Abstract
Ocular imaging instruments, such as Confocal Scanning Laser Ophthalmoscopy (CSLO), captures high-quality images of the optic disc (also known as optic nerve head) that help clinicians to diagnose glaucoma. We present an integrated data analytics framework to aid clinicians in interpreting CSLO optic nerve images to diagnose and monitor the progression of glaucoma. To distinguish between healthy and glaucomatous optic discs, our framework derives shape information from CSLO images using image processing (Zernike moment method), selects salient features (hybrid feature selection), and then trains image classifiers (Multilayer Perceptron, Support Vector Machine, Bayesian Network). To monitor glaucoma progression over time, our framework uses a mathematical model of the optic disc to extract morphological features from CSLO images and applies clustering (Self-Organizing Maps) to visualize subtypes of glaucomatous optic disc damage. We contend that our data analytics framework offers an automated and objective analysis of optic nerve images that can potentially support both diagnosis and monitoring of glaucoma. We validated our framework with CSLO optic nerve images and our data analytics approach detected glaucomatous optic discs with a sensitivity of 0.86, a specificity of 0.80, an accuracy of 0.838, and an AUROC of 0.913 with a Bayesian network classifier using the optimal subset of Zernike features (six moments). Furthermore, our framework identified, using morphological features, five clusters of CSLO images, where each cluster stands for a subtype of optic nerve damage (two healthy subtypes and three glaucoma subtypes). The characteristics of each cluster—the subtype of the image—were determined by experts who examined the morphology of the images within each cluster and provided subtype characteristics to each cluster.
Similar content being viewed by others
References
Stamper RL, Lieberman MF, Drake MV (2009) Primary open angle glaucoma. In: Stamper RL, Lieberman MF, Drake MV (eds) Becker-Shaffer’s diagnosis and therapy of the glaucomas, 8th edn. Mosby/Elsevier, Edinburg, pp 239–265. https://doi.org/10.1016/B978-0-323-02394-8.00017-6
Dielemans I, de Jong PTVM, Stolk R, Vingerling JR, Grobbee DE, Hofman A (1996) Primary open-angle glaucoma, intraocular pressure, and diabetes mellitus in the general elderly population. Ophthalmology 103:1271–1275. https://doi.org/10.1016/S0161-6420(96)30511-3
Brandt JD (2004) Corneal thickness in glaucoma screening, diagnosis, and management. Curr Opin Ophthalmol 15:85–89
Prum BE, Rosenberg LF, Gedde SJ, Mansberger SL, Stein JD, Moroi SE, Herndon LW, Lim MC, Williams RD (2016) Primary Open-Angle Glaucoma Preferred Practice Pattern® guidelines. Ophthalmology 123:P41–P111. https://doi.org/10.1016/j.ophtha.2015.10.053
Jampel HD, Friedman D, Quigley H, Vitale S, Miller R, Knezevich F, Ding Y (2009) Agreement among glaucoma specialists in assessing progressive disc changes from photographs in open-angle glaucoma patients. Am J Ophthalmol 147:39–44.e1. https://doi.org/10.1016/j.ajo.2008.07.023
Azuara-Blanco A, Katz LJ, Spaeth GL, Vernon SA, Spencer F, Lanzl IM (2003) Clinical agreement among glaucoma experts in the detection of glaucomatous changes of the optic disk using simultaneous stereoscopic photographs. Am J Ophthalmol 135:949–950. https://doi.org/10.1016/S0002-9394(03)00480-X
Coops A, Henson DB, Kwartz AJ, Artes PH (2006) Automated analysis of Heidelberg retina tomograph optic disc images by glaucoma probability score. Investig. Opthalmology Vis. Sci. 47:5348. https://doi.org/10.1167/iovs.06-0579
