Top

International Ophthalmology

Published in:

01-12-2024 | Diabetic Retinopathy | Original Paper

Resilient back-propagation machine learning-based classification on fundus images for retinal microaneurysm detection

Authors: S. Steffi, W. R. Sam Emmanuel

Published in: International Ophthalmology | Issue 1/2024

Abstract

Background

The timely diagnosis of medical conditions, particularly diabetic retinopathy, relies on the identification of retinal microaneurysms. However, the commonly used retinography method poses a challenge due to the diminutive dimensions and limited differentiation of microaneurysms in images.

Problem Statement

Automated identification of microaneurysms becomes crucial, necessitating the use of comprehensive ad-hoc processing techniques. Although fluorescein angiography enhances detectability, its invasiveness limits its suitability for routine preventative screening.

Objective

This study proposes a novel approach for detecting retinal microaneurysms using a fundus scan, leveraging circular reference-based shape features (CR-SF) and radial gradient-based texture features (RG-TF).

Methodology

The proposed technique involves extracting CR-SF and RG-TF for each candidate microaneurysm, employing a robust back-propagation machine learning method for training. During testing, extracted features from test images are compared with training features to categorize microaneurysm presence.

Results

The experimental assessment utilized four datasets (MESSIDOR, Diaretdb1, e-ophtha-MA, and ROC), employing various measures. The proposed approach demonstrated high accuracy (98.01%), sensitivity (98.74%), specificity (97.12%), and area under the curve (91.72%).

Conclusion

The presented approach showcases a successful method for detecting retinal microaneurysms using a fundus scan, providing promising accuracy and sensitivity. This non-invasive technique holds potential for effective screening in diabetic retinopathy and other related medical conditions.

Lee R, Wong TY, Sabanayagam C (2015) Epidemiology of diabetic retinopathy, diabetic macular edema, and related vision loss. Eye and vision 2(1):17PubMedPubMedCentralCrossRef

Wilkinson C, Ferris FL, Klein RE et al (2003) Proposed international clinical diabetic retinopathy and diabetic macular edema disease severity scales. Ophthalmology 110(9):1677–1682PubMedCrossRef

Yau JW, Rogers SL, Kawasaki R et al (2012) Global prevalence and major risk factors of diabetic retinopathy. Diabetes Care 35(3):556–564PubMedPubMedCentralCrossRef

Ahmed NGA, Hamza MF, Hassan SN (2023) Knowledge, practice and attitude of diabetic patients regarding prevention of diabetic retinopathy. J Surv Fisher Sci 10(3S):3896–3908

Lyssekboron A, Wylegala A, Polanowska K, Krysik K, Dobrowolski D (2017) Longitudinal changes in retinal nerve fiber layer thickness evaluated using avanti rtvue-xr optical coherence tomography after 23g vitrectomy for epiretinal membrane in patients with open-angle glaucoma. J Healthc Eng 2017:4673714–4673714PubMed

Salz DA, Witkin AJ (2015) Imaging in diabetic retinopathy. Middle East Afr J Ophthalmol 22(2):145–150PubMedPubMedCentralCrossRef

Bernardes R, Serranho P, Lobo C (2011) Digital ocular fundus imaging: a review. Ophthalmological 226(4):161–181CrossRef

Chew EY, Ferris FL (2006) Chapter 67—nonproliferative diabetic retinopathy. In: Ryan SJ, Hinton DR, Schachat AP, Wilkinson CP (eds.) Retina, Fourth edition edn., Mosby, Edinburgh, pp 1271–1284

Eftekhari N, Pourreza HR, Masoudi M, Ghiasishirazi K, Saeedi E (2019) Microaneurysm detection in fundus images using a two-step convolutional neural network. Biomed Eng Online 18(1):67PubMedPubMedCentralCrossRef

10.

Chaturvedi SS, Gupta K, Ninawe V, Prasad PS (2019) Advances in computer-aided Diagnosis of diabetic retinopathy. arXiv e-prints, 1909–09853

11.

Saha S, Xiao D, Bhuiyan A, Wong TY, Kanagasingam Y (2019) Color fundus image registration techniques and applications for automated analysis of diabetic retinopathy progression: a review. Biomed Signal Process Control 47:288–302CrossRef

12.

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

13.

Biyani RS, Patre BM (2018) Algorithms for red lesion detection in diabetic retinopathy: a review. Biomed Pharmacother 107:681–688PubMedCrossRef

14.

Chen Z, Chen B et al (2022) A preliminary observation on rod cell photo biomodulation in treating diabetic macular edema. Adv Ophthalmol Pract Res 2(2):10051

15.

Lazar I, Hajdu A (2011) Microaneurysm detection in retinal images using a rotating cross-section-based model. In: 2011 IEEE international symposium on biomedical imaging: from nano to macro. Piscataway: IEEE, p 1405–1409

16.

