نوع مقاله: مقاله کامل پژوهشی

نویسندگان

1 استادیار بخش برق، دانشکده فنی و مهندسی، دانشگاه آزاد اسلامی واحد کازرون

2 دانشیار گروه بیوالکتریک، دانشکدة مهندسی پزشکی، دانشگاه صنعتی امیرکبیر

3 استادیار بخش رادیولوژی، دانشگاه علوم پزشکی شیراز

10.22041/ijbme.2007.13488

چکیده

در این تحقیق فیلتر جدیدی برای حذف نویزهای لکه ای از تصاویر سونوگرافی طراحی شده است. فیلتر طراحی شده فیلتری با قابلیت های یادگیری شبکه های عصبی، تطبیق اطلاعات با قالب فازی و بهینه شدن متغیرها بر اساس الگوریتم ژنتیک تک عضوی است. شبکه عصبی به کار رفته یک شبکه چهار لایه رو به جلو با وزن های باینری است. ورودی در پنجره ای از همسایگی های پیکسل مورد پردازش فازی شده و به کمک قواعد ساده فازی مناسب آن اصلاح می شود. پهنای توابع عضویت و وزن های شبکه متغیرهایی اند که توسط الگوریتم ژنتیک بر خط (با یک عضو) و فقط با استفاده از عملگر جهش بهینه می شوند. نتایج به دست آمده نشان می دهد که این فیلتر سریع و هوشمند نسبت به فیلترهای استاندارد مانند میانه و وینر قدرت حذف نویز بالاتری دارد. همچنین با مقایسه این فیلتر با فیلتر فازی عصبی با الگوریتم یادگیری ژنتیک با 50 عضو جمعیت مشاهده شد که قابلیت کاهش نویز در هر دو نوع فیلتر مشابه بوده است هر چند سرعت یادگیری در فیلتر طراحی شده بسیار بیشتر است.

کلیدواژه‌ها

موضوعات

عنوان مقاله [English]

Speckle Noise Removal By Genetic Neuro-Fuzzy System In Sonography Images

نویسندگان [English]

  • Ali Rafiei 1
  • Mohammad Hasan Moradi 2
  • Mohammad Reza Farzaneh 3

1 Assistant professor, electrical department, Engineering School, Islamic Azad University, Kazeroun Branch

2 Associate professor, Biomedical Engineering School, Amirkabir University of Technology

3 Assistant professor,Radiology Department, Shiraz University Medical Sciences and Health Services

چکیده [English]

A new filter was designed and approved for speckle noise removal in sonography images. In this filter, a new idea is used by using neural network learning, fuzzy information and genetic algorithm optimization. The multi-layer perceptron neural network with binary weights is used in this filter. The neighborhood window of each pixel is used as input statistical features to estimate the noise level. Then it is fuzzificated and justified by simple fuzzy rules. The membership function width and network weights are optimized by on-line genetic algorithm. The on-line algorithm contains one individual, defined as a queen. In this algorithm, the next generation is created by using only the mutation operator. The performance of this filter was compared with the other speckle noise reduction techniques such as the median and homomorphic Wiener filters. Indeed, our proposed method is able to effectively remove speckle noises while preserving the quality of fine details in the image data better than the other methods. In this system, two classic and on-line GAs are used. The classic algorithm includes 50 strings. The results showed that both of the algorithms are the same in terms of noise reduction but the classic one is slower than the other one.

کلیدواژه‌ها [English]

  • Speckle Noise
  • Neuro-Fuzzy System
  • On-Line Genetic Algorithm
  • Classic Genetic Algorithm
  • Sonography Images

[1]     Tsantis S, Dimitropoulos N, Ioannidou M, Cavouras D, Nikiforidis G; Inter-scale wavelet analysis for speckle reduction in thyroid ultrasound images; Computerized Medical Imaging and Graphics 2007; 31(3):117-127.

[2]     Gupta S, Kaur L, Chauhan R C, Saxena S C; A versatile technique for visual enhancement of medical ultrasound images; Digital Signal Processing 2007; 17(3):542-560.

[3]     Achim A, Bezerianos A, Tsakalides P ; Novel bayesian multiscale method for speckle removal in medical ultrasound images; IEEE Trans on Med Imag 2001; 20(8):772-783.

[4]     Chirungrueng C, Suvichakorn A; Fast edge processing noise reduction for ultrasound images; IEEE Trans on Nucl Scien 2001; 48(3):849-854.

[5]     Adam D, Beilin-Nissan S, Friedman Z, Behar V; The combined effect of spatial compounding and nonlinear filtering on the speckle reduction in ultrasound images; Ultrasonics 2006; 44(2):166-181.

[6]     Li PC, Chen MJ; Strain compounding, a new approach for speckle reduction; IEEE Trans on Ultra Ferroelec and Freq Cont 2002; 49(1):39-46.

[7]     Husbey O, Lie T, Longo T; Bayesian 2-D deconvolution , a model for diffuse ultrasound scattering; IEEE Trans on Ultra Ferroelec and Freq Cont 2001; 48(1):121-130.

[8]     Abd-Elmoniem KZ, Kadad YM, Youssef AB; Real time ultrasound speckle reduction and coherent enhancement; Inter Conf on Imag Proc 2000; 1:160- 163.

