Novel expert system for glaucoma identification using non-parametric spatial envelope energy spectrum with fundus images

• Autorzy: Raghavendra U. , Bhandary S. V. , Gudigar A. , Acharya U. R.

Identyfikatory

DOI

10.1016/j.bbe.2017.11.002

• Języki publikacji: EN

Abstrakty

EN

Glaucoma is the prime cause of blindness and early detection of it may prevent patients from vision loss. An expert system plays a vital role in glaucoma screening, which assist the ophthalmologists to make accurate decision. This paper proposes a novel technique for glaucoma detection using optic disk localization and non-parametric GIST descriptor. The method proposes a novel area based optic disk segmentation followed by the Radon transformation (RT). The change in the illumination levels of Radon transformed image are compensated using modified census transformation (MCT). The MCT images are then subjected to GIST descriptor to extract the spatial envelope energy spectrum. The obtained dimension of the GIST descriptor is reduced using locality sensitive discriminant analysis (LSDA) followed by various feature selection and ranking schemes. The ranked features are used to build an efficient classifier to detect glaucoma. Our system yielded a maximum accuracy (97.00%), sensitivity (97.80%) and specificity (95.80%) using support vector machine (SVM) classifier with nineteen features. Developed expert system also achieved maximum accuracy (93.62%), sensitivity (87.50%) and specificity (98.43%) for public dataset using twenty six features. The proposed method is efficient and computationally less expensive as it require only nineteen features to model a classifier for the huge dataset. Therefore the proposed method can be effectively utilized in hospitals for glaucoma screening.

Słowa kluczowe

EN

computer aided diagnosis; GIST descriptor; glaucoma; support vector machine; Radon transform

PL

komputerowe wspomaganie diagnostyki; jaskra; maszyna wektorów wspierających; transformata Radona

• Wydawca: Nałęcz Institute of Biocybernetics and Biomedical Engineering of the Polish Academy of Sciences ; Elsevier
• Czasopismo: Biocybernetics and Biomedical Engineering
• Rocznik: 2018
• Tom: Vol. 38, no. 1
• Strony: 170--180
• Opis fizyczny: Bibliogr. 91 poz., rys., tab., wykr.

Twórcy

autor

Raghavendra U.

• Department of Instrumentation and Control Engineering, Manipal Institute of Technology, Manipal University, Manipal 576104, India

autor

Bhandary S. V.

• Department of Ophthalmology, Kasturba Medical College, Manipal University, Manipal India

autor

Gudigar A.

• Department of Instrumentation and Control Engineering, Manipal Institute of Technology, Manipal University, Manipal India

autor

Acharya U. R.

• Department of Electronics and Computer Engineering, Ngee Ann Polytechnic, Singapore; Department of Biomedical Engineering, School of Science and Technology, Singapore University of Social Sciences, Singapore; Department of Biomedical Engineering, Faculty of Engineering, University of Malaya, Kuala Lumpur Malaysia

