Advertisement

A critical review of red lesion detection algorithms using fundus images

  • Shilpa Joshi
  • P. T. Karule
Review Article
  • 35 Downloads

Abstract

There are two types of clinical signs of diabetic retinopathy: red lesions and bright lesions. Red lesions which include microaneurysms are early signs of diabetic retinopathy. Microaneurysms are clinically important initial qualities of retinopathy. Their number increases with the severity of retinopathy. Hemorrhages are also signs of diabetic retinopathy which appear after microaneurysms. This work has concentrated on the review of the development of several techniques to automate the detection and classification of suggestive features of red lesions of first retinopathy progress.

Keywords

Microaneurysms Hemorrhages Red lesions Diabetic retinopathy 

Notes

Acknowledgments

The authors would like to express their deep sense of gratitude to Dr. Sonal A. Jain, Saraswati Skin and Eye Care Centre, Mumbai, for providing guidance on red lesions in fundus images.

References

  1. 1.
    Lay BJ (1983). Analyze automatic fluorescein angiograms images and diabetic retinopathy, PhD thesis, Center of Mathematical Morphology, Paris School of Mines.Google Scholar
  2. 2.
    Oien GE, Osnes P. Diabetic retinopathy: automatic detection of early symptoms from retinal images, Proceedings Norwegian Signal Processing Symposium. 1995;pp. 7–9. https://doi.org/10.1.1.40.3374.Google Scholar
  3. 3.
    Spencer T, Phillips S, McHardy K, Forrester J. Automated detection and quantification of MAs in fluorescein angiograms. Graefes Archive for Clinical and Experimental Ophthalmology, Springer 1991. pp. 36–41.  https://doi.org/10.1007/BF00166760.
  4. 4.
    Frame A, Undrill PE, Cree MJ, Olson JA, Forrester J. A comparison of computer-based classification methods applied to the detection of MAs in ophthalmic fluorescein angiograms. Comput BioL Med. 1998;28:225–38.CrossRefPubMedGoogle Scholar
  5. 5.
    Walter T, Klein J C. Automatic detection of microaneurysms in color fundus images of the human retina by means of the bounding box closing, Lecture Notes Computer Science, Springer 2002 pp 210–220.  https://doi.org/10.1007/3-540-36104-9_23.
  6. 6.
    Zhang X, Fan G. Retinal spot lesions detection using adaptive multiscale morphological processing, Int. Sym. Visual Comp. Springer 2006 pp. 490–501.  https://doi.org/10.1007/11919629_50.
  7. 7.
    Karnowski TP, Govindasamy VP, Tobin KW, Chaum E, Abramoff MD. Retina lesions and microaneurysms segmentation using morphological reconstruction methods with ground-truth data, Conf. Proc. IEEE Engineering Med Biology Society, 2008 pp. 5433–5436.Google Scholar
  8. 8.
    Balasubramanian S, Pradhan S, Chandrasekaran V. Red lesions detection in digital fundus images, IEEE Conference, ICIP 2008 pp. 2932–2935.  https://doi.org/10.1109/ICIP.2008.4712409.
  9. 9.
    Matei D, Matei R. Detection of diabetic symptoms in retina images using analog algorithms, World Scientific and Engineering Academy and Society (WSEAS) Stevens Point, Wisconsin, USA ©2008, ISPRA'08 2010 pp. 224–227.Google Scholar
  10. 10.
    Kamel M, Belkassim S Mendonca AM, Campilho A. A neural network approach for the automatic detection of MAs in retinal angiograms, Neural Networks, 2001. Proceedings. IJCNN '01. International Joint Conference on, Volume: 4, OI 2001 pp. 2695-2699.  https://doi.org/10.1109/IJCNN.2001.938798.
  11. 11.
