A novel approach for automatic blood vessel extraction in retinal images: complex ripplet-I transform and complex valued artificial neural network

This study determined the features of line, curve, and ridge structures in images using complex ripplet-I and enabled extraction of blood vessel networks from retinal images through a complex valued artificial neural network using those features. Forty color fundus images in the DRIVE database and 20 color fundus images in the STARE database were used to test the success of the proposed system. In this study, a complex version of ripplet-I transform was used for the first time. By presenting the directed image for the determination of the unique geometrical properties of the vessel regions, complex ripplet-I transforms showing better performance than other types of multiresolution analysis were combined with a complex valued ANN. The results in the study were reobtained using leave-one-out crossvalidation method with bagging technique in order to ensure the stability and correctness of the performance. In the DRIVE database, the highest average accuracy of the system was found to be 98.44% for complex ripplet-I transform and complex valued ANN. For the STARE database (labeled by Adam Hoover), highest average accuracy rates were obtained as 99.25% for complex ripplet-I transforms and complex valued ANN. Similarly, for the other labeled data (by Valentina Kouznetsova), highest average accuracy rates were obtained as 98.03% for complex ripplet-I transforms and complex valued ANN.

PDF

___

[1] Akita K, Kuga H. A computer method of understanding ocular fundus images. Pattern Recogn 1982; 15: 431-443.
[2] 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. In: IEEE International Conference Image Processing; 1619 September 1996; Lausanne, Switzerland. New York, NY, USA: IEEE. pp. 695- 698.
[3] Chutatape O, Zheng L, Krishnan SM. Retinal blood vessel detection and tracking by matched Gaussian and Kalman filters. In: IEEE International Conference Engineering in Medicine and Biology Society; 29 October1 November 1998; Hong Kong. New York, NY, USA: IEEE. pp. 3144-3149.
[4] Sinthanayothin C, Boyce JF, Cook HL, Williamson TH. Automatic localisation of the optic disk, fovea, and retinal blood vessels from digital colour fundus images. Brit J Ophthalmol 1999; 83: 902-910.
[5] Hoover AD, Kouznetsova V, Goldbaum M. Locating blood vessels in retinal images by piece-wise threshold probing of a matched filter response. IEEE T Med Imaging 2000; 19: 203-210.
[6] Staal J, Abramoff MD, Niemeijer M, Viergever MA, Ginneken B. Ridge based vessel segmentation in color images of the retina. IEEE T Med Imaging 2004; 23: 501-509.
[7] Soares JVB, Leandro JJG, Cesar RM, Jelinek HF, Cree MJ. Retinal vessel segmentation using the 2-D Gabor wavelet and supervised classification. IEEE T Med Imaging 2006; 25: 1214-1222.
[8] Mendon¸ca AM, Campilho A. Segmentation of retinal blood vessels by combining the detection of centerlines and morphological reconstruction. IEEE T Med Imaging 2006; 25: 1200-1213.
[9] Ricci E, Perfetti R. Retinal blood vessel segmentation using line operators and support vector classification. IEEE T Med Imaging 2007; 26: 1357-1365.
[10] Martinez-Perez ME, Hughes AD, Thom SA, Bharath AA, Parker KH. Segmentation of blood vessels from red-free and fluorescein retinal images. Med Image Anal 2007; 11: 47-61.
[11] Feng P, Pan Y, Wei B, Jin W, Mi D. Enhancing retinal image by the contourlet transform. Pattern Recogn Lett 2007; 28: 516-522.
[12] Zhang Y, Hsu W, Lee ML. Segmentation of retinal vessels using nonlinear projections. In: IEEE International Conference on Image Processing; 16 September19 October 2007; San Antonio, TX, USA. New York, NY, USA: IEEE. pp. 541-544.
[13] Lam BSY, Yan H. A novel vessel segmentation algorithm for pathological retina images based on the divergence of vector fields. IEEE T Med Imaging 2008; 27: 237-246.
[14] Kande GB, Savithri TS, Subbaiah PV. Retinal vessel segmentation using spatially weighted fuzzy c-means clustering and histogram matching. In: IEEE India Conference; 1113 December 2008; Kanpur, India. New York, NY, USA: IEEE. pp. 1-6.
[15] Akram MU, Atzaz A, Aneeque SF, Khan SA. Blood vessel enhancement and segmentation using wavelet transform. In: IEEE International Conference on Digital Image Processing; 79 March 2009; Bangkok, Thailand. New York, NY, USA: IEEE. pp. 34-38.
[16] Xu L, Luo S. A novel method for blood vessel detection from retinal images. Biomed Eng Online 2010; 9: 1-14.