Bibliografia

• [1] Lim R, Goldberg I. The glaucoma book: a practical, evidence-based approach to patient care; 2010;3, Chapter 1.
• [2] Lim TC, Chattopadhyay S, Acharya UR. A survey and comparative study on the instruments for glaucoma detection. Med Eng Phys 2012;34(2):129–39.
• [3] Bourne RRA. The optic nerve head in glaucoma. Commun Eye Health 2006;19(59):44–5.
• [4] Sommer A, Tielsch JM, Katz J, Quigley HA, Gottsch JD, Javitt J, Singh K. Relationship between intraocular pressure and primary open angle glaucoma among white and black Americans. The Baltimore Eye Survey. Arch Ophthalmol 1991;109(8):1090–5.
• [5] Quigley HA, Broman AT. The number of people with glaucoma worldwide in 2010 and 2020. Br J Ophthalmol 2006;90(3):262–7.
• [6] Goldmann H, Schmidt T. Applanation tonometry. Ophthalmologica 1957;134:221–42.
• [7] Acharya UR, Ng EYK, Suri JS. Image modeling of the human eye, Artech House bioinformatics & biomedical imaging series. Artech House; 2008.
• [8] Burgoyne CF. Pearls of glaucoma management. Berlin, Heidelberg: Springer; 2010. p. 1.
• [9] Eye Diseases Prevalence Research Group. Prevalence of open-angle glaucoma among adults in the United States. Arch Ophthalmol 2004;122:532–8.
• [10] Nordmann JP, Mesbah M, Berdeaux G. Scoring of visual field measured through Humphrey perimetry: principal component varimax rotation followed by validated cluster analysis. Invest Ophthalmol Vis Sci 2005;46:3169–76.
• [11] Sharma P, Sample PA, Zangwill LM, Schuman JS. Diagnostic tools for glaucoma detection and management. Surv Ophthalmol 2008;53(1):S17–32.
• [12] Yannuzzi LA, Ober MD, Slakter JS, Spaide RF, Fisher YL, Flower RW, Rosen R. Ophthalmic fundus imaging: today and beyond. Am J Ophthalmol 2004;137(3):511–24.
• [13] Acharya UR, Yun WL, Ng EYK, Yu W, Suri JS. Imaging systems of human eye: a review. J Med Syst 2008;32(4): 301–315.
• [14] Noronha K, Acharya UR, Nayak KP, Kamath S, Bhandary SV. Decision support system for diabetic retinopathy using discrete wavelet transform. Proc Inst Mech Eng Part H J Eng Med 2013;227(3):251–61.
• [15] Acharya UR, Chua CK, Ng EYK, Yu W, Chee C. Application of higher order spectra for the identification of diabetes retinopathy stages. J Med Syst 2008;32(6):481–8.
• [16] Acharya UR, Lim CM, Ng EYK, Chee C, Tamura T. Computer-based detection of diabetes retinopathy stages using digital fundus images. Proc Inst Mech Eng Part H J Eng Med 2009;223(5):545–53.
• [17] Yun WL, Acharya UR, Venkatesh YV, Chee C, Lim CM, Ng EYK. Identification of different stages of diabetic retinopathy using retinal optical images. Int Sci 2008; 178(1):106–21.
• [18] Chrástek R, Wolf M, Donath K, Niemann H, Paulus D, Hothorn T, Lausen B, Lämmer R, Mardin C, Michelson G. Automated segmentation of the optic nerve head for diagnosis of glaucoma. Med Image Anal 2005;9(4): 297–314.
• [19] Kanski JJ, McAllister JA, Salmon JF. Glaucoma: a colour manual of diagnosis and treatment. 2nd ed. Oxford; Boston: Butterworth-Heinemann; 1996.
• [20] Glaucoma Guide; 2010. Available: http://www.medrounds.org/glaucomaguide/2006/02/ section-1-b-meaning-of-cupping.html.
• [21] Vingrys AJ. The many faces of glaucomatous optic neuropathy. Clin Exp Optomet 2000;83:145–60.
• [22] Betz P, Camps F, Collignon-Brach J, Lavergne G, Weekers R. Biometric study of the disc cup in open-angle glaucoma. Graefes Arch Clin Exp Ophthalmol 1982;218(2):70–4.
• [23] Kourkoutas D, Karanasiou IS, Tsekouras GJ, Moshos M, Iliakis E, Georgopoulos G. Glaucoma risk assessment using a non-linear multivariable regression method. Comput Methods Programs Biomed 2012;108(3):31149–5.
• [24] Xu J, Chutatape O, Sung E, Zheng C, Kuan PCT. Optic disk feature extraction via modified deformable model technique for glaucoma analysis. Pattern Recognit 2007; 40(7):2063–76.
• [25] Xu J, Chutatape O, Chew P. Automated optic disk boundary detection by modified active contour model. IEEE Trans Biomed Eng 2007;54(3):473–82.
• [26] Hoover A, Goldbaum M. Locating the optic nerve in a retinal image using the fuzzy convergence of the blood vessels. IEEE Trans Biomed Eng 2003;22(8):951–8.