[9]     Betrouni N, Vermandel M, Pasquier D, Maouche S, Rousseau J; Segmentation of abdominal ultrasoundn images of the prostate using a priori information and an adapted noise filter; Computerized Medical Imaging and Graphics 2005; 29(1): 43-51.

[10] Ritenour E, Nelson T, Raff U; Application of the median filter to digital radiographic images; In Proc IEEE Int Conf Acoust Spee Sig Proc 1998; 23(1):1-4.

[11] Loupas T, Mcdicken W, Allan P; An adaptive weighted median filter for speckle suppression in medical ultrasonic images; IEEE Trans Circ Sys 1989; 36:129–135.

[12] Czerwinsky RN, Jones DL, O’Brien Jr WD; Ultrasound speckle reduction by directional median filtering; In Proc Int Conf Imag Proc 1995; 1:358–361.

[13] Hu J, Hu X; Application of median filter to speckle suppression in intravascular ultrasound images; In Proc 2nd Austral NewZea Conf Intel Inform Sys 1994;302– 306.

[14] Fried R, Bernholt T, Gather U; Repeated median and hybrid filters; Computational Statistics & Data Analysis 2006; 50(9): 2313-2338.

[15] Lin T C, Yu P T; Partition fuzzy median filter based on fuzzy rules for image restoration; Fuzzy Sets and Systems 2004; 147(1): 75-97.

[16] Gupta K, Gupta R; Despeckle and geographical feature extraction in SAR images by wavelet transform; ISPRS Journal of Photogrammetry and Remote Sensing 2007; 62(6) 473-484.

[17] Ye W, Li X; A discrete problem on d-dimensional symmetric weighted median filters; Discrete Mathematics 2007; 23(3): 117-134.

[18] Simoncelli E, Adelson E; Noise removal via Bayesian wavelet coring; In Thir Int Conf Imag Proc 1996; 1:379–382.

[19] Zong X, Laine A, Geiser E; Speckle reduction and contrast enhancement of echocardiograms via multiscale nonlinear processing; IEEE Trans Med Imag 1998; 17:532–540.

[20] Gagnon L, Jouan A; Speckle filtering of SAR images—A comparative study between complexwavelet based and standard filters; In SPIE Proc 1997; 3169:80–91.

[21] Popescu M, Cristea P, Bezerianos A; Multiresolution distributed filtering: A novel technique that reduces the amount of data required in high-resolution electrocardiography; Future Gen Comp Sys 1999; 15:195–209.

[22] Papadimitriou S ,Bezerianos A; Multiresolution analysis and denoising of computer performance evaluation data with the wavelet transform; J Sys Archit 1996; 42:55–65.

[23] Lin CT, Juang CF; An adaptive neural fuzzy filter and its applications; IEEE Trans On Sys Man And Cyber- Part b: Cyber 1997; 27(4):635-656.

[24] Russo F; Evolutionary neural fuzzy system for data filtering; IEEE Inst And Meas Tech Conf St Paul Minnesola, USA 1998; 826-831.

[25] Cojbasic ZM Nikolic VD; An approach to neuro-fuzzy filtering for communications and control; 5th Inter Conf On Telecom In Mod Sat Cab And Broad Serv: TELSIKS 2001; 2:719-722.

[26] Hong X Harris Cj Wilson PA; Neurofuzzy state identification using prefiltering; IEE Proc. Cont.Theory Appl. 1999; 146(2):234-240.

[27] Russo F; Evolutionary neural fuzzy systems for noise cancellation in image data; IEEE Trans On Instr And Meas 1999; 48(5):915-920.

[28] Wong HS Guan L; A neural learning approach for adaptive image restoration using a fuzzy model-based network architecture; IEEE Trans Neur Net 2001; 12(3):516-531.

[29] Sinha SK Karray F; Classification of underground pipe scanned images using feature extraction and neurofuzzy algorithm; IEEE Trans On Neur Net 2002; 13(2):393-401.

[30] Boskovitz V Guterman H; An adaptive neuro fuzzy system for automatic image segmentation and edge detection; IEEE Trans On Fuz Sys 2002; 10(2):247- 262.

[31] Rafiee A Moradi MH Farzaneh MR; Impulse noise reduction in sonography images by using neuro-fuzzy filters; Mach Visi And Imag Proc: MVIP2003 KhajehNasir Al-Din Toosi University Tehran Iran 2003: 102-109.

[32] Wang LX; Adaptive Fuzzy Systems and Control: Design and Stability Analysis; Prentice Hall: Englewood Cliffs: NJ 1994.

[33] Durant EA Wakefield GH; Efficient model fitting using a genetic algorithm: pole-zero approximations of HRTFs; IEEE Trans On Spee And Aud Proc 2002; 10(1):18-27.

[34] Goldberg DE; Genetic Algorithms in Search, Optimization and Machine Learning Reading; MA: Addison-Wesley; 1989.

[35] Russo M; Genetic fuzzy learning; IEEE Trans On Evolut Comput 2000; 4(3):259-273.

[36] Saifipour N; On-line Genetic Algorithm in Optimization and Control; Ph.D. Thesis Amirkabir University; 2002.