Kotowski J, Wollstein G, Ishikawa H, Schuman JS (2014) Imaging of the optic nerve and retinal nerve fiber layer: an essential part of glaucoma diagnosis and monitoring. Surv Ophthalmol 59:458–467. https://doi.org/10.1016/j.survophthal.2013.04.007
Mistlberger A, Liebmann JM, Greenfield DS, Pons ME, Hoh S-T, Ishikawa H, Ritch R (1999) Heidelberg retina tomography and optical coherence tomography in normal, ocular-hypertensive. and glaucomatous eyes Ophthalmology 106:2027–2032. https://doi.org/10.1016/S0161-6420(99)90419-0
Zinser G, Wijnaendts-van-Resandt RV, Dreher AW, Weinreb RN, Harbarth U, Schroder H, Burk RO (1989) Confocal laser tomographic scanning of the eye. In: Wampler JE (ed) Proc. SPIE 1161, New Methods in Microscopy and Low Light Imaging, San Diego, August 7. International Society for Optics and Photonics, Bellingham, pp 337–344
Wollstein G, Garway-Heath DF, Hitchings RA (1998) Identification of early glaucoma cases with the scanning laser ophthalmoscope. Ophthalmology 105:1557–1563. https://doi.org/10.1016/S0161-6420(98)98047-2
Swindale NV, Stjepanovic G, Chin A, Mikelberg FS (2000) Automated analysis of normal and glaucomatous optic nerve head topography images. Invest Ophthalmol Vis Sci 41:1730–1742
Miglior S, Guareschi M, Albe’ E, Gomarasca S, Vavassori M, Orzalesi N (2003) Detection of glaucomatous visual field changes using the Moorfields regression analysis of the Heidelberg retina tomograph. Am J Ophthalmol 136:26–33. https://doi.org/10.1016/S0002-9394(03)00084-9
Wollstein G, Garway-Heath DF, Fontana L, Hitchings RA (2000) Identifying early glaucomatous changes: comparison between expert clinical assessment of optic disc photographs and confocal scanning ophthalmoscopy. Ophthalmology 107:2272–2277. https://doi.org/10.1016/S0161-6420(00)00363-8
Strouthidis NG, Garway-Heath DF (2008) New developments in Heidelberg retina tomograph for glaucoma. Curr Opin Ophthalmol 19:141–148. https://doi.org/10.1097/ICU.0b013e3282f4450b
Tipping ME (2001) Sparse Bayesian learning and the relevance vector machine. J Mach Learn Res 1:211–244
Strouthidis NG, Demirel S, Asaoka R, Cossio-Zuniga C, Garway-Heath DF (2010) The Heidelberg retina tomograph glaucoma probability score: reproducibility and measurement of progression. Ophthalmology 117:724–729. https://doi.org/10.1016/j.ophtha.2009.09.036
Iester M, Oddone F, Prato M, Centofanti M, Fogagnolo P, Rossetti L, Vaccarezza V, Manni G, Ferreras A (2013) Linear discriminant functions to improve the glaucoma probability score analysis to detect glaucomatous optic nerve heads. J Glaucoma 22:73–79. https://doi.org/10.1097/IJG.0b013e31823298b3
Banister K, Boachie C, Bourne R, Cook J, Burr JM, Ramsay C, Garway-Heath D, Gray J, McMeekin P, Hernández R, Azuara-Blanco A (2016) Can automated imaging for optic disc and retinal nerve fiber layer analysis aid glaucoma detection? Ophthalmology 123:930–938. https://doi.org/10.1016/j.ophtha.2016.01.041
Zhu H, Poostchi A, Vernon SA, Crabb DP (2014) Detecting abnormality in optic nerve head images using a feature extraction analysis. Biomed Opt Express 5:2215–2230. https://doi.org/10.1364/BOE.5.002215
Bowd C, Chan K, Zangwill LM, Goldbaum MH, Lee T-W, Sejnowski TJ, Weinreb RN (2002) Comparing neural networks and linear discriminant functions for glaucoma detection using confocal scanning laser ophthalmoscopy of the optic disc. Invest Ophthalmol Vis Sci 43:3444–3454