    Jaafar H. F., Nandi A.K. and Nuaimy W.. Automatic detection of red lesions from digital color fundus photographs, Annual Int. Conf. Of the IEEE EMBS 2011 pp. 6232–6235.Google Scholar
  12. 12.
    Goldbaum M, Moezzi S, Taylor A, Chatterjee S, Boyd J, Hunter E, Jain R. Automated diagnosis and image understanding with object extraction, object classification, and inferencing in retinal images, IEEE Int. Conf. on Image Processing, 1996 pp. 695–698.  https://doi.org/10.1109/ICIP.1996.560760.
  13. 13.
    Yang G, Gagnon L, Wang S, Boucher M. Algorithm for detecting micro-aneurysms in low resolution color retinal images, Proceedings of Vision Interface 2001 pp. 265–271. http://savoirs.usherbrooke.ca/handle/11143/4546.
  14. 14.
    Harangi B, Hajdu A. Automatic exudate detection by fusing multiple active contours and region wise classification. Comput Biol Med. 2014;54:156–71.  https://doi.org/10.1016/j.compbiomed.2014.09.001.CrossRefPubMedGoogle Scholar
  15. 15.
    Niemeijer M, Ginneken BV, Staal J, Suttorp-Schulten MS. Automatic detection of red lesions in digital color fundus photographs. IEEE Trans Med Imaging. 2005;24(5):584–92.CrossRefPubMedGoogle Scholar
  16. 16.
    Bae JP, Kim KG, Kang HC, Jeong CB. A study on hemorrhage detection using hybrid method in fundus images. J Digit Imaging Springer. 2010;23:394–404.  https://doi.org/10.1007/s10278-010-9274-9.Google Scholar
  17. 17.
    Ege BM, Hejlesen OK, Larsen OV, Moller K, Jennings B, Kerr D, et al. Screening for diabetic retinopathy using computer-based image analysis and statistical classification. Comput Methods Prog Biomed. 2000;62(3):165–75.  https://doi.org/10.1016/SO169-2607(00)00065-1.
  18. 18.
    Kahai P, Namuduri K R, Thompson H. Decision support framework for automated screening diabetic retinopathy. Int J Biomed Imaging, 2006 article ID 45806, pages 8.  https://doi.org/10.1155/IJBI/2006/45806.
  19. 19.
    Walter T. Application of mathematical morphology a diagnostic retinal automatic images fluorescein angiographic and color diabetic retinopathy images, PhD thesis. 2003.Google Scholar
  20. 20.
    Giancardo L, Meriaudeau F, Karnowski T, Tobin K, Chaum E. Microaneurysms detection with radon transform-based classification on retina images. Eng Med Biol Soc EMBC IEEE. 2011:5939–42.  https://doi.org/10.1109/IEMBS.2011.6091562.
  21. 21.
    Giancardo L, Meriaudeau F, Karnowski T, Tobin K, Chaum E. Microaneurysms detection with the radon cliff operator in retinal fundus images. Int. Proc SPIE. 2010;  https://doi.org/10.1117/12.844442, page 76230U.
  22. 22.
    Kande GB, Tirumala S, Subbaiah PV, Tagore M. Detection of red lesions in digital fundus images. IEEE Proc ISBI. 2009:558–61.  https://doi.org/10.1109/ISBI.2009.5193108.
  23. 23.
    Osareh A, Mirmehdi M, Thomas B, Markham R. Classification and localization of diabetic-related eye disease, Proc. European Conference Computer Vision, Springer 2006 pp. 325–329.  https://doi.org/10.1007/3-540-47979-1_34
  24. 24.
    Li T, Niemeijer M, Abramoff MD. Splat feature classification: detection of the presence of large retinal hemorrhages, IEEE Symp on Bio Medical Imaging, 2011 pp 681–684.Google Scholar
  25. 25.
    Niemeijer M, Ginneken B, Cree MJ, Mizutani A, Quellec G, Sánchez C, et al. Retinopathy online challenge: automatic detection of microaneurysms in digital color fundus photographs. IEEE Trans Med Imaging. 2010;29:185–95.Google Scholar
  26. 26.
