Previous |  Up |  Next


image fusion; image analysis; 2D and 3D image registration; ophthalmology; retina imaging; subtractive angiography; computed tomography; illumination correction; image averaging; spatial transforms
The paper presents an overview of image analysis activities of the Brno DAR group in the medical application area of retinal imaging. Particularly, illumination correction and SNR enhancement by registered averaging as preprocessing steps are briefly described; further mono- and multimodal registration methods developed for specific types of ophthalmological images, and methods for segmentation of optical disc, retinal vessel tree and autofluorescence areas are presented. Finally, the designed methods for neural fibre layer detection and evaluation on retinal images, utilising different combined texture analysis approaches and several types of classifiers, are shown. The results in all the areas are shortly commented on at the respective sections. In order to emphasise methodological aspects, the methods and results are ordered according to consequential phases of processing rather then divided according to individual medical applications.
[1] al., R. Bock et: Glaucoma risk index: automated glaucoma detection from color fundus images. Medical Image Analysis 14 (2000), 3, 471–481.
[2] Brinkmann, B. H., Manduca, A., Robb, R. A.: Optimised homomorphic unsharp masking for MR greyscale inhomogeneity correction. IEEE Trans. Med. Imag. 17 2, 161–171. DOI 10.1109/42.700729
[3] Budenz, D. L.: Reproducibility of retinal nerve fiber thickness measurements using the stratus OCT in normal and glaucomatous eyes. Invest. Ophthalmology and Visual Science 46 (2005), 2440–2443. DOI 10.1167/iovs.04-1174
[4] Bellmann, C: Topography of fundus autofluorescence with a new confocal scanning laser ophthalmoscope. Ophthalmology 94 (1997), 385–91. DOI 10.1007/s003470050130
[5] Chanwimaluang, T., Fan, G.: An efficient blood vessel detection algorithm for retinal images using local entropy tresholding. Proc. Int. Symp. Circuits & Systems’03, 5 (2003), 21–24.
[6] Chrástek, R., Niemann, H., Kubečka, L., Jan, J., Derhartunian, V., Michelson, G.: Optic nerve head segmentation in multimodal retinal images. In: Proc. SPIE 2005, Bellingham 2005, pp. 1604–1615.
[7] al., R. Chrástek et: Segmentation of the optic nerve head for glaucoma diagnosis. In: Proc. SPIE 2005, Bellingham 2005, pp. 1604–1615.
[8] Ciulla, T. A., Regillo, C. D., Harris, A. H.: Retina and Optic Nerve Imaging. Lippincott Williams and Wilkins, Philadelphia 2003.
[9] Cree, M. J., Cornforth, D., Jelinek, H. F.: Vessel segmentation and tracking using a two-dimensional model. IVC New Zealand (2005), 345–350.
[10] Dawant, B. M., Zijdenbos, P., Margolin, R. A.: Correction of intensity variations in MR images for computer-aided tissue classification. IEEE Trans. Med. Imag. 12 (1993), 4, 770–781. DOI 10.1109/42.251128
[11] al., F. C. Delori et: In vivo fluorescence of the ocular fundus exhibits retinal pigment epithelium lipofuscin characteristics. Invest. Ophthalmol. Vis. Sci. 12 (1995), 718–29.
[12] Dodson, P. M.: Diabetic Retinopathy. Oxford University Press 2008.
[13] Figueiredo, M. A. T., Jain, A. K.: Unsupervised learning of finite mixture models. IEEE Trans. Pattern Analysis and Machine Intelligence 24 (2002), 3, 381–396. DOI 10.1109/34.990138
[14] al., M. J. Greaney et: Comparison of optic nerve imaging methods to distinguish normal eyes from those with glaucoma. Invest Ophthalmol Vis. Sci. 43 (2002), 1, 140–145.
[15] al., E. Grisan et: A new tracking system for robust extraction of retinal vessel structure. In: Proc. 26th IEEE EMBC 2004, San Francisco 2004, pp. 1620–1623.