• [27] Lalonde M, Beaulieu M, Gagnon L. Fast and robust optic disc detection using pyramidal decomposition and Hausdorff- based template matching. IEEE Trans Med Imag 2011; 20(11):1193–200.
• [28] Fleming AD, Goatman KA, Philip S, Olson JA, Sharp PF. Automatic detection of retinal anatomy to assist diabetic retinopathy screening. Phys Med Biol 2007;52(2):331–45.
• [29] Foracchia M, Grisan E, Ruggeri A. Detection of optic disc in retinal images by means of a geometrical model of vessel structure. IEEE Trans Biomed Eng 2004;23(10):1189–95.
• [30] Joshi G, Sivaswamy J, Krishnadas SR. Depth discontinuity- based cup segmentation from multiview color retinal images. IEEE Trans Biomed Eng 2012;59(6):1523–31.
• [31] Nayak J, Acharya UR, Bhat PS, Shetty A, Lim TC. Automated diagnosis of glaucoma using digital fundus images. J Med Syst 2009;33(5):337–46.
• [32] Xu Y, Xu D, Lin S, Liu J, Cheng J, Cheung CY, Aung T, Wong TY. Sliding window and regression based cup detection in digital fundus images for glaucoma diagnosis. Medical Image Computing and Computer-Assisted Intervention – MICCAI 2011, 14. Berlin, Heidelberg: Springer; 2011. p. 1–8.
• [33] Yuji H, Noudo A, Muramatsu C, Sawada A, Hara T, Yamamoto T, Fujita H. Vertical cup-to-disc ratio measurement for diagnosis of glaucoma on fundus images. SPIE Medical Imaging. International Society for Optics and Photonics; 2010. p. 76243C.
• [34] Balasubramanian M, Zabic S, Bowd C, Thompson HW, Wolenski P, Iyengar SS, Karki BB, Zangwill LM. Clinical evaluation of the proper orthogonal decomposition framework for detecting glaucomatous changes in human subjects. Invest Ophthalmol Vis Sci 2010;51:264–71.
• [35] Boquete L, Miguel-Jiménez JM, Ortega S, Rodríguez-Ascariz JM, Pérez-Rico C, Blanco R. Multifocal electroretinogram diagnosis of glaucoma applying neural networks and structural pattern analysis. Expert Syst Appl 2012;39(1): 234–238.
• [36] Huang ML, Chen HY, Huang JJ. Glaucoma detection using adaptive neuro-fuzzy inference system. Expert Syst Appl 2007;32(2):458–68.
• [37] Acharya UR, Dua S, Du X, Sree SV, Chua CK. Automated diagnosis of glaucoma using texture and higher order spectra features. IEEE Trans Inf Technol Biomed 2011; 15(3):449–55.
• [38] Dua S, Acharya UR, Chowriappa P, Sree SV. Wavelet based energy features for glaucomatous image classification. IEEE Trans Inf Technol Biomed 2012;16(1):80–7.
• [39] Mookiah MRK, Acharya UR, Lim CM, Petznick A, Suri JS. Data mining technique for automated diagnosis of glaucoma using higher order spectra and wavelet energy features. Knowl Based Syst 2012;33:73–82.
• [40] Kim PY, Iftekharuddin KM, Gunvant P, Tóth M, Garas A, Holló G, Essock EA. Feature-based glaucomatous progression prediction using scanning laser polarimetry (SLP) data. Proc SPIE 2011;7963:79633T.
• [41] Noronha KP, Acharya UR, Nayak KP, Martis RJ, Bhandary SV. Automated classification of glaucoma stages using higher order cumulant features. Biomed Sig Process Control 2014;10:174–83.
• [42] Yousefi S, Goldbaum MH, Balasubramanian M, Jung TP, Weinreb RN, Medeiros FA, Zangwill LM, Liebmann JM, Girkin CA, Bowd C. Glaucoma progression detection using structural retinal nerve fiber layer measurements and functional visual field points. IEEE Trans Biomed Eng 2014;61(4):1143–54.
• [43] Ceccon S, Garway-Heath DF, Crabb DP, Tucker A. Exploring early glaucoma and the visual field test: classification and clustering using Bayesian networks. IEEE J Biomed Health Inf 2014;18(3):1008–14.
• [44] Maheshwari S, Pachori RB, Acharya UR. Automated diagnosis of glaucoma using empirical wavelet transform and correntropy features extracted from fundus images. IEEE J Biomed Health Inf 2017;21(3):803–13.
• [45] Maheshwari S, Pachori RB, Kanhangad V, Bhandary SV, Acharya UR. Iterative variational mode decomposition based automated detection of glaucoma using fundus images. Comput Biol Med 2017;88:142–9.
• [46] Acharya UR, Bhat S, Koh JEW, Bhandary SV, Adeli H. A novel algorithm to detect glaucoma risk using texton and local configuration pattern features extracted from fundus images. Comput Biol Med 2017;88:72–83.