    Kande GB, Tirumala SS, Subbaiah PV. Automatic detection of microaneurysms and hemorrhages in digital fundus images. J Digit Imaging Springer. 2010;23:430–7.CrossRefGoogle Scholar
  27. 27.
    Usher D, Dumskyj M, Himaga M, Williamson TH, Nussey S, Boyce J. Automated detection of diabetic retinopathy in digital retinal images: a tool for diabetic retinopathy screening. Diabet Med. 2004;01085.x:84–90.  https://doi.org/10.1046/j.1464-5491.2003.CrossRefGoogle Scholar
  28. 28.
    Garcia M, Sanchez C, Lopez I, Diez A. Automatic detection of red lesions in retinal images using a multilayer perceptron neural network. Conf Proc IEEE Eng Med Biol Soc. 2008:1085–93.Google Scholar
  29. 29.
    Garcia M, Lopez MI, Alvarez D, Hornero R. Assessment of four neural network-based classifiers to automatically detect red lesions in retinal images. Med Eng Phys. 2010:1085–93.  https://doi.org/10.1016/j.medengphy.2010.07.014.
  30. 30.
    Wenhua X., Faling Y. and Guohua C.. Detection of microaneurysms in digital fundus images based on SVM, IEEE Int. Conference on Oxide Materials for Electronic Engineering (OMEE), 2012 pp. 104–108.Google Scholar
  31. 31.
    Ram K, Joshi G, Sivaswamy J. A successive clutter rejection based-approach for early detection of diabetic retinopathy. IEEE Trans Biomed Eng. 2011;58:664–73.  https://doi.org/10.1109/TBME.2010.2096223.CrossRefPubMedGoogle Scholar
  32. 32.
    Nagayoshi H, Hiramatsu Y, Kagehiro T, Mizuno Y, Himaga M, Sato S. Detection of lesions from fundus images for diagnosis of diabetic retinopathy. IEICE. 2005:61–6.Google Scholar
  33. 33.
    Grisan E, Ruggeri A. Segmentation of candidate dark lesions in fundus images based on local thresholding and pixel density, IEEE EMBS 2007 pp. 23–26.  https://doi.org/10.1109/IEMBS.2007.4353907.
  34. 34.
    Roychoudhari S, Dara DK, Keshab KP. DREAM: diabetic retinopathy analysis using machine learning. IEEE J BiomedHealth Info. 2014:1717–29.Google Scholar
  35. 35.
    Quellec G, Lamard M, Josselin P M, Cazuguel G, Cochener B, Roux C. Detection of lesions in retina photographs based on the wavelet transform, International Conference of the IEEE Engineering in Medicine and Biology Society. 2006 pp. 2618–2621.Google Scholar
  36. 36.
    Hatanaka Y, Nakagawa T, Hayashi Y, Hara T, Fujita H. Improvement of automated detection method of hemorrhages in fundus images. IEEE EMBS. 2008:5429–32.Google Scholar
  37. 37.
    Hatanaka Y, Nakagawa T, Hayashi Y, Mizukusa Y, Fujita A, Kahase K, Fujita H. CAD scheme to detect hemorrhages and exudates in ocular fundus images, Proc. SPIE 6514, Medical Imaging, Computer Aided Diagnosis, 2007.  https://doi.org/10.1117/12.708367.
  38. 38.
    Lee SC, Lee ET, Kingsley RM, Wang Y, Russell D, Klein R, Warn A. Comparison of diagnosis of early retinal lesions of diabetic retinopathy between a computer system and human experts. Arch Ophthalmol. 2001;119(4):509–15.Google Scholar
  39. 39.
    Cree M.J., Olson J. A., McHardy K.C, Sharp P.F., Forrester J. V. A fully automated comparative microaneurysms digital detection system. 1997;622–628.  https://doi.org/10.1038/eye.1997.166.
  40. 40.
    Huang K, Yan M. A local adaptive algorithm for microaneurysms detection in digital fundus images. Proc of Computer Vision for Biomedical Image Application, Springer, 2005 pp 103–13.  https://doi.org/10.1007/11569541_1.
  41. 41.