[16] Gazárek, J., Kolář, R., Jan, J., Odstrčilík, J.: Blood vessel tree recontruction in retinal OCT data. In: Proc. EURASIP Conf. BIOSIGNAL 2010, Brno 2010, CD issue, 4 pp.
[17] Guillemaud, R., Brady, M.: Estimating the bias field of MR images. IEEE Trans. Med. Imag. 16 (1997), 3, 238–251. DOI 10.1109/42.585758
[18] al., Y. Hayashi et: Detection of retinal nerve fiber layer defects in retinal fundus images using Gabor filtering. In: Proc. of SPIE 6514 (2006).
[19] Hoh, St.: Evaluating the optic nerve head and retinal nerve fibre layer: The role of Heidelberg retina tomography, scanning laser polarimetry and optical coherence tomography. Annals Academy of Medicine 16 (2007), 195–202.
[20] Jan, J., Odstrčilík, J., Gazárek, J., Kolář., R.: Retinal image analysis aimed at early detection of neural-layer deterioration. Submitted.
[21] Jan, J., Chrástek, R., Kubečka, L.: Automated optic disc segmentation in multimodal images of retina. In: Proc. DOG/SOE Congress 2005, Berlin 2005, CD issue.
[22] Jan, J., al., R. Kolář et: Analysis of fused ophthalmologic image data. In: Proc. 6th EURASIP conf. Speech & Image Processing, Multimedia Communications & Services, Maribor 2007, pp. 37–40.
[23] Jan, J.: Retinal image analysis – Brno group). In: SAOT Retina Image Processing Workshop 2009, Erlangen Univ.
[24] Jan, J.: Retinal image analysis aimed at blood vessel structure segmentation and neural layer detection. In: Proc. BEC 2008, Tallin 2008, pp. 31–38
[25] Jan, J.: Medical Image Processing, Reconstruction and Restoration – Concepts and Methods. CRC Press, Taylor and Francis Group 2006.
[26] Jan, J., Odstrčilík, J., Gazárek, J., Kolář, R.: Retinal image analysis aimed at support of early neural-layer deterioration diagnosis. In: Proc. ITAB 2009, Larnaca, 4 pp., CD issue.
[27] Janknecht, P., Funk, J.: Optic nerve head analyser and Heidelberg retina tomograph: accuracy and reproducibility of topographic measurements in a model eye and in volunteers. British Journal of Ophthalmology 78 (1994), 760–768. DOI 10.1136/bjo.78.10.760
[28] Jorge, J., Leandro, G., al., M. Roberto et: Vessels segmentation in retina: Preliminary assessment of the mathematical morphology and of the wavelet transform techniques. In: XIV Brazilian SIBGRAPI’01 2001, pp. 84–91.
[29] Kolář, R., Šikula, V., Base, M.: Retinal image registration using phase correlation. In: Proc. 20th EURASIP Conf. BIOSIGNAL 2010, Brno 2010, CD issue, 4 pp.
[30] Kolář, R., Jan, J., Chrástek, R., Laemmer, R., Mardin, Ch. Y.: Autofluorescence areas detection in HRA images. In: Proc. EMBEC’05, Prague 2005, CD issue.
[31] Kolář, R., Kubečka, L., Jan, J., Chrastek, R.: Disparity estimation in uncalibrated stereo retina images. In: Proc. EMBEC’05, Prague 2005, CD issue.
[32] Kolář, R., Jan, J.: Detection of glaucomatous eye via color fundus images using fractal dimensions. In: Proc. 6th EURASIP Conf. Speech & Image Processing, Multimedia Communications & Services, Maribor 2007, pp. 37–40.
[33] Kolář, R., Jan, J., Kubečka, L.: Registration and fusion of the autofluorescent and infrared retinal images. Internat. J. Biomedical Imaging (2008), 513478, pp. 1–11.
[34] Kolář, R., Jan, J., Kubečka, L.: Computer support for early glaucoma diagnosis based on the fused retinal images. Scripta Medica (2006), 79, 269–276.