Park J-M, Reed J, Zhou Q (2002) Active feature selection in optic nerve data using support vector machine. In: Fogel DB (ed) Proc. of the 2002 International Joint Conference on Neural Networks (IJCNN’02), May 12-17, Honolulu, Hawaii. IEEE, Piscataway, pp 1178–1182
Belghith A, Balasubramanian M, Bowd C, Weinreb RN, Zangwill LM (2014) A unified framework for glaucoma progression detection using Heidelberg retina tomograph images. Comput Med Imaging Graph 38:411–420. https://doi.org/10.1016/j.compmedimag.2014.03.002
Mardin CY, Hothorn T, Peters A, Jünemann AG, Nguyen NX, Lausen B (2003) New glaucoma classification method based on standard Heidelberg retina tomograph parameters by bagging classification trees. J Glaucoma 12:340–346
Bowd C, Lee I, Goldbaum MH, Balasubramanian M, Medeiros FA, Zangwill LM, Girkin CA, Liebmann JM, Weinreb RN (2012) Predicting glaucomatous progression in glaucoma suspect eyes using relevance vector machine classifiers for combined structural and functional measurements. Investig Opthalmol Vis Sci 53:2382–2389. https://doi.org/10.1167/iovs.11-7951
Racette L, Chiou CY, Hao J, Bowd C, Goldbaum MH, Zangwill LM, Lee T-W, Weinreb RN, Sample PA (2010) Combining functional and structural tests improves the diagnostic accuracy of relevance vector machine classifiers. J Glaucoma 19:167–175. https://doi.org/10.1097/IJG.0b013e3181a98b85
Horn FK, Lämmer R, Mardin CY, Jünemann AG, Michelson G, Lausen B, Adler W (2012) Combined evaluation of frequency doubling technology perimetry and scanning laser ophthalmoscopy for glaucoma detection using automated classification. J Glaucoma 21:27–34. https://doi.org/10.1097/IJG.0b013e3182027766
Twa MD, Parthasarathy S, Johnson CA, Bullimore MA (2012) Morphometric analysis and classification of glaucomatous optic neuropathy using radial polynomials. J Glaucoma 21:302–312. https://doi.org/10.1097/IJG.0b013e31820d7e6a
Broadway DC, Nicolela MT, Drance SM (2003) Optic disc morphology on presentation of chronic glaucoma. Eye 17:798. https://doi.org/10.1038/sj.eye.6700478 author reply 799
Abidi SSR, Artes PH, Yan S, Yu J (2007) Automated interpretation of optic nerve images: a data mining framework for glaucoma diagnostic support. In: Kuhn KA, Warren JR, Leong T-Y (eds) MEDINFO 2007: building sustainable health systems. IOS Press, Amsterdam, pp 1309–1313
Liao SX, Pawlak M (1998) On the accuracy of Zernike moments for image analysis. IEEE Trans Pattern Anal Mach Intell 20:1358–1364. https://doi.org/10.1109/34.735809
Ming-Kuei H (1962) Visual pattern recognition by moment invariants. IEEE Trans Inf Theory 8:179–187. https://doi.org/10.1109/TIT.1962.1057692
Teague MR (1980) Image analysis via the general theory of moments. J Opt Soc Am 70:920–930. https://doi.org/10.1364/JOSA.70.000920
Hosny KM (2010) A systematic method for efficient computation of full and subsets Zernike moments. Inf. Sci. (Ny). 180:2299–2313. https://doi.org/10.1016/j.ins.2010.02.006
Papakostas GA, Boutalis YS, Karras DA, Mertzios BG (2007) A new class of Zernike moments for computer vision applications. Inf Sci (NY) 177:2802–2819. https://doi.org/10.1016/j.ins.2007.01.010
Teh C-H, Chin RT (1988) On image analysis by the methods of moments. IEEE Trans Pattern Anal Mach Intell 10:496–513. https://doi.org/10.1109/34.3913
Khotanzad A, Hong YH (1990) Invariant image recognition by Zernike moments. IEEE Trans Pattern Anal Mach Intell 12:489–497. https://doi.org/10.1109/34.55109