• [47] Glaucoma public database http://medimrg.webs.ull.es/ [date of access: 15.07.17].
• [48] Giancardo L, Meriaudeau F, Karnowski TP, Li Y, Garg S, Tobin Jr KW, Chaum E. Exudate-based diabetic macular edema detection in fundus images using publicly available datasets. Med Image Anal 2012;16:216–26.
• [49] Magli E, Olmo G, Presti LL. Pattern recognition by means of the Radon transform and continuous wavelet transform. J Signal Process 1999;73:277–89.
• [50] Jafari-Khouzani K, Soltanian-Zadeh H. Rotation-invariant multiresolution texture analysis using radon and wavelet transforms. IEEE Trans Image Process 2005;14:783–95.
• [51] Zabih R, Woodfill J. Non-parametric local transforms for computing visual correspondence. European Conference on Computer Vision, 2; 1994. pp. 151–8.
• [52] Kublbeck C, Ernst A. Face detection and tracking in video sequences using the modified census transformation. Image Vis Comput 2006;24(6):564–72.
• [53] Oliva A, Torralba A. Modeling the shape of the scene: a holistic representation of the spatial envelope. Int J Comput Vis 2001;42(3):145–75.
• [54] GIST descriptors. Information available at: http://www.quora.com/Computer-Vision/ What-is-a-GIST-descriptor# [date accessed on 04.07.17].
• [55] Acharya UR, Fujita H, Bhat S, Raghavendra U, Gudigar A, Molinari F, Vijayananthan A, Ng KH. Decision support system for fatty liver disease using GIST descriptors extracted from ultrasound images. Inf Fus 2016;29:32–9.
• [56] Raghavendra U, Acharya UR, Gudigar A, Tan JH, Fujita H, Hagiwara Y, Molinari F, Kongmebhol P, Ng KH. Fusion of spatial gray level dependency and fractal texture features for the characterization of thyroid lesions. Ultrasonics 2017;77:110–20.
• [57] Acharya UR, Raghavendra U, Fujita H, Hagiwara Y, Koh JEW, Tan JH, Sudarshan VK, Vijayananthan A, Yeong CH, Gudigar A, Ng KH. Automated characterization of fatty liver disease and cirrhosis using curvelet transform and entropy features extracted from ultrasound images. Comput Biol Med 2016;(79):250–8.
• [58] Raghavendra U, Acharya UR, Fujita H, Gudigar A, Chokkadi S. Application of Gabor wavelet and locality sensitive discriminant analysis for automated identification of breast cancer using digitized mammogram images. Appl Soft Comput 2016;46:151–61.
• [59] Raghavendra U, Acharya UR, Ng EYK, Tan JH, Gudigar A. An integrated index for breast cancer identification using histogram of oriented gradient and kernel locality preserving projection features extracted from thermograms. Quant Infrared Thermogr J 2016;13(2): 195–209.
• [60] Gudigar A, Chokkadi S, Raghavendra U, Acharya UR. Multiple thresholding and subspace based approach for detection and recognition of traffic sign. Multimed Tools Appl 2016;76(5):6973–91.
• [61] Gudigar A, Chokkadi S, Raghavendra U, Acharya UR. An efficient traffic sign recognition based on graph embedding features. Neural Comput Appl 2017. http://dx.doi.org/10.1007/s00521-017-3063-z.
• [62] Gudigar A, Chokkadi S, Raghavendra U, Acharya UR. Local texture patterns for traffic sign recognition using higher order spectra. Pattern Recognit Lett 2017;94:202–10.
• [63] Rao A, Noushath S. Survey: subspace methods for face recognition. Comput Sci Rev 2010;4(1):1–17.
• [64] Cai D, He X, Zhou K, Han J, Bao H. Locality sensitive discriminant analysis. Proceedings of the 20th International Joint Conference Artificial Intelligence; 2007. p. 708–13.
• [65] Saeys Y, Inza I, Larranaga P. A review of feature selection techniques in bioinformatics. Bioinf Rev 2007;23(19): 2507–2517.
• [66] Obuchowski NA. Receiver operating characteristic curves and their use in radiology. Radiology 2003;229:3–8.
• [67] T-test, Student's t-tests. Information available at: http://www.physics.csbsju.edu/stats/t-test.html [date accessed on 04.07.17].
• [68] Dash M, Liu H. Handling large unsupervised data via dimensionality reduction. ACM SIGMOD Workshop on Research Issues in Data Mining and Knowledge Discovery; 1999.
• [69] Abe N, Kudo M. Entropy criterion for classifier-independent feature selection. Knowledge-based intelligent information and engineering systems. Lect Notes Comput Sci 2005;3684:689–95.