Lazar I, Hajdu A (2013) Retinal microaneurysm detection through local rotating cross-section profile analysis. IEEE TransMed Imaging 32(2):400–407CrossRef

17.

Niemeijer M, Van Ginneken B, Staal J, Suttorp-Schulten MS, Abràmoff MD (2005) Automatic detection of red lesions in digital color fundus photographs. IEEE Trans Med Imaging 24(5):584–592PubMedCrossRef

18.

Giancardo L, Meriaudeau F, Karnowski TP, Li Y, Tobin KW, Chaum E (2011) Microaneurysm detection with radon transform-based classification on retina images. In: international conference of the IEEE engineering in medicine and biology society, pp 5939–5942

19.

Zhang B, Wu X, You J, Li Q, Karray F (2010) Detection of microaneurysms using multi-scale correlation coefficients. Pattern Recogn 43(6):2237–2248ADSCrossRef

20.

Ram K, Joshi GD, Sivaswamy J (2011) A successive clutter-rejection-based approach for early detection of diabetic retinopathy. IEEE Trans Biomed Eng 58(3):664–673PubMedCrossRef

21.

Saha, R., Chowdhury, A. R., & Banerjee, S. (2016). Diabetic retinopathy related lesions detection and classification using machine learning technology. In Artificial Intelligence and Soft Computing: 15th International Conference, ICAISC 2016, Zakopane, Poland, June 12–16, 2016, Proceedings, Part II 15 (pp. 734–745). Springer International Publishing.

22.

Zhou W, Wu C, Chen D, Yi Y, Du W (2017) Automatic microaneurysm detection using the sparse principal component analysis-based unsupervised classification method. IEEE Access 5:2563–2572CrossRef

23.

Srivastava R, Duan L, Wong DWK, Liu J, Wong TY (2016) Detecting retinal microaneurysms and haemorrhages with robustness to the presence of blood vessels. Comput Methods Progr Biomed 138:83–91CrossRef

24.

Wu B, Zhu W, Shi F, Zhu S, Chen X (2017) Automatic detection of microaneurysms in retinal fundus images. Comput Med Imaging Gr 55:106–112CrossRef

25.

Wang S, Tang HL, Turk LA, Hu Y, Sanei S, Saleh GM, Peto T (2017) Localizing microaneurysms in fundus images through singular spectrum analysis. IEEE Trans Biomed Eng 64(5):990–1002ADSPubMedCrossRef

26.

Derwin DJ, Selvi ST, Singh OJ (2019) Secondary observer system for detection of microaneurysms in fundus images using texture descriptors. J Digit Imaging 33(1):159–167PubMedCentralCrossRef

27.

Mizutani A, Muramatsu C, Hatanaka Y, Suemori S, Hara T, Fujita H(2009) Automated microaneurysm detection method based on double-ring filter in retinal fundus images. In: proceedings of SPIE medical imaging, vol 7260, 2009, pp 72 601N–72 601N–8

28.

Zhang X (2014) Image processing methods for computer-aided screening of diabetic retinopathy, Ph.D. dissertation, EcoleNationaleSup´erieuredesMines de Paris, Paris

29.

Adal KM, Sidib D, Ali S, Chaum E, Karnowski TP, Mriaudeau F (2014) Automated detection of microaneurysms using scale-adapted blob analysis and semi-supervised learning. Comput Methods Programs Biomed 114(1):1–10PubMedCrossRef

30.

Dai B, Wu X, Bu W (2016) Retinal microaneurysms detection using gradient vector analysis and class imbalance classification. PLoS ONE 11(8):1–23CrossRef

31.

Budak U, Şengür A, Guo Y, Akbulut Y (2017) A novel microaneurysms detection approach based on convolutional neural networks with reinforcement sample learning algorithm. Health Inf Sci Syst 5(1):14PubMedPubMedCentralCrossRef

32.

Wang S, Tang HL, Hu Y et al (2017) Localizing microaneurysms in fundus images through singular spectrum analysis. IEEE Trans Biomed Eng 64(5):990–1002ADSPubMedCrossRef

33.

Seoud L, Hurtut T, Chelbi J, Cheriet F, Langlois JMP (2016) Redlesion detection using dynamic shape features for diabetic retinopathy screening. IEEE Trans Med Imag 35(4):1116–1126CrossRef

34.

Eftekhari N et al (2019) Microaneurysm detection in fundus images using a two-step convolutional neural network. Biomed Eng Online 18(1):1–16CrossRef

35.

Dashtbozorg B et al (2018) Retinal microaneurysms detection using local convergence index features. IEEE Trans Image Process 27(7):3300–3315ADSMathSciNetPubMedCrossRef

36.

