Novel Genetic-Neuro-Fuzzy Filter for Speckle Reduction from Sonography Images
- 89 Downloads
Edge-preserving speckle noise reduction is essential to computer-aided ultrasound image processing and understanding. A new class of genetic-neuro-fuzzy filter is proposed to optimize the trade-off between speckle noise removal and edge preservation. The proposed approach combines the advantages of the fuzzy, neural, and genetic paradigms. Neuro-fuzzy approaches are very promising for nonlinear filtering of noisy images. Fuzzy reasoning embedded into the network structure aims at reducing errors while fine details are being processed. The learning method based on the real-time genetic algorithms (GAs) performs an effective training of the network from a collection of training data and yields satisfactory results after a few generations.
The performance of the proposed filter has been compared with that of the commonly used median and Wiener filters in reducing speckle noises on ultrasound images. We evaluate this filter by passing the filter’s output to the edge detection algorithm and observing its ability to detect edge pixels.
Experimental results show that the proposed genetic-neuro-fuzzy technique is very effective in speckle noise reduction as well as detail preserving even in the presence of highly noise corrupted data, and it works significantly better than other well-known conventional methods in the literature.
KeywordsUltrasound speckle real-time genetic algorithm neuro-fuzzy genetic-neuro-fuzzy
The authors thank the anonymous reviewers of this paper for their detailed comments and suggestions.
- 1.Achim, AL, Bezerianos, AN, Tsakalides, PA 2001Novel bayesian multiscale method for speckle removal in medical ultrasound imagesIEEE Trans On Medical Imaging20772783Google Scholar
- 2.Chirungrueng, CH, Suvichakorn, AI 2001Fast edge processing noise reduction for ultrasound imagesIEEE Trans Nuclear Science48849854Google Scholar
- 5.Jain, AN 1989Fundamentals of Digital Image Processing Englewood CliffsNJ, Prentice-HallGoogle Scholar
- 6.Li, P-C, Chen, M-J 2002Strain compounding, a new approach for speckle reductionIEEE Trans. Ultr. Ferroelectonic Freq. Cont.493946Google Scholar
- 7.Husbey, OD, Lie, TO, Longo, TH 2001Bayesian 2-D deconvolution, a model for diffuse ultrasound scatteringIEEE Trans. Ultr. Ferroelectonic Freq. Cont48121130Google Scholar
- 8.KHZ Abd-Elmoniem, Ya M Kadad, AB BA M Youssef: Real time ultrasound speckle reduction and coherent enhancement. In International Conference on Image Processing, 10–13 Sept. 2000: Image Processing Proceeding, 2000 IEEE, Vol 1, pp. 172–175Google Scholar
- 9.Ioannidis AL, Kazakos DA, Watson DD: Application of median filtering on nuclear medicine scintigram images. In: Proceedings of the 7th International Conference on Pattern Recognition, Montreal, Canada, pp. 33–36, 1984Google Scholar
- 10.Ritenour, ER, Nelson, TR, Raff, UO 1998Application of the median filter to digital radiographic imagesProc. IEEE Int. Conf. Acoust. Speech, Signal Processing.23112314Google Scholar
- 13.Hu, J, Hu, X (1994) “Application of median filter to speckle suppression in intravascular ultrasound images” Intelligent Information Systems 1994. In: Proc. 1994 2nd IEEE Australian and New Zealand Conf. Intelligent Information Systems, 29 Nov–2 Dec 1994, pp 302–306Google Scholar
- 15.Huang, TS, Yang, GY, Tang, GY 1979A fast two-dimensional median filtering algorithmIEEE Trans. Acoust. Speech, Signal ProcessingASSP-271318Google Scholar
- 16.Pitas, I, Venetsanopolous, AN 1990Nonlinear Digital Filter-Principles and ApplicationsKluwer AcademicNorwell, MAGoogle Scholar
- 17.Zong, X, Laine, AF, Geiser, EA 1998Speckle reduction and contrast enhancement of echocardiograms via multiscale nonlinear processingIEEE Trans. Med. Imag17532540Google Scholar
- 18.Lin, CT, Juang, CF 1997An adaptive neural fuzzy filter and its applicationsIEEE Trans Systems, Man, and Cybernetics—Part b: Cybernetics27635656Google Scholar
- 19.Russo, F 1998A Evolutionary neural fuzzy system for data filteringIEEE Inst. Meas. Tech. Conf. St Paul Minnesola.826831MAY 18–21Google Scholar
- 20.Cojbasic F, Nikolic VD: An approach to neuro-fuzzy filtering for communications and control. In: 5th IEEE International Conference on Telecommunications in Modern Satellite, Cable and Broadcasting Service, TELSIKS 2001, Vol. 2, pp. 719–722, 2001Google Scholar
- 22.Russo, F 1999Evolutionary neural fuzzy systems for noise cancellation in image dataIEEE Trans Instr Meas48915920Google Scholar
- 23.Wong, HS, Guan, L 2001A neural learning approach for adaptive image restoration using a fuzzy model-based network architectureIEEE Trans Neural Networks12516531Google Scholar
- 25.Boskovitz, V, Guterman, H 2002An adaptive neuro-fuzzy system for automam tic image segmentation and edge detectionIEEE Trans Fuzzy Systems10247262Google Scholar
- 26.Russo, M 2000Genetic fuzzy learningIEEE Trans Evol Comput4259273Google Scholar
- 27.Durant, EA, Wakefield, GH 2002Efficient model fitting using a genetic algorithm: pole-zero approximations of HRTFsIEEE Trans Speech Audio Processing101827Google Scholar
- 28.Goldberg DE: Genetic algorithms. In: Search, Optimization and Machine Learning. Reading, MA: Addison-Wesley, 1989Google Scholar
- 29.Rafiee Kerachi A, Moradi MH, Farzaneh MR: Impulse noise reduction in sonography images by using neuro-fuzzy filters. Second Iranian Conference on Machine Vision, Image Processing & Applications, MVIP2003, KhajehNasir Al-Din Toosi University Tehran, Iran, 2003Google Scholar
- 30.Rafiee A: Sonography images enhancement by neuro-fuzzy algorithms. Ph.D. Thesis, Research and Science campus, Islamic Azad University, Tehran, Iran, 2003Google Scholar
- 31.Saifipour N: On-line genetic algorithm in optimization and control. Ph.D. Thesis Amirkabir University, Tehran, Iran, 2002Google Scholar