Abstract
Posterior capsule opacification (PCO) is the most common complication of cataract surgery, occurring in up to 50% of patients by 2–3 years after the operation [Spalton in Eye 13(Pt 3b):489–492, 1999]. This paper proposes a new approach for the assessment of PCO digital images. The approach deploys an unsupervised learning technique for clustering image pixels into different regions based on chromatic attributes. The innovative aspect of this paper lies in proposing the number of regions in a clustered image as a measurement tool for assessing the PCO. Experiments using synthetic data confirmed the plausibility of this approach. A series of experiments conducted on real PCO images demonstrated the robustness and stability of the proposed algorithm. Finally, the comparison of our method’s assessment with medical expert evaluation reveals a very reasonable concordance.
Similar content being viewed by others
References
Spalton DJ (1999) Posterior capsular opacification after cataract surgery. Eye 13(Pt 3b):489–492
Aslam TM, Dhilon B, Werghi N, Taguri A, Wadood A (2002) Systems of analysis of posterior capsule opacification. Br J Ophtalmol 86:1181–1186
Lasa MS, Datiles MB, Magno BV, Mahurkar A (1995) Scheimpflug photography and postcataract surgery posterior capsule opacification. J Ophthal Surg 26:110–113
Hayashi K, Hayashi H, Nakao F, Hayashi F (1998) In vivo quantitative measurement of posterior capsule opacification after extracapsular cataract surgery. Am J Ophthalmol 125(6): 837–843
Tetz MR, Auffrath GU, Speaker M (1997) Photographic image analysis system, of posterior capsule opacification. J Cataract Refract Surg 23:1515–1520
Ursell PG, Spalton DJ, Pande MV (1998) Relationship between intraocular lens biomaterials and posterior capsule opacification. J Cataract Refract Surg 24:352–360
Wang MC, Woung LC (2000) Digital retroilluminated photography to analyze posterior capsule opacification in eyes with intraocular lenses. J Cataract Refract Surg 26:56–51
Friedman DS, Duncan DD, Munoz B (1999) Digital image capture and automated analysis of posterior capsular opacification. Investig Ophthalmol Vis Sci 40:1715–1726
Barman B, Hollick EJ, Boyce JF (2000) Quantification of posterior, capsular opacification in digital images after cataract surgery. Investig Ophthalmol Vis Sci 41:3883–3892
Paplinski AP, Boyce JF (1997) Segmentation of a class of ophthalmological images using a directional variance operator and co-occurrence arrays. Opt Eng 36:3140–3147
Paplinski AP, Boyce JF, Barman SA (2000) Automatic quantification of posterior capsule opacification. In: Proceedings of SPIE: medical imaging 3979:951–958
Siegl H, Pinz A, Bühl W, Georgopoulos M, Findl O, Menapace R (2001) Assessment of posterior capsule opacification after cataract surgery. In: Proceedings 12th SCIA, Scandinavian conference on image analysis, Bergen, pp 54–61
Findl O et al (2003) Comparison of 4 methods for quantifying posterior capsule opacification. J Cataract Refract Surg 29:106–111
Aslam T, Patton N, Graham J (2005) A freely accessible, evidence based, objective system of analysis of posterior capsular opacification; evidence for its validity and reliability. BMC Ophthalmol 5(1):1–10
Rao KS, Raju S, Wang JR (1993) Estimation of soil moisture and surface roughness parameters from backscattering coefficient. IEEE Trans Geosci Remote Sens 31(5):1094–1099
Zhang K, Butler C, Yang Q (1997) A fiber optic sensor for the measurement of surface roughness and displacement using artificial neural network. IEEE Trans IEEE Trans Instrumen Meas 46(4):899–902
Lo SP, Chiu JT, Lin HY (2005) Rapid measurement of surface roughness for face-milling aluminum using laser scattering and the Taguchi method. Int J Adv Manuf Technol 26(9–10):1071–1077