Habib MM et al (2017) Detection of microaneurysms in retinal images using an ensemble classifier. Inf Med Unlocked 9:44–57CrossRef

37.

Lazar I, Hajdu A (2013) Retinal microaneurysm detection through local rotating cross-section profile analysis. IEEE Trans Med Imag 32(2):400–407CrossRef

38.

Zhang X (2014) Image processing methods for computer-aided screening of diabetic retinopathy, Ph.D. dissertation, EcoleNationaleSuperieure des ´ Mines de Paris, Paris

39.

Ali Shah SA, Laude A, Faye I, Tang TB (2016) Automated microaneurysm detection in diabetic retinopathy using curvelet transform. J Biomed Opt 21(10):101404PubMedCrossRef

40.

Wang S, Tang HL, Turk LIA et al (2017) Localizing microaneurysms in fundus images through singular spectrum analysis. IEEE Trans Biomed Eng 64(5):990–1002ADSPubMedCrossRef

41.

Mayya V, Sowmya Kamath S, Kulkarni U (2021) Automated microaneurysms detection for early diagnosis of diabetic retinopathy: a comprehensive review. Comput Methods Progr Biomed Update 1:100013CrossRef

42.

Suchetha M, Sai Ganesh N, Raman R, Edwin Dhas D (2021) Region of interest-based predictive algorithm for subretinal hemorrhage detection using faster R-CNN. Soft Comput 25(24):15255–15268PubMedPubMedCentralCrossRef

43.

Yadav D, Karn AK, Giddalur A, Dhiman A, Sharma S, Yadav AK (2021) Microaneurysm detection using color locus detection method. Measurement 176:109084CrossRef

44.

Dai B, Xiangqian Wu, Wei Bu (2016) Retinal microaneurysms detection using gradient vector analysis and class imbalance classification. PLoS ONE 11(8):e0161556PubMedPubMedCentralCrossRef

45.

Bradley D, Roth G (2007) Adapting thresholding using the integral image. J Gr Tools 12(2):13–21CrossRef

46.

Naoum RS, Abid NA, Al-Sultani ZN (2012) An enhanced resilient backpropagation artificial neural network for the intrusion detection system. Int J Comput Sci Netw Secur (IJCSNS) 12(3):11

47.

MESSIDOR: Methods for evaluating segmentation and indexing techniques dedicated to retinal ophthalmology. https://www.scribd.com/document/70380364/Messidor-Abstract-En

48.

Kauppi T, Kalesnykiene V, Kamarainen J, Lensu L, Sorri I, Raninen A, Voutilainen R, Uusitalo H, K¨alvi¨ainen H, Pietil¨a J (2007) DIARETDB1diabeticretinopathy database and evaluation protocol. In: 11th conference on medical image understanding and analysis

49.

Decenciere E, Cazuguel G, Zhang X et al (2013) TeleOphta: Machine learning and image processing methods for teleophthalmology. IRBM 34(2):196–203CrossRef

50.

Niemeijer M, Van Ginneken B, Cree MJ et al (2010) Retinopathy online challenge: automatic detection of microaneurysms in digital color fundus photographs. IEEE Trans Med Imag 29(1):185–195CrossRef

Title: Resilient back-propagation machine learning-based classification on fundus images for retinal microaneurysm detection
Authors: S. Steffi
W. R. Sam Emmanuel
Publication date: 01-12-2024
Publisher: Springer Netherlands
Keywords: Diabetic Retinopathy
Diabetic Retinopathy
Published in: International Ophthalmology / Issue 1/2024
Print ISSN: 0165-5701
Electronic ISSN: 1573-2630
DOI: https://doi.org/10.1007/s10792-024-02982-5

Keynote webinar | Spotlight on medication adherence

Springer Medicine

Resilient back-propagation machine learning-based classification on fundus images for retinal microaneurysm detection

Abstract

Background

Problem Statement

Objective

Methodology

Results

Conclusion

Keynote webinar | Spotlight on medication adherence

Springer Medicine

Abstract

Background

Problem Statement

Objective

Methodology

Results

Conclusion

Please log in to get access to this content

Other articles of this Issue 1/2024

Effect of direct oral anticoagulants on bleeding during and after cataract surgery

Orbital fat graft retroseptal transconjunctival blepharoplasty for treatment of groove in the infraorbital region

Choroidal, retinal, and optic nerve changes in rheumatoid arthritis and primary sjogren’s syndrome patients: comparıson with each other and healthy subjects

Posterior vitreous attachment as a risk factor for endophthalmitis following intravitreal antivascular endothelial growth factor injection

Long-term clinical outcomes of patients with sympathetic ophthalmia

Thickness of anterior sclera and corneal layers in systemic sclerosis