Li S, Lee M-C, Pun C-M (2009) Complex Zernike moments features for shape-based image retrieval. IEEE Trans Syst Man, Cybern - Part A Syst Humans 39:227–237. https://doi.org/10.1109/TSMCA.2008.2007988
Singh C, Mittal N, Walia E (2011) Face recognition using Zernike and complex Zernike moment features. Pattern Recognit Image Anal 21:71–81. https://doi.org/10.1134/S1054661811010044
Chandrashekar G, Sahin F (2014) A survey on feature selection methods. Comput Electr Eng 40:16–28. https://doi.org/10.1016/j.compeleceng.2013.11.024
Guyon I, Elisseeff A (2003) An introduction to variable and feature selection. J Mach Learn Res 3:1157–1182
Saeys Y, Inza I, Larranaga P (2007) A review of feature selection techniques in bioinformatics. Bioinformatics 23:2507–2517. https://doi.org/10.1093/bioinformatics/btm344
Whitney AW (1971) A direct method of nonparametric measurement selection. IEEE Trans Comput C-20:1100–1103. https://doi.org/10.1109/T-C.1971.223410
Marill T, Green D (1963) On the effectiveness of receptors in recognition systems. IEEE Trans Inf Theory 9:11–17. https://doi.org/10.1109/TIT.1963.1057810
Tsai C-F, Eberle W, Chu C-Y (2013) Genetic algorithms in feature and instance selection. Knowledge-Based Syst 39:240–247. https://doi.org/10.1016/j.knosys.2012.11.005
Lin S-W, Ying K-C, Chen S-C, Lee Z-J (2008) Particle swarm optimization for parameter determination and feature selection of support vector machines. Expert Syst Appl 35:1817–1824. https://doi.org/10.1016/j.eswa.2007.08.088
Hruschka ER, Hruschka ER, Ebecken NFF (2004) Feature selection by Bayesian Networks. In: Tawfik AY, Goodwin SD (eds) Advances in Artificial Intelligence: 17th Conference of the Canadian Society for Computational Studies of Intelligence, Canadian AI 2004, London, Ontario, Canada, May 17–19, 2004. Proceedings. Springer, Berlin, pp 370–379
Cooper GF, Herskovits E (1992) A Bayesian method for the induction of probabilistic networks from data. Mach Learn 9:309–347. https://doi.org/10.1007/BF00994110
Koller D, Sahami M (1996) Toward optimal feature selection. In: Saitta L (ed) Proceedings of the Thirteenth International Conference on Machine Learning (ICML), Bari, Italy, July 3–6, 1996. Morgan Kaufmann, San Mateo, pp 284–292
Pearl J (1988) Probabilistic reasoning in intelligent systems: networks of plausible inference. Morgan Kaufmann Publishers, Burlington
Kohonen T (1990) The self-organizing map. Proc IEEE 78:1464–1480. https://doi.org/10.1109/5.58325
Lötsch J, Ultsch A (2014) Exploiting the structures of the U-matrix. In: Villmann T, Schleif F-M, Kaden M, Lange M (eds) Advances in Self-Organizing Maps and Learning Vector Quantization: Proceedings of the 10th International Workshop, WSOM 2014, Mittweida, Germany, July, 2–4, 2014. Springer, Cham, pp 249–257
Kohonen T (2013) Essentials of the self-organizing map. Neural Netw 37:52–65. https://doi.org/10.1016/j.neunet.2012.09.018
Ultsch A, Siemon HP (1990) Kohonen’s self organizing feature maps for exploratory data analysis. In: Widrow B, Angeniol B (eds) Proceedings of the International Neural Network Conference (INNC-90), July 9–13, 1990, Paris, France. Kluwer Academic Publishers, Dordrecht, pp 305–308
Vesanto J, Alhoniemi E (2000) Clustering of the self-organizing map. IEEE Trans Neural Netw 11:586–600. https://doi.org/10.1109/72.846731
Figueiredo MATAT, Jain AKK (2002) Unsupervised learning of finite mixture models. IEEE Trans Pattern Anal Mach Intell 24:381–396. https://doi.org/10.1109/34.990138
Dempster AP, Laird NM, Rubin DB (1977) Maximum likelihood from incomplete data via the EM algorithm. J R Stat Soc Ser B 39:1–38