    Sherif A. Microaneurysms detection using vessels removal and circular Hough transform, IEEE Proc 19th Natl Radio Science Conference, Egypt 2002 1-2:421–426.Google Scholar
  42. 42.
    Raman B., Bursell E. S., Wilson M., Zamora G., Benche I., Nemeth S. C. and Soliz P.. The effects of spatial resolution on an automated diabetic retinopathy screening system's performance in detecting microaneurysms for diabetic retinopathy, Proceedings of 17th IEEE Symposium on Computer-Based Medical Systems, 2004 pp.128–133.Google Scholar
  43. 43.
    Kose C, Sevik U, Ikibas C, Erdol H. Simple methods for segmentation and measurement of diabetic retinopathy lesions in retinal fundus images. Computer Method Prog Biomedical. 2012:274–93.  https://doi.org/10.1016/j.cmpb.2011.06.007.
  44. 44.
    Zhang D, Li X, Shang X, Yi Y, Wang Y. Robust hemorrhage detection in diabetic retinopathy image, 1st ACPR 2011 pp. 209–213.  https://doi.org/10.1109/ACPR.2011.6166529.
  45. 45.
    Hatanaka Y., Inoue T., Okumura S.. Automated microaneurysms detection method based on double-ring filter and feature analysis in retinal fundus images, IEEE Conf. on Computer-Based Medical Systems (CBMS) 2012 pp.1–4  https://doi.org/10.1109/CBMS.2012.6266339.
  46. 46.
    Zhang B, Wu X, You J, Li Q, Karray F. Detection of microaneurysms using multi-scale correlation coefficients. Pattern Recogn. 2010;43(6):2237–48.  https://doi.org/10.1016/j.patcog.2009.12.017.CrossRefGoogle Scholar
  47. 47.
    Mizutani A, Muramatsua C, Hatanaka Y, (2009). Automated microaneurysms detection method based on double-ring filter in retinal fundus images, Proc. SPIE, vol. 7260, pp. 72601N-1-8.  https://doi.org/10.1117/12.813468.
  48. 48.
    Mendonça A., Campilho A., Nunes J. Automatic segmentation of microaneurysms in retinal angiograms of diabetic patients. Proc. ICIAP, 10th Int. Conference Image Analysis Process, 1999 p 728.Google Scholar
  49. 49.
    Agurto C, Murray V, Barriga E, Murillo S, Pattichis M, Davis H, et al. Multiscale AM-FM methods for diabetic retinopathy lesions detection. IEEE Trans Med Imaging. 2010;29(2):502–12.  https://doi.org/10.1109/TMI.2009.2037146.
  50. 50.
    Bhalerao A, Patanaik A, Anand S, Saravanan P. Robust detection of microaneurysms for sight threatening retinopathy screening, In: 6th Indian Conference on Computer Vision, Graphics & Image Processing 2008 pp 520–527.Google Scholar
  51. 51.
    Sinthanayothin C, Boyce JF, Williamson TH, Cook HL, Mensah E, Lal S, et al. Automated detection of diabetic retinopathy on digital fundus image. Int J Diabet Med. 2002;19:105–12.Google Scholar
  52. 52.
    Streeter L. and Cree M. J.. Microaneurysms detection in color fundus images, Image and Vision Computing NZ, 2003 pp 280–285.Google Scholar
  53. 53.
    Serrano C, Acha B, Revuelto S. 2D adaptive filtering and region growing algorithm for the detection of microaneurysms. Proc SPIE Med Imaging: Process. 2007;5370:1924–31.CrossRefGoogle Scholar
  54. 54.
    Fleming A D, Philip S, Goatman K A. Automated microaneurysms detection using local contrast normalization and local vessel detection, IEEE Trans in Medical Imag. 2006 pp. 1223–1232.Google Scholar
  55. 55.
    Marino C, Ares E, Penedo ME, Ortega M, Barreira N, Gomez F. Automated three stage red lesions detection in digital color fundus images. WSEAS Trans Comput. 2008;7:207–15.Google Scholar
  56. 56.
    Lalonde M, Laliberté F, Gagnon L. RetsoftPlus: a tool for retinal image analysis. Proc 17th IEEE Symp Computer-Based Med System (CBMS’04). Bethesda, MD, USA, 2004 pp. 542–547.Google Scholar
