheidt-Nave C, Brinks R (2019) Projected number of people with diagnosed Type 2 diabetes in Germany in 2040. Diabet Med 36(10):1217–1225

    Google Scholar 

  4. Nisha KL, Sreelekha G, Sathidevi PS, Mohanachandran P, Vinekar A (2019) A computer-aided diagnosis system for plus disease in retinopathy of prematurity with structure adaptive segmentation and vessel based features. Comput Med Imaging Graph 74:72–94

    Google Scholar 

  5. Uysal E, Güraksin GE (2021) Computer-aided retinal vessel segmentation in retinal images: convolutional neural networks. Multimedia Tools and Applications 80(3):3505–3528

    Google Scholar 

  6. Ramani RG, Jeslin Shanthamalar J (2020) Improved image processing techniques for optic disc segmentation in retinal fundus images. Biomed Signal Process Control 58:1–18

    Google Scholar 

  7. Graham PS, Kaidonis G, Abhary S, Gillies MG, Daniell M, Essex RW, Chang JH (2018) Genome-wide association studies for diabetic macular edema and proliferative diabetic retinopathy. BMC Med Genet 19(1):1–8

    Google Scholar 

  8. Kandhasamy JP, Balamurali S, Kadry S, Ramasamy LK (2020) Diagnosis of diabetic retinopathy using multi-level set segmentation algorithm with feature extraction using svm with selective features. Multimedia Tools and Applications 79(15):10581–10596

    Google Scholar 

  9. Das D, Biswas SK, Bandyopadhyay S (2022) A critical review on diagnosis of diabetic retinopathy using machine learning and deep learning. Multimedia Tools Appl 81:25613–25655

    Google Scholar 

  10. Raevis J, Elmalem VI (2020) Pseudotumor cerebri syndrome causing a terson like syndrome. Am J Ophthalmol Case Rep 20:100993

    Google Scholar 

  11. Fraz MM, Badar M, Malik AW, Barman SA (2019) Computational methods for exudates detection and macular edema estimation in retinal images: a survey. Arch Comput Methods Eng 26(4):1193–1220

    Google Scholar 

  12. Asiri N, HussainM AFA, Alzaidi N (2019) Deep learning based computer-aided diagnosis systems for diabetic retinopathy: A survey. Artif Intell Med 99:1–20

    Google Scholar 

  13. Yanase J, Triantaphyllou E (2019) A systematic survey of computer-aided diagnosis in medicine: Past and present developments. Expert Syst Appl 138:1–25

    Google Scholar 

  14. Saygılı A (2021) A new approach for computer-aided detection of coronavirus (COVID-19) from CT and X-ray images using machine learning methods. Appl Soft Comput 105:1–17

    Google Scholar 

  15. Bhardwaj C, Jain S, Sood M (2021) Hierarchical severity grade classification of non-proliferative diabetic retinopathy. J Ambient Intell Humaniz Comput 12(2):2649–2670

    Google Scholar 

  16. Stolte S, Fang R (2020) A survey on medical image analysis in diabetic retinopathy. Med Image Anal 64:1–75

    Google Scholar 

  17. Rahim T, Usman MA, Shin SY (2020) A survey on contemporary computer-aided tumor, polyp, and ulcer detection methods in wireless capsule endoscopy imaging. Comput Med Imaging Graph 85:1–25

    Google Scholar 

  18. Kumar SD, Esakkirajan S, Bama S, Keerthiveena B (2020) A microcontroller based machine vision approach for tomato grading and sorting using SVM classifier. Microprocess Microsyst 76:1–13

    Google Scholar 

  19. Wu Z, Shi G, Chen Y, Shi F, Chen X, Coatrieux G, Yang J, Luo L, Li S (2020) Coarse-to-fine classification for diabetic retinopathy grading using convolutional neural network. Artif Intell Med 108:1–9

    Google Scholar 

  20. Berbar MA (2022) Features extraction using encoded local binary pattern for detection and grading diabetic retinopathy. Health Information Science and Systems 10(1):1–13

    Google Scholar 

  21. Subramanian B, Saravanan V, Nayak RK, Gunasekaran T, Hariprasath S (2019) Diabetic Retinopathy-Feature Extraction and Classification using Adaptive Super Pixel Algorithm. Int J Eng Adv Technol 9:618–627