[35] Kolář, R., Jan, J., Jiřík, R.: Semiautomatic detection and evaluation of autofluorescent areas. In: Proc. IEEE–EMBC 2007, Lyon 2007, pp. 3327–3330.
[36] Kolář, R., Laemmer, R., Jan, J., Mardin, C.: The segmentation of zones with increased autofluorescence in the junctional zone of parapapillary atrophy. Physiological Measurement (2009), 30, 505–516.
[37] Kubečka, L., Jan, J.: Retinal image fusion and registration. In: Proc. EMBEC’05, Prague 2005, CD issue.
[38] Kubečka, L., Skokan, M., Jan, J.: Optimization methods for registration of multimodal images of retina. In: Proc. IEEE-EMBC, Cancun 2003, pp. 599–601.
[39] Kubečka, L., Jan, J.: Registration of bimodal retinal images – improving modifications. In: Proc. 26th IEEE EMBC, San Francisco 2004, pp. 1695–1698.
[40] Kubečka, L., Jan, J., Kolář, R.: Retrospective illumination correction of retinal images. J. Biomedical Imaging (2010), 5, 201–210.
[41] Kubečka, L., Jan, J., Kolář, R., Jiřík, R.: Improving quality of autofluorescence images using non-rigid image registration. In: Proc. EUSIPCO 2006, Florence 2006, CD issue, pp. 357–361.
[42] Kubečka, L., Jan, J., Kolář, R., Jiřík, R.: Elastic registration for auto-fluorescence image averaging. In: Proc. IEEE-EMBC 2006, New York 2006, CD issue, pp. 1948–1951.
[43] al., R. Laemmer et: Measurement of autofluorescence in the parapapillary atrophic zone in patients with ocular hypertension. Graefes Arch. Clin. Exp. Ophthalmol. (2007), 245, 51–58.
[44] Lalondey, M., Gagnony, L., Boucherz, M. C.: Non-recursive paired tracking for vessel extraction from retinal images. In: Proc. Vision Interface 2000, Montreal 2000, pp. 61-68.
[45] al., S. Y. Lee et: Automated quantification of retinal nerve fiber layer atrophy in fundus photograph. In: Proc. IEEE EMBC San Francisco 2004, 1, pp. 1241–1243.
[46] al., S. Z. Li et: Markov Radnom Field Modeling in Image Analysis. Springer 2009. MR 2493908
[47] al., R. Linde et: Reproducibility of parapapillary autofluorescence measurement in glaucoma diagnostics. In: Proc. DOG 2005, p. 482.
[48] Likar, B., Derganc, J., Pernus, F.: Segmentation-based retrospective correction of intensity non-uniformity in multispectral MR images. In: Proc. Conf. Medical Imaging: Image Processing, San Diego (M. Sonka, J. M. Fitzpatrick, eds.), Proc. SPIE 4684 (2002), pp. 1531–1540.
[49] Likar, B., Maintz, J. B., Viergever, M., Pernus, F.: Retrospective shading correction based on entropy minimization. J. Microscopy 197 (2000), 3, 285–295. DOI 10.1046/j.1365-2818.2000.00669.x
[50] Lois, N., Halfyard, A. S., Bird, A. C., Fitzke, F. W.: Quantitative evaluation of fundus autofluorescence imaged in vivo in eyes with retinal disease. Br. J. Ophthalmol. 84 (2000), 741–5. DOI 10.1136/bjo.84.7.741
[51] Lundström, M., Eklundh, O. J.: Computer densitometry of retinal nerve fibre atrophy – a pilot study. Acta Ophthalmologica 58 (1980), 4, 639–644. DOI 10.1111/j.1755-3768.1980.tb08306.x
[52] Maes, F.: Segmentation and Registration of Multimodal Medical Images. PhD. Thesis, Kath. Univ. Leuven 1998.
[53] Mangin, J.-F.: Entropy minimization for automatic correction of intensity nonuniformity. In: IEEE Works. MMBIA, Hilton Head Island 2000, 162–169.