  57. 57.
    Abramoff MD, Niemeijer M, Suttorp-Schulten MS, Viergever MA, Russel SR, Ginneken B. Evaluation of a system for automatic detection of diabetic retinopathy from color fundus photographs in a large population of patients with diabetes. Diabetes Care. 2008;31:193–8.  https://doi.org/10.2337/dc07-1312.CrossRefPubMedGoogle Scholar
  58. 58.
    Kauppi T., Kalesnykiene V., Kmrinen J. K., Lensu L, Sorr I., Raninen A., Voutilainen R., Uusitalo H., Klviinen H. and Pietil J.. Diaretdb1 diabetic retinopathy database and evaluation protocol, Proc. 11th Conf. Med. Image Understand Analysis 2007 pp. 61–65.Google Scholar
  59. 59.
    UK National Screening Committee. National screening program for diabetic retinopathy 2009. https://legacyscreening.phe.org.uk/screening-recommendations.php Public Health.
  60. 60.
    Gardner GG, Keating D, Williamson TH, Elliott AT. Automatic detection of diabetic retinopathy using artificial neural network: a screening tool. Br J Ophthalmol. 1996;80:940–4.CrossRefPubMedPubMedCentralGoogle Scholar
  61. 61.
    Spencer T, Olson JA, McHardy K, Sharp P, Forrester J. An image-processing strategy for the segmentation and quantification in fluorescein angiograms of the ocular fundus. Computer Biomed Res. 1996;29:284–302.CrossRefGoogle Scholar
  62. 62.
    Hipwell JH, Strachan F, Olson JA, McHardy KC, Forrester J. Automated detection of microaneurysms in digital red-free photographs: a diabetic screening tool. Diabet Med. 2000;17(8):588–94.CrossRefPubMedGoogle Scholar
  63. 63.
    Larsen M, Godt J, Larsen N, Lund AH, Sjolie AK, Agardh E, et al. Automated detection of fundus photographic red lesions in diabetic retinopathy. Investig Ophthalmol Vis Sci. 2003;44 pp. 761–766.  https://doi.org/10.1167/iovs.02-0418.
  64. 64.
    Grisan E., Ruggeri A.. A hierarchical Bayesian classification for non-vascular lesions detection in fundus images, in EMBEC’05, Springer, 3rd European Medical and Biological Engineering Conference 2005 pp. 234–240.Google Scholar
  65. 65.
    Walter T, Klein JC. Automatic detection of microaneurysms in color fundus images. Med Image Anal. 2007;11:555–66.  https://doi.org/10.1016/j.media.2007.05.001.CrossRefPubMedGoogle Scholar
  66. 66.
    Quellec G, Lamard M, Josselin PM, Cazuguel G, Cochener B. Optimal wavelet transforms for the detection of microaneurysms in retina photographs. IEEE Trans Med. 2008;27(9):1230–41.  https://doi.org/10.1109/TMI.2008.920619.CrossRefGoogle Scholar
  67. 67.
    Dupas B, Walter T, Erginay A, Ordonez R, Deb-Joardar N, Gain P, et al. Evaluation of automated fundus photograph analysis algorithms for detecting microaneurysms, hemorrhages and exudates, and of a computer-assisted diagnostic system for grading diabetic retinopathy. Diabetes Metab. 2010;36:213–20.  https://doi.org/10.1016/j.diabet2010.01.02.
  68. 68.
    Antal B., Hajdu A. Improving microaneurysms detection in color fundus images using an optimal combination of preprocessing methods and candidate extractor, 18th European Signal Processing Conference, IEEE, EUSIPCO 2010 1224–1228.Google Scholar
  69. 69.
    Langroudi MN, Sadjedi H, (2010). A new method for automatic detection and diagnosis of retinopathy diseases in color fundus images based on morphology, IEEE, International Conference on Bioinformatics and Biomedical Technology, pp. 134–138.  https://doi.org/10.1109/ICBBT.2010.5478995.