    Google Scholar 

  22. Shankar K, Perumal E, Vidhyavathi RM (2020) Deep neural network with moth search optimization algorithm based detection and classification of diabetic retinopathy images. SN Applied Sciences 2(4):1–10

    Google Scholar 

  23. Jadhav AS, Patil PB, Biradar S (2021) Optimal feature selection-based diabetic retinopathy detection using improved rider optimization algorithm enabled with deep learning. Evol Intel 14(4):1431–1448

    Google Scholar 

  24. Randive SN, Rahulkar AD, Senapati RK (2018) LVP extraction and triplet-based segmentation for diabetic retinopathy recognition. Evol Intel 11(1):117–129

    Google Scholar 

  25. Vinayaki VD, Kalaiselvi R (2022) Multithreshold image segmentation technique using remora optimization algorithm for diabetic retinopathy detection from fundus images. Neural Process Lett 54(3):2363–2384

    Google Scholar 

  26. Abdelmaksoud E, El-Sappagh S, BarakatS AT, Elmogy M (2021) Automatic diabetic retinopathy grading system based on detecting multiple retinal lesions. IEEE Access 9:15939–15960

    Google Scholar 

  27. Bhardwaj C, Jain S, Sood M (2021) Transfer learning based robust automatic detection system for diabetic retinopathy grading. Neural Comput Appl 33(20):13999–14019

    Google Scholar 

  28. Nazir T, Irtaza A, Shabbir Z, Javed A, Akram U, Mahmood MT (2019) Diabetic retinopathy detection through novel tetragonal local octa patterns and extreme learning machines. Artif Intell Med 99:1–10

    Google Scholar 

  29. Amin J, Sharif M, Rehman A, Raza M, Mufti MR (2018) Diabetic retinopathy detection and classification using hybrid feature set. Microsc Res Tech 81(9):990–996

    Google Scholar 

  30. Gayathri S, Gopi VP, Palanisamy P (2020) A lightweight CNN for Diabetic Retinopathy classification from fundus images. Biomed Signal Process Control 62:1–11

    Google Scholar 

  31. Gayathri S, Krishna AK, Gopi VP, Palanisamy P (2020) Automated binary and multi-class classification of diabetic retinopathy using haralick and multiresolution features. IEEE Access 8:1–11

    Google Scholar 

  32. Rundo L, Tangherloni A, Galimberti S, Cazzaniga P, Woitek R, Sala E, Nobile MS, Mauri M (2019) HaraliCU: GPU-powered Haralick feature extraction on medical images exploiting the full dynamics of gray-scale levels. In: Parallel Computing Technologies: 15th International Conference, PaCT 2019, Almaty, Kazakhstan, August 19–23, Proceedings, vol 15. Springer International Publishing, pp 304–318

  33. Kausu TR, Gopi VP, Wahid KA, Doma W, Niwas SI (2018) Combination of clinical and multiresolution features for glaucoma detection and its classification using fundus images. Biocybernetics and Biomedical Engineering 38(2):329–341

    Google Scholar 

  34. Tavakoli M, Mehdizadeh A, Shahri RP, Dehmeshki J (2021) Unsupervised automated retinal vessel segmentation based on Radon line detector and morphological reconstruction. IET Image Proc 15(7):1484–1498

    Google Scholar 

  35. Gadekallu TR, KhareN, Bhattacharya S, Singh S, Maddikunta PKR and Srivastava G (2020) Deep neural networks to predict diabetic retinopathy. J Ambient Intell Humaniz Comput 1–14

  36. Salamat N, Missen MMS, Rashid A (2019) Diabetic retinopathy techniques in retinal images: A review. Artif Intell Med 97:168–188

    Google Scholar 

  37. Koh JEW, Ng EYK, Bhandary SV, Laude A, Acharya UR (2018) Automated detection of retinal health using PHOG and SURF features extracted from fundus images. Appl Intell 48(5):1379–1393

    Google Scholar 

  38. Derwin DJ, Tamil Selvi S, Jeba Singh O, Priestly Shan B (2020) A novel automated system of discriminating Microaneurysms in fundus images. Biomed Signal Process Control 58:1–9

    Google Scholar 

  39. Barmparis GD, Tsironis GP (2020) Estimating the infection horizon of COVID-19 in eight countries with a data-driven approach. Chaos, Solitons Fractals 135(109842):1–5

    Google Scholar 

  40. Kumar S, Adarsh A, Kumar B, Singh AK (2020) An automated early diabetic retinopathy detection through improved blood vessel and optic disc segmentation. Opt Laser Technol 121:1–11

