Fuzzy genetic-based noise removal filter for digital panoramic X-ray images

• Autorzy: Rafati M. , Farnia F. , Taghvaei M. E. , Nickfarjam A. M.

Identyfikatory

DOI

10.1016/j.bbe.2018.08.005

• Języki publikacji: EN

Abstrakty

EN

This paper proposed a novel fuzzy genetic-based noise removal filter and surveyed the gain of popular filters for noise removal in the digital orthopantomography (OPG) images. The proposed filter is a non-invasive technique for attaining sub-clinical information from the areas of interest in each tooth, both jaws and maxillofacial. The proposed Poisson removal filter combines 4th-order partial differential equations (PDE), total variation (TV) and Bayes shrink threshold accompanied by fuzzy genetic algorithm (FGA) and the exact unbiased inverse of generalized Anscombe transformation (EUIGAT). Experiments were performed in order to show the effect of noise removal filters on 110 simulated, 106 phantom and 104 panoramic radiographic images for subjects (aged 30–60 years old, 50 males and 54 females). Various noises degraded filters and Canny edge detection was performed separately in three kinds of images. The program measured mean square error (MSE), peak signal to noise ratio (PSNR), image quality index (IQI), structural similarity index metric (SSIM) and figure of merit (FOM). The results verify that the proposed filter enhances physicians' and dentists' skill of diagnosing normal and pathological events in the teeth, jaws, temporomandibular joint (TMJ) regions and changeable anatomical panoramic landmarks related to osteoporosis progress in the mandible bone using noise removal and improving images quality. Experimental results show the superiority of this filter over other noise removal filters.

Słowa kluczowe

EN

orthopantomography image; genetic algorithm; Poisson noise; Anscombe transformation

PL

obraz ortopantomograficzny; algorytm genetyczny; transformacja Anscombe

• Wydawca: Nałęcz Institute of Biocybernetics and Biomedical Engineering of the Polish Academy of Sciences ; Elsevier
• Czasopismo: Biocybernetics and Biomedical Engineering
• Rocznik: 2018
• Tom: Vol. 38, no. 4
• Strony: 941--965
• Opis fizyczny: Bibliogr. 89 poz., rys., tab., wykr.

Twórcy

autor

Rafati M.

• Department of Medical Physics and Radiology, Faculty of Paramedicine, Kashan University of Medical Sciences, Kashan, Iran

autor

Farnia F.

• Department of Medical Physics and Radiology, Faculty of Paramedicine, Kashan University of Medical Sciences, Kashan, Iran

autor

Taghvaei M. E.

• Department of Dentistry, Kashan University of Medical Sciences, Kashan, Iran

autor

Nickfarjam A. M.

• Department of Computer Engineering, Faculty of Electrical and Computer Engineering, University of Kashan, Kashan, Iran

Bibliografia

• [1] Chikhalekar AT. Analysis of image processing for digital X-ray. Int Res Eng Technol 2016;3:1364–8.
• [2] Yousif Abdallah YM, Almoustafa AA, Elhadi G, Mohammed M, Khalafallah O, Khalid T. Application of analysis approach in noise estimation in panoramic X-rays images using image processing program (Matlab). Can J Med 2011;2:38–48.
• [3] Yousif Abdallah YM, Abdelwahab RI. Improvement of orthopantography (OPG) images using texture analysis. Int J Sci Res 2014;3:1771–5.
• [4] Sindu YU, Ravikiran A, Swamy RR, Nayyar AS, Kartheek B. Digital panoramic radiography: an aid in the early detection of Osteoporotic signs. Arch Med Health Sci 2017;37:205–11.
• [5] Malhotra A, Kumar EAD. Image denoising with various filtering techniques. Int J Adv Res Comput Sci Technol 2015;3:129–31.
• [6] Mredula L, Dorairangaswamy MA. An extensive review of significant researches on medical image denoising technique. Int J Comput Appl 2013;64:1–12.
• [7] Thakur KV, Damodare OH, Sapkal AM. Poisson noise reducing bilateral filter. Procedia Comput Sci 2016;79:861–5.
• [8] Kumar N, Nachamai M. Noise removal and filtering techniques used in medical images. Orient J Comput Sci Technol 2017;10:103–13.
• [9] Das S, Saikia J, Das S, Goni N. A comparative study different noise filtering techniques in digital images. Int J Eng Gen Sci 2015;3:180–90.
• [10] Sutha S, Leavline EJ, Singh DAAG. A comprehensive study on wavelet based shrinkage methods for denoising natural images. WSEAS Trans Signal Process 2013;9:203–15.
• [11] Khosravi MH, Hassanpour H. Image denoising using anisotropic equations on reflection and illustration components of image. Int J Eng 2014;27:1339–48.
• [12] Figueiredo MAT, Oliveira DJP, Nowak RD. On total variation denoising: a new majorization-minimization algorithm and experimental comparison with wavelet denoising. IEEE International Conference on Image Processing. 2006. pp. 2633–6.
• [13] Chan TF, Osher S, Shen J. The digital TV filter and nonlinear denoising. IEEE Trans Image Process