[54] Michelson, G., Groh, M. J.: Screening models for glaucoma. Curr Opin Ophthalmol. 12 (2001), 2, 105–11. DOI 10.1097/00055735-200104000-00005
[55] Muramatsu, Ch., Hayashi, Y., al., A. Sawada et: Detection of retinal nerve fiber layer defects on retinal fundus images for early diagnosis of glaucoma. J. Biomedical Optics 15 (2010), 1, 1–7. DOI 10.1117/1.3322388
[56] al., R. Nayak et: Automated diagnosis of glaucoma using digital fundus images. J. Med. Syst. 33 (2009), 337–346. DOI 10.1007/s10916-008-9195-z
[57] al., H. Niemann et: Towards automated diagnostic evaluation of retina images. J. Pattern Recognition and Image Analysis 16 (2006), 4, 671–676. DOI 10.1134/S1054661806040146
[58] Niemeijer, M., Staal, J., al., B. Ginneken et: Comparative study of retinal vessel segmentation methods on a new publicly available database. In: Proc. SPIE Med. Imag., San Diego 5370 (2004), p. 648.
[59] al., J. Staal et: Ridge-based vessel segmentation in color images of the retina. IEEE Trans. on Medical Imaging 23 (2004), 4, 501–509. DOI 10.1109/TMI.2004.825627
[60] Odstrčilík, J., Jan, J., Gazárek, J., Kolář, R.: Improvement of vessel segmentation by matched filtering in colour retinal images. In: Proc. World Congress on Med. Physics Biomed. Engrg., Munich 2009, p. 4.
[61] Odstrčilík, J., Kolář, R., Harabis, V., Gazárek, J., Jan, J.: Retinal nerve fiber layer analysis via Markov random fields texture modelling. In: Proc. EUSIPCO 2010, Eurasip, Aalborg 2010.
[62] Perona, P., Malik, J.: Scale-space and edge detection using anisotropic diffusion. IEEE Trans. Pattern Analysis Machine Intelligence 12 (1990), 629–639. DOI 10.1109/34.56205
[63] Porter, R., Canagarajah, N.: Robust rotation-invariant texture classification: wavelet, Gabor filter and GMRF based schemes. IEEE Proc. Vis.-Image Signal Processing 144 (1997), 3, 180–188.
[64] Scheunders, P.: An orthogonal wavelet representation of multivalued images. IEEE Trans. Image Processing 12 (2003), 6, 718–725. DOI 10.1109/TIP.2003.811502 | MR 1988274
[65] Skokan, M., Skoupý, A., Jan, J.: Registration of multimodal images of retina. In: Proc. 24th Conf. IEEE EMBC, Houston 2002, pp. 1094–1096.
[66] Styner, M., Brechbuehler, CH., Szekely, G., Gerig, G.: Parametric estimate of intensity inhomogeneities applied to MRI. IEEE Trans. Med. Imag. 19 (2000), 3, 153–165. DOI 10.1109/42.845174
[67] Tvrdík, J.: Generalized controlled random search and competing heuristic. In: Proc. 10th Int. Conf. on Soft Computing MENDEL 2004, pp. 228–33.
[68] Tvrdík, J.: Controlled random search algorithm with alternating heuristics. AUTOMA (2002), 1, 54–57.
[69] Viestenz, A., Langenbucher, A., Mardin, C. Y.: Parapapillary autofluorescence as indicator for glaucoma. Klin. Monatsbl. Augenheilkd. 223 (2006), 315–20.
[70] al., K. A. Vermeer et: A model based method for retinal blood vessel detection. Computers in Biology and Medicine 34 (2004), 209–219. DOI 10.1016/S0010-4825(03)00055-6
[71] Zhu, J., Liu, B., Schwartz, S. C.: General illumination correction and its application to face normalization. In: Proc. IEEE ICASSP’03 3 (2003), pp. III–133–6.
[72] Zitová, B., Flusser, J.: Image registration methods: a survey image. Vis. Comput. 21 (2003), 977–1000. DOI 10.1016/S0262-8856(03)00137-9
Partner of
EuDML logo