  70. 70.
    Giancardo L, Meriaudeau F, Karnowski T, Tobin K. Validation of microaneurysms-based diabetic retinopathy screening across retina fundus datasets. IEEE CBMS. 2013:125–31.Google Scholar
  71. 71.
    Tang L, Niemeijer M, Reinhardt J, Garvin M. Splat feature classification with application to retinal hemorrhage detection in fundus images. IEEE Trans Med Imaging. 2013;32(2):364–75.CrossRefPubMedGoogle Scholar
  72. 72.
    Azar A T, Valentina B E. Classification and detection of diabetic retinopathy, Advances in intelligent analysis of medical data & decision support system, Springer  https://doi.org/10.1007/978-3-319-00029-9_12 SCI 2013 473:135–145.
  73. 73.
    Manjiri P, Ramesh M, Rajput Y, Saswade M, Deshpande N. Automated localization of optic disk, detection of microaneurysms and extraction of blood vessels to bypass angiography, Proc. of Int. Conference on Frontiers of Intelligent Computing: Theory and Application, https://link.springer.com/book/10.1007/978-3-319-11933-5, 2014 pp. 579–587.Google Scholar
  74. 74.
    Angadi S and Ravishankar M. Detection and classification of microaneurysms using DTCWT and Log Gabor features in retinal images. Proc. of Int. Conference on Frontiers of Intelligent Computing: Theory and Application,  https://doi.org/10.1007/978-3-319-12012-6_65, Springer 2014 pp. 589–597.
  75. 75.
    Varsanyi P, Fegyvari Z, Sergyan S, Vamossy Z. Manual microaneurysms detection support with size and shape-based detection, IEEE Symposium Application of Computer Intelligence and Informatics 2014 pp. 361–365.Google Scholar
  76. 76.
    Manoj Kumar SB, Manjunath R, Sheshadri HS. Feature extraction from the fundus images for the diagnosis of diabetic retinopathy. International Conference on Emerging Research in Electronics, Computer Science and Technology (ICERECT), IEEE 2015 pp.240–245.Google Scholar
  77. 77.
    Das V, Puhan N B, Panda R. Entropy thresholding based microaneurysms detection in fundus images, Conference on Computer Vision, Pattern Recognition, Image Processing Graphics IEEE 2015 pp. 1–4.Google Scholar
  78. 78.
    Bharali P, Medhi J P and Nirmala S.R., (2015). Detection of hemorrhages in diabetic retinopathy analysis using color fundus images, IEEE 2nd International Conference on Recent Trends in Information Systems (ReTIS), IEEE, pp. 237–242.Google Scholar
  79. 79.
    Mane V, Kawadiwale RB, Jadhav DV. Detection of red lesions in diabetic retinopathy affected fundus images. Adv Comput IEEE. 2015:56–60.Google Scholar
  80. 80.
    Shan J, Li L. Deep learning method for microaneurysms detection in fundus images, IEEE First Conference on Connected Health: Application, Systems and Engineering Technologies 2016 pp.357–358.Google Scholar
  81. 81.
    Mohammad N, Zaid U, Supriyanto E. Automated detection of microaneurysms for fundus images. IEEE EMBS Conference on Biomedical Engineering and Sciences (IECBES) Conference, 2016 pp. 600–605.Google Scholar
  82. 82.
    Mumtaz R, Hussain M, Sarwar S, Khan K, Mumtaz S, Mumtaz M. Automatic non-proliferative diabetic retinopathy screening system based on color fundus image. Int J Diabetes Dev Ctries. 2017;38:80–7.  https://doi.org/10.1007/s13410-017-0561-6.CrossRefGoogle Scholar

Copyright information

© Research Society for Study of Diabetes in India 2018

Authors and Affiliations

  1. 1.Department of Electronics Engineering, YCCENagpur UniversityNagpurIndia

Personalised recommendations