• [70] Lopes N. Comparing machine learning algorithms with the Wilcoxon Signed Rank Test. Information available at: http://www.uc.pt/fctuc/dei/statisticalHypothesis/noel [date accessed on 04.07.17].
• [71] Hwang T, Sun CH, Yun T, Yi GS. FiGS: a filter-based gene selection workbench for microarray data. BMC Bioinf 2010;11. Information available at: http://www.biomedcentral.com/1471-2105/11/50 (date accessed on 04.07.17).
• [72] Natarajan S, Lipsitz SR, Fitzmaurice GM, Sinha D, Ibrahim JG, Haas J, Gellad W. An extension of the Wilcoxon Rank- Sum test for complex sample survey data. Journal of the Royal Statistical Society Series C Applied Statistics 2012; 61(4):653–64.
• [73] Yuan Y, van Allen EM, Omberg L, Wagle N, Amin-Mansour A, et al. Assessing the clinical utility of cancer genomic and proteomic data across tumor types. Nat Biotechnol 2014;32:644–52.
• [74] Kailath T. The divergence and Bhattacharyya distance measures in signal selection. IEEE Trans Commun Technol 1967;15(1):52–60.
• [75] Vapnik V. The nature of statistical learning theory. New York: Springer-Verlag; 1995.
• [76] Burgess CJC. A tutorial on support vector machines for pattern recognition. Data Min Knowl Discov 1998;2(2):1–47.
• [77] Osareh A, Mirmehdi M, Thomas B, Markham R. Comparison of colour spaces for optic disc localization in retinal images. Proc. 16th Int. Conf. Pattern Recog., 1. 2002. pp. 743–6.
• [78] Lowell J, Hunter A, Steel D, Basu A, Ryder R, Fletcher E, Kennedy L. Optic nerve head segmentation. IEEE Trans Med Imaging 2004;23(2):256–64.
• [79] Townsend KA, Wollstein G, Danks D, Sung KR, Ishikawa H, Kagemann L, Gabriele ML, Schuman JS. Heidelberg Retina Tomograph 3 machine learning classifiers for glaucoma detection. Br J Ophthalmol 2008;92:814–8.
• [80] Fink F, Worle K, Gruber P, Tome AM, Gorriz-Saez JM, Puntonet CG, Lang EW. ICA analysis of retina images for glaucoma classification. Engineering in Medicine and Biology Society, EMBS 2008, 30th Annual International Conference of the IEEE. 2008. pp. 4664–7.
• [81] Nagarajan R, Balachandran C, Gunaratnam D, Klistorner A, Graham S. Neural network model for early detection of glaucoma using multi-focal visual evoked potential (M-Vep). Invest Ophthalmol Vis Sci 2002;42.
• [82] Bock R, Meier J, Nyúl LG, Hornegger J, Michelson G. Glaucoma risk index: automated glaucoma detection from color fundus images. Med Image Anal 2010;14:471–81.
• [83] Huang ML, Chen HY, Huang WC, Tsai YY. Linear discriminant analysis and artificial neural network for glaucoma diagnosis using scanning laser polarimetry – variable cornea compensation measurements in Taiwan Chinese population. Graefe's Arch Clin Exp Ophthalmol 2010;248(3):435–41.
• [84] Kolar R, Jan J. Detection of glaucomatous eye via color fundus images using fractal dimensions. Radio Eng 2008; 17(3):109–14.
• [85] Acharya UR, Ng EYK, Eugene LWJ, Noronha KP, Min LC, Nayak KP, Bhandary SV. Decision support system for the glaucoma using Gabor transformation. Biomed Signal Process Control 2015;15:18–26.
• [86] Larose DT. Discovering knowledge in data: an introduction to data mining. New Jersey, USA: Wiley Interscience; 2004.
• [87] Rodríguez AEG, Trinidad JFM, Borroto MG, Ochoa JAC. Mining patterns for clustering on numerical datasets using unsupervised decision trees. Knowl Syst 2015;82:70–9.
• [88] Huang ZH, Li WJ, Wang J, Zhang T. Face recognition based on pixel-level and feature-level fusion of the top-level's wavelet sub-bands. Inf Fus 2015;22:95–104.
• [89] Khan A, Farooq H. Principal component analysis-linear discriminant analysis feature extractor for pattern recognition. IJCSI Int J Comput Sci Issues 2011;8(6):267–70.
• [90] Scikit Learn, LDA and QDA. Information available at: http://scikit-learn.org/stable/modules/lda qda.html [last accessed in November 2017].
• [91] Sugeno M. Industrial applications of fuzzy control. Elsevier Science Pub. Co.; 1985.

Uwagi

PL

Opracowanie rekordu w ramach umowy 509/P-DUN/2018 ze środków MNiSW przeznaczonych na działalność upowszechniającą naukę (2018).