Gunarathne GPP, Christidis K (2000) Measurement of surface texture using ultrasound. Proc IEEE Conf Instrum Meas Technol 2:611–616
Lee BY, Juan H, Yu SF (2002) A study of computer vision for measuring surface roughness in the turning process. Int J Adv Manuf Technol 19(4), February (2002)
Balagurunathan Y, Dougherty ER (2003) Morphological quantification of surface roughness. Opt Eng 42(6):1795–804
MacKay D (2003) Information theory, inference and learning algorithms. Cambridge University Press
Tyree EW, Long JA (1998) A Monte Carlo evaluation of the moving method, k-means and two self-organising neural networks. Pattern Anal Appl 1(2):79–90
Hopefield JJ (1984) Neurons with graded response have collective computationla properties like those of two-state neurons. Proc Natl Acad Sci 81:3088–3092
Hopfield JJ, Tank DW (1985) Neural computation of descisions in optimization problems. Biol Cybern 52:141–152
Takefuji Y (1992) Neural network parallel computing. Kluwer Academic, Dordrecht
Takefuji Y (1992) Neural network parallel computing for combinatorial optimization problems. J Knowl Eng 5(3):41–61
Huang CL (1992) Parallel image segmentation using modified Hopfield model. Pattern Recognit Lett 13(5):345–353
Poli R, Valli G (1995) Hopfield neural nets for the optimum segmentation of medical images. In: Fiesler E, Beale R (eds) Handbook of neural computation chapter G.5.5. Oxford University Press
Campadelli P, Medici D, Schettini R (1997) Color image segmentation using Hopfield networks. Image Vis Comput 15(3):161–166
Kagamar-Parsi B, Gualtieri JA, Devaney JE, Kamagar- Parsi B (1990) Clustering with neural networks. Biol Cybern 61:201–208
Amartur SC, Piraino D, Takefuji Y (1992) Optimization neural networks for the segmentation of magnetic resonance images. IEEE Trans Med Imagaing 11(2):215–220
Rosenfeld A, Pfalz A (1966) Sequential operations in digital picture processing. J ACM 13(4):471–494
Haralick RM, Shapiro LG (1992) Computer and robot vision, vol 1. Addison–Wesley, pp 28–48
Glassner A (2001) Fill ’er up! IEEE Comput Graph Appl 21(1):78–85
Preteux F, Schmitt M (1988) Random texture analysis and synthesis. In: Serra J (ed) Image analysis and mathematical morphology, vol 2. Academic Press, New York
Jain AK, Murty MN, Flynn PJ (1999) Data clustering: a review. ACM Comput Surv 31(3):264–323
Dumitrescu D, Lazzerini B, Marcelloni F (2000) A fuzzy hierarchical classification system for olfactory signals. Pattern Anal Appl 3(4)
Chou Y-Y, Shapiro LG (2003) A hierarchical multiple classifier learning algorithm. Pattern Anal Appl 6:(2)
Omran MGH, Salman A, Engelbrecht AP (2006) Dynamic clustering using particle swarm optimization with application in image segmentation. Pattern Anal Appl 8(4)
Pelleg D, Moore A (2000) X-means: extending K-means with efficient estimation of the number of clusters. In: Proceedings of 17th international conference on machine learning, San Francisco, CA, USA, pp 727–734
Hamerly G, Elkan C (2003) Learning the k in k-means. In: Proceedings of conference on neural information processing systems, pp 281–288
Feng Y, Hamerly G (2006) PG-means: learning the number of clusters in data. In: Proceedings of conference on neural information processing systems, pp 393–400
Acknowledgments
We would like to thank Dr. Tariq Aslam from the Manchester Eye Hospital, UK, for providing the PCO images and Dr. P. Bhatia, Dr. A. Rao, Dr. P. Warhekar, Dr K.H. Sathish and Dr. B.S. Chidamber from the Ophthalmology Department at Welcare Hospital, for their kind collaboration and feedback.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Werghi, N., Sammouda, R. & AlKirbi, F. An unsupervised learning approach based on a Hopfield-like network for assessing posterior capsule opacification. Pattern Anal Applic 13, 383–396 (2010). https://doi.org/10.1007/s10044-010-0181-y
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10044-010-0181-y