    Google Scholar 

  41. Shinde A, Rahulkar A, Patil C (2019) Biomedical image indexing and retrieval based on new efficient hybrid approach using directional decomposition and a novel local directional frequency encoded pattern: a post feature descriptor. Multimedia Tools Appl 78(16):23483–23519

    Google Scholar 

  42. Adem K (2018) Exudate detection for diabetic retinopathy with circular Hough transformation and convolutional neural networks. Expert Syst Appl 114:289–295

    Google Scholar 

  43. Mayya V, Kamath S, Kulkarni U (2021) Automated microaneurysms detection for early diagnosis of diabetic retinopathy: A Comprehensive review. Comput Methods Programs Biomed Update 1:1–45

    Google Scholar 

  44. Ahmadieh H, Behbahani S, Safi S (2021) Continuous wavelet transform analysis of ERG in patients with diabetic retinopathy. Doc Ophthalmol 142(3):305–314

    Google Scholar 

  45. Washburn PS (2020) Investigation of severity level of diabetic retinopathy using adaboost classifier algorithm. Mater Today: Proc 33:3037–3042

    Google Scholar 

  46. Mazlan N, Yazid H (2019) An improved retinal blood vessel segmentation for diabetic retinopathy detection. Comput Methods Biomech Biomed Eng: Imaging Vis 7(1):49–58

    Google Scholar 

  47. Remeseiro B, Mendonça AM, Campilho A (2021) Automatic classification of retinal blood vessels based on multi-level thresholding and graph propagation. Vis Comput 37(6):1247–1261

    Google Scholar 

  48. Gundluru N, Rajput DS, Lakshmanna K, Kaluri R, Shorfuzzaman M, Uddin M, Khan MAR (2022) Enhancement of detection of diabetic retinopathy using Harris hawks optimization with deep learning model. Comput Intell Neurosci 2022:1–13

    Google Scholar 

  49. Abrami A, Kavitha R (2023) A novel automated komodo Mlipir optimization based attention BiLSTM for early detection of diabetic retinopathy. Signal, Image Video Process 1–9

  50. Herliana A, Arifin T, Susanti S and Hikmah AB (2018) Feature selection of diabetic retinopathy disease using particle swarm optimization and neural network. In: 2018 6th International Conference on Cyber and IT Service Management (CITSM). IEEE, Parapat, Indonesia, pp 1–4

  51. Priya RP, Sivarani TS, Saravanan AG (2022) Deep long and short term memory based Red Fox optimization algorithm for diabetic retinopathy detection and classification. Int J Numer Methods Biomed Eng 38(3):e3560

    Google Scholar 

  52. Vinayaki VD, Kalaiselvi R (2022) Aquila Optimizer based deep neural network for Automatic Diabetic Retinopathy detection and classification. In: 2022 IEEE International Conference on Signal Processing, Informatics, Communication and Energy System (SPICES). IEEE, Thiruvananthapuram, India, pp 55–60

  53. Bellemo V, Lim G, Rim TH, Tan GSW, Cheung CY, Sadda S, He M-g et al (2019) Artificial intelligence screening for diabetic retinopathy: the real-world emerging application. Curr DiabRep 19:1–12

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Computer Science, Amity University, Noida, Uttar Pradesh, India

    Shubhi Gupta

  2. Amity University, Noida, Uttar Pradesh, India

    Sanjeev Thakur

  3. U.P. Rajarshi Tandon Open University, Noida, Uttar Pradesh, India

    Ashutosh Gupta

Authors
  1. Shubhi Gupta
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Sanjeev Thakur
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Ashutosh Gupta
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

All authors read and approved the final manuscript.

Corresponding author

Correspondence to Shubhi Gupta.

Ethics declarations

Ethical approval

This article does not contain any studies with human participants or animals performed by authors.

Consent to participate

All the authors involved have agreed to participate in this submitted article.

Consent to publish

All the authors involved in this manuscript give full consent for publication of this submitted article.

Conflict of interest

Authors declare that they have no conflict of interest.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Gupta, S., Thakur, S. & Gupta, A. Comparative study of different machine learning models for automatic diabetic retinopathy detection using fundus image. Multimed Tools Appl 83, 34291–34322 (2024). https://doi.org/10.1007/s11042-023-16813-9

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-023-16813-9

Keywords

Search

Navigation