[17] Peng Q, Peng G, Xu D, You X, Pang B. A fast approach to retinal vessel segmentation. In: Chinese Conference on Pattern Recognition; 2123 October 2010; Chongqing, China. New York, NY, USA: IEEE. pp. 1-5.
[18] Moghimirad E, Rezatofighi SH, Soltanian-Zadeh H. Multi-scale approach for retinal vessel segmentation using medialness function. In: IEEE International Symposium on Biomedical Imaging: From Nano to Macro; 1417 April 2010; Rotterdam, the Netherlands. New York, NY, USA: IEEE. pp. 29-32.
[19] Peng Q, You X, Zhou L, Cheung Y. Retinal blood vessels segmentation using the radial projection and supervised classification. In: International Conference on Pattern Recognition; 2326 August 2010; ˙Istanbul, Turkey. New York, NY, USA: IEEE. pp. 1489-1492
[20] Akram MU, Khanum A. Retinal images: blood vessel segmentation by threshold probing. In: IEEE Symposium on Industrial Electronics & Applications; 35 October 2010; Penang, Malaysia. New York, NY, USA: IEEE. pp. 493-497.
[21] Marin D, Aquino A, Gegundez-Arias ME, Bravo JM. A new supervised method for blood vessel segmentation in retinal images by using gray-level and moment invariants-based features. IEEE T Med Imaging 2011; 30: 146-158.
[22] Miri MS, Mahloojifar A. Retinal image analysis using curvelet transform and multistructure elements morphology by reconstruction. IEEE T Bio-Med Eng 2011; 58: 1183-1191.
[23] Fraz MM, Remagnino P, Hoppe A, Velastin S, Uyyanonvara B, Barman SA. A supervised method for retinal blood vessel segmentation using line strength, multiscale Gabor and morphological features. In: IEEE International Conference on Signal and Image Processing Applications; 1618 November 2011; Kuala Lumpur, Malaysia. New York, NY, USA: IEEE. pp. 410-415.
[24] Onkaew D, Turior R, Uyyanonvara B, Kondo T. Automatic extraction of retinal vessels based on gradient orientation analysis. In: International Joint Conference on Computer Science and Software Engineering; 1113 May 2011; Nakhon Pathom, Thailand. New York, NY, USA: IEEE. pp. 102-107.
[25] Fraz MM, Basit A, Remagnino P, Hoppe A, Barma SA. Retinal vasculature segmentation by morphological curvature, reconstruction and adapted hysteresis thresholding. In: International Conference on Emerging Technologies; 56 September 2011; Islamabad, Pakistan. New York, NY, USA: IEEE. pp. 1-6.
[26] Xiang D, Tian J, Deng K, Zhang X, Yang F, Wan X. Retinal vessel extraction by combining radial symmetry transform and iterated graph cuts. In: International Conference of the IEEE Engineering in Medicine and Biology Society; 30 August3 September 2011; Boston, MA, USA. New York, NY, USA: IEEE. pp. 3950-3953.
[27] Kharghanian R, Ahmadyfard A. Retinal blood vessel segmentation using Gabor wavelet and line operator. International Journal of Machine Learning and Computing 2012; 2: 593-597.
[28] Devi KK, Anto A, Peter KJ. Curvelet transform and multi structure elements morphology by reconstruction based retinal image analysis. International Journal of Soft Computing and Engineering 2012; 2: 548-553.
[29] Kalaivani M, Jeyalakshmi MS, Aparna V. Extraction of retinal blood vessels using Curvelet transform and Kirschs templates. International Journal of Emerging Technology and Advanced Engineering 2012; 2: 360-363.
[30] Shahbeig S. Retinal image analysis using multi-directional functors based on geodesic conversions. Turk J Electr Eng Co 2014; 22: 768-779.
[31] Shajahan SN, Roy RC. An improved retinal blood vessel segmentation algorithm based on multistructure elements morphology. International Journal of Computer Applications 2012; 57: 31-36.
[32] Yin Y, Adel M, Bourennane S. An automatic tracking method for retinal vascular tree extraction. In: IEEE International Conference on Acoustics, Speech and Signal Processing; 2530 March 2012; Kyoto, Japan. New York, NY, USA: IEEE. pp. 709-712.
[33] Oliveira WS, Ren TI, Cavalcanti GDC. An unsupervised segmentation method for retinal vessel using combined filters. In: International Conference on Tools with Artificial Intelligence; 79 November 2012; Athens, Greece. New York, NY, USA: IEEE. pp. 750-756.