Schwarz G (1978) Estimating the dimension of a model. Ann Stat 6:461–464. https://doi.org/10.1214/aos/1176344136
Akaike H (1974) A new look at the statistical model identification. IEEE Trans Automat Contr 19:716–723. https://doi.org/10.1109/TAC.1974.1100705
Yu J, Abidi SSR, Artes PH (2005) A hybrid feature selection strategy for image defining features: towards interpretation of optic nerve images. In: Proceedings of 2005 International Conference on Machine Learning and Cybernetics: August 18–21, 2005, Ramada Hotel, Guangzhou, China. pp. 5127–5132. IEEE, Los Alamitos, CA, USA
Yan S, Abidi SSR, Artes PH (2005) Analyzing sub-classifications of glaucoma via SOM based clustering of optic nerve images. In: Engelbrecht R, Geissbuhler A, Lovis C, Mihalas G (eds) Connecting Medical Informatics and Bio-Informatics: Proceedings of MIE2005 The 19th International Congress of the European Federation for Medical Informatics (MIE2005), Geneva, August 28–September 1, 2005. IOS Press, Amsterdam, pp 483–488
Kohavi R, John GH (1997) Wrappers for feature subset selection. Artif Intell 97:273–324. https://doi.org/10.1016/S0004-3702(97)00043-X
Riedmiller M (1994) Advanced supervised learning in multi-layer perceptrons—from backpropagation to adaptive learning algorithms. Comput Stand Interfaces 16:265–278. https://doi.org/10.1016/0920-5489(94)90017-5
Rumelhart DE, Hinton GE, Williams RJ (1986) Learning representations by back-propagating errors. Nature 323:533–536. https://doi.org/10.1038/323533a0
Thomas P, Suhner M-C (2015) A new multilayer perceptron pruning algorithm for classification and regression applications. Neural Process Lett 42:437–458. https://doi.org/10.1007/s11063-014-9366-5
Cortes C, Vapnik V (1995) Support-vector networks. Mach Learn 20:273–297. https://doi.org/10.1007/BF00994018
Burges CJC (1998) A tutorial on support vector machines for pattern recognition. Data Min Knowl Discov 2:121–167. https://doi.org/10.1023/A:1009715923555
Yu W, Liu T, Valdez R, Gwinn M, Khoury MJ (2010) Application of support vector machine modeling for prediction of common diseases: the case of diabetes and pre-diabetes. BMC Med Inform Decis Mak 10:16. https://doi.org/10.1186/1472-6947-10-16
Boser BE, Guyon IM, Vapnik VN (1992) A training algorithm for optimal margin classifiers. In: Proceedings of the fifth annual workshop on Computational learning theory-COLT ‘92, Pittsburgh, Pennsylvania, USA—July 27–29, 1992. pp. 144–152. ACM Press, New York, New York, USA
Bowd C, Zangwill LM, Medeiros FA, Hao J, Chan K, Lee T-W, Sejnowski TJ, Goldbaum MH, Sample PA, Crowston JG, Weinreb RN (2004) Confocal scanning laser ophthalmoscopy classifiers and stereophotograph evaluation for prediction of visual field abnormalities in glaucoma-suspect eyes. Investig. Opthalmology Vis. Sci. 45:2255. https://doi.org/10.1167/iovs.03-1087
Bock R, Meier J, Nyúl LG, Hornegger J, Michelson G (2010) Glaucoma risk index: automated glaucoma detection from color fundus images. Med Image Anal 14:471–481. https://doi.org/10.1016/j.media.2009.12.006
Acharya UR, Dua S, Du X, Sree SV, Chua CK (2011) Automated diagnosis of glaucoma using texture and higher order spectra features. IEEE Trans Inf Technol Biomed 15:449–455. https://doi.org/10.1109/TITB.2011.2119322
Goldbaum MH, Sample PA, Chan K, Williams J, Lee T-W, Blumenthal E, Girkin CA, Zangwill LM, Bowd C, Sejnowski T, Weinreb RN (2002) Comparing machine learning classifiers for diagnosing glaucoma from standard automated perimetry. Invest Ophthalmol Vis Sci 43:162–169
