Mathematical morphology for microaneurysm detection in fundus images

Abstract

Aim:

Fundus image analysis is the basis for the better understanding of retinal diseases which are found due to diabetes. Detection of earlier markers such as microaneurysms that appear in fundus images combined with treatment proves beneficial to prevent further complications of diabetic retinopathy with an increased risk of sight loss.

Methods:

The proposed algorithm consists of three modules: (1) image enhancement through morphological processing; (2) the extraction and removal of red structures, such as blood vessels preceded by detection and removal of bright artefacts; (3) finally, the true microaneurysm candidate selection among other structures based on feature extraction set.

Results:

The proposed strategy is successfully evaluated on two publicly available databases containing both normal and pathological images. The sensitivity of 89.22%, specificity of 91% and accuracy of 92% achieved for the detection of microaneurysms for Diaretdb1 database images. The algorithm evaluation for microaneurysm detection has a sensitivity of 83% and specificity 82% for e-ophtha database.

Conclusion:

In automated detection system, the successful detection of the number of microaneurysms correlates with the stages of the retinal diseases and its early diagnosis. The results for true microaneurysm detection indicates it as a useful tool for screening colour fundus images, which proves time saving for counting of microaneurysms to follow Diabetic Retinopathy Grading Criteria.

Keywords

Fundus images microaneurysms diabetic retinopathy morphology red lesions

Get full access to this article

View all access options for this article.

References

Baudoin

Lay

Klein

JC.

Automatic detection of microaneurysms in diabetic fluorescein angiography. Rev Epidemiol Sante Publique 1984; 32(3–4): 254–261.

Spencer

Phillips

Sharp

PF.

Automated detection and quantification of microaneurysms in fluorescein angiograms. Graefes Arch Clin Exp Ophthalmol 1992; 230(1): 36–41.

Cree

Gamble

Cornforth

DJ.

Color normalization to reduce inter-patient and intra-patient variability in microaneurysms detection in color retinal images. In: Proceedings of the APRS workshop on digital image computing, Brisbane, QLD, Australia, 21 February 2005.

Frame

Undrill

Cree

, et al. A comparison of computer based classification methods applied to the detection of microaneurysms in ophthalmic fluorescein angiograms. Comput Biol Med 1998; 28(3): 225–238.

Niemeijer

van Ginneken

Staal

, et al. Automatic detection of red lesions in digital color fundus photographs. IEEE Trans Med Imag 2005; 24(5): 584–592.

Fleming

Phillip

Goatman

. Automated microaneurysm detection using local contrast normalization and local vessel detection. IEEE Trans Med Imag 2006: 1223–1232.

Ram

Joshi

Sivaswamy

A successive clutter-rejection-based approach for early detection of diabetic retinopathy. IEEE Trans Biomed Eng 2011; 58(3): 664–673.

Huang

Yan

. A local adaptive algorithm for microaneurysms detection in digital fundus images. In: Proceedings of the computer vision for biomedical image applications symposium, Beijing, China, 21 October 2005.

Hipwell

Strachan

Olson

, et al. Automated detection of microaneurysms in digital red-free photographs: a diabetic retinopathy screening tool. Diabet Med 2000: 588–594.

10.

Zhang

Fan

Retinal spot lesion detection using adaptive multiscale morphological processing. In: Proceedings of the symposium advances in visual computing, Lake Tahoe, NV, 6–8 November 2006, pp. 490–501. New York: Springer.

11.

Kande

Savithri

Subbaiah

PV.

Automatic detection of microaneurysms and hemorrhages in digital fundus images. J Digit Imaging 2010; 23(4): 430–437.

12.

Quellec

Lamard

Josselin

, et al. Optimal wavelet transform for the detection of microaneurysms in retina photographs. IEEE Trans Med Imaging 2008; 27(9): 1230–1241.

13.

Azar

Balas

. Classification and detection of diabetic retinopathy. Adv Intell Ann Med Data Decision 2013; 473: 135–145.

14.

Rahim

Jayne

Palade

, et al. Automatic detection of microaneurysms in colour fundus images for diabetic retinopathy screening. Neural Comput Appl 2016; 27(5): 1149–1164.

15.

Jelinek

Cree

Worsley

, et al. An automated microaneurysm detector as a tool for identification of diabetic retinopathy in rural optometric practice. Clin Exp Optom 2006; 89(5): 299–305.

16.

Orlando

Prokofyeva

Del Fresno

, et al. An ensemble deep learning based approach for red lesion detection in fundus images. Comput Methods Programs Biomed 2018; 153: 115–127.

17.

Kahai

Namuduri

Thompson

A decision support framework for automated screening of diabetic retinopathy. Int J Biomed Imaging 2006; 2006: 45806.

18.

Akram

Khalid

Khana

SA.

Identification and classification of microaneurysms for early detection of diabetic retinopathy. Pattern Recogn 2012; 46(1): 107–116.

19.

Dupas

Walter

Erginay

, et al. Evaluation of automated fundus photograph analysis algorithms for detecting microaneurysms, haemorrhages and exudates, and of a computer-assisted diagnostic system for grading diabetic retinopathy. Diabetes Metab 2010; 36(1): 213–220.

20.

Walter

Massin

Erginay

, et al. Automatic detection of microaneurysms in color fundus images. Med Image Anal 2007; 11: 555–566.

21.

Jimenez

Alemany

Benjumea

, et al. Automatic detection of microaneurysms in color fundus images. Arch Soc Esp Oftalmol 2011; 86(9): 277–281.

22.

Srivastava

Duan

Wong

DWK

, et al. Detecting retinal microasneurysms and hemorrhages with robustness to the presence of blood vessels. Comput Methods Programs Biomed 2016; 138: 83–91.

23.

Grading diabetic retinopathy from stereoscopic color fundus photographs -an extension of the modified Airlie House classification. ETDRS report no 10. Early Treatment Diabetic Retinopathy Study Research Group Ophthamology. 1991; 98: 786–806.

24.

International clinical diabetic retinopathy disease severity scale, American Academy for ophthalmology, October 2002, http://www.icoph.org/downloads/Diabetic-Retinopathy-Scale.pdf

25.

Early Treatment Diabetic Retinopathy Study Research Group. Grading diabetic retinopathy from stereoscopic color fundus photographs: an extension of the modified Airlie House classification: ETDRS report number 10. Ophthalmology 1991; 98: 786–806.

26.

The Wisconsin epidemiologic study of diabetic retinopathy: XXII the twenty-five-year progression of retinopathy in persons with type 1 diabetes. Ophthalmology 2008; 115(11): 1859–1868.