[34] Oliveira WS, Ren TI, Cavalcanti GDC. Retinal vessel segmentation using average of synthetic exact filters and hessian matrix. In: International Conference on Image Processing; 30 September3 October 2012; Orlando, FL, USA. New York, NY, USA: IEEE. pp. 2017-2020.
[35] Johnson RC, Padmagireesan SJ, Raheem A, Pillai AV. Comparison of curvelet and contourlet transforms for retinal analysis. In: IEEE India Conference; 79 December 2012; Kochi, India. New York, NY, USA: IEEE. pp. 1214-1217.
[36] Silvia MJ, Poovizhi S. Retinal image analysis using ripplet-I transform and segmentation using morphological gradient. International Journal of Emerging Technology and Advanced Engineering 2012; 2: 719-724.
[37] Shanmugam V, Banu RSDW. Retinal blood vessel segmentation using an extreme learning machine approach. In: IEEE Point-of-Care Healthcare Technologies; 1618 January 2013; Bangalore, India. New York, NY, USA: IEEE. pp. 318-321.
[38] Fraz MM, Remagnino P, Hoppe A, Barma SA. Retinal image analysis aimed at extraction of vascular structure using linear discriminant classifier. In: International Conference on Computer Medical Applications; 2022 January 2013; Sousse, Tunis. New York, NY, USA: IEEE. pp. 1-6.
[39] Ocbagabir H, Hameed I, Abdulmalik S, Barkana Buket D. A novel vessel segmentation algorithm in color images of the retina. In: Applications and Technology Conference; 3 May 2013; Farmingdale, NY, USA. New York, NY, USA: IEEE. pp. 1-6.
[40] Asad AH, Azar AT, Fouad MMM, Hassanien AE. An improved ant colony system for retinal blood vessel segmentation. In: Federated Conference on Computer Science and Information Systems; 811 September 2013; Krakow, Poland. New York, NY, USA: IEEE. pp. 199-205.
[41] Sheet D, Karri SPK, Conjeti S, Ghosh S, Chatterjee J, Ray AK. Detection of retinal vessels in fundus images through transfer learning of tissue specific photon interaction statistical physics. In: International Symposium on Biomedical Imaging; 711 April 2013; San Francisco, CA, USA. New York, NY, USA: IEEE. pp. 1452-1456.
[42] Ceylan M, Ya¸sar H. Blood vessel extraction from retinal images using complex wavelet transform and complexvalued artificial neural network. In: International Conference on Telecommunications and Signal Processing; 24 July 2013; Rome, Italy. New York, NY, USA: IEEE. pp. 822-825.
[43] Candes EJ, Donoho DL. Curvelets-A surprisingly effective nonadaptive representation for objects with edges. In: Cohen A, Rabut C, Schumaker L, editors. Curves and Surface Fitting. Nashville, TN, USA: Vanderbilt University Press, 1999. pp. 105-120.
[44] Donoho DL, Duncan MR. Digital curvelet transform: strategy, implementation and experiments. In: SPIE on Wavelet Application VII; 5 April 2000; Orlando, FL, USA. Orlando, FL, USA: SPIE. pp. 12-30.
[45] Candes EJ, Guo F. New multiscale transforms, minimum total variation synthesis: application to edge-preserving image reconstruction. Signal Process 2002; 82: 1519-1543.
[46] Candes EJ, Donoho DL. New tight frames of curvelets and optimal representations of objects with piecewise-C2 singularities. Commun Pur Appl Math 1999; 57: 219-266.
[47] Candes EJ, Demanet L, Donoho DL, Ying L. Fast Discrete Curvelet Transforms. Technical Report 2005. Pasadena, CA, USA: Applied and Computational Mathematics-California Institute of Technology.
[48] Neelamani R, Baumstein A, Ross W. Adaptive subtraction using complex-valued curvelet transform. Geophysics 2010; 75: V51-V60.
[49] He Y, Xing-Lan Z , Wei-Wei L, Feng C. Image restoration using Gaussian scale mixtures in complex curvelet transform domain. In: International Conference on Measuring Technology and Mechatronics Automation; 1314 March 2010; Changsha City, China. New York, NY, USA: IEEE. pp. 427-430.
[50] Xu J, Yang L, Wu D. Ripplet: A new transform for image processing. J Vis Commun Image R 2010; 21: 627-639.
[51] www.curvelet.org (accessed 21 August 2014).
[52] Ceylan R, Ceylan M, Ozbay Y, Kara S. Fuzzy clustering complex-valued neural network to diagnose cirrhosis ¨ disease. Expert Syst Appl 2011; 38: 9744-9751.