Bergstra J, Bengio Y (2012) Random search for hyper-parameter optimization. J Mach Learn Res 13:281–305
Garcia S, Luengo J, Sáez JA, López V, Herrera F (2013) A survey of discretization techniques: taxonomy and empirical analysis in supervised learning. IEEE Trans Knowl Data Eng 25:734–750. https://doi.org/10.1109/TKDE.2012.35
Fayyad UM, Irani KB (1993) Multi-interval discretization of continuous-valued attributes for classification learning. In: Proc. of the 13th International Joint Conference on Artificial Intelligence—volume 2, Chambery, France, August 28-September 3, 1993. pp. 1022–1027. Morgan Kaufmann Publishers, San Mateo, CA
Nicolela MT, Drance SM (1996) Various glaucomatous optic nerve appearances. Ophthalmology 103:640–649. https://doi.org/10.1016/S0161-6420(96)30640-4
Hammel N, Belghith A, Bowd C, Medeiros FA, Sharpsten L, Mendoza N, Tatham AJ, Khachatryan N, Liebmann JM, Girkin CA, Weinreb RN, Zangwill LM (2016) Rate and pattern of rim area loss in healthy and progressing glaucoma eyes. Ophthalmology 123:760–770. https://doi.org/10.1016/j.ophtha.2015.11.018
Nicolela MT, Drance SM, Broadway DC, Chauhan BC, McCormick TA, LeBlanc RP (2001) Agreement among clinicians in the recognition of patterns of optic disk damage in glaucoma. Am J Ophthalmol 132:836–844. https://doi.org/10.1016/S0002-9394(01)01254-5
Xu D, Tian Y (2015) A comprehensive survey of clustering algorithms. Ann Data Sci 2:165–193. https://doi.org/10.1007/s40745-015-0040-1
Sarlin P, Eklund T (2013) Financial performance analysis of European banks using a fuzzified Self-Organizing Map. Int J Knowledge-based Intell Eng Syst 17:223–234. https://doi.org/10.3233/KES-130261
Raftery AE (1995) Bayesian model selection in social research. Sociol Methodol 25:111. https://doi.org/10.2307/271063
Lausen B, Adler W, Peters A (2008) Comparison of classifiers applied to confocal scanning laser ophthalmoscopy data. Methods Inf Med 47:38–46. https://doi.org/10.3414/ME0348
Liu W, Wang Z, Liu X, Zeng N, Liu Y, Alsaadi FE (2017) A survey of deep neural network architectures and their applications. Neurocomputing 234:11–26. https://doi.org/10.1016/J.NEUCOM.2016.12.038
Cerentini A, Welfer D, Cordeiro d’Ornellas M, Pereira Haygert CJ, Dotto GN (2017) Automatic identification of glaucoma using deep learning methods. Stud Health Technol Inform 245:318–321
Raghavendra U, Fujita H, Bhandary SV, Gudigar A, Tan JH, Acharya UR (2018) Deep convolution neural network for accurate diagnosis of glaucoma using digital fundus images. Inf Sci (Ny) 441:41–49. https://doi.org/10.1016/J.INS.2018.01.051
Shen D, Wu G, Suk H-I (2017) Deep learning in medical image analysis. Annu Rev Biomed Eng 19:221–248. https://doi.org/10.1146/annurev-bioeng-071516-044442
Kumar Y, Aggarwal A, Tiwari S, Singh K (2018) An efficient and robust approach for biomedical image retrieval using Zernike moments. Biomed Signal Process Control 39:459–473. https://doi.org/10.1016/J.BSPC.2017.08.018
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of Interest
On behalf of all authors, the corresponding author states that there is no conflict of interest.
Rights and permissions
About this article
Cite this article
Abidi, S.S.R., Roy, P.C., Shah, M.S. et al. A Data Mining Framework for Glaucoma Decision Support Based on Optic Nerve Image Analysis Using Machine Learning Methods. J Healthc Inform Res 2, 370–401 (2018). https://doi.org/10.1007/s41666-018-0028-7
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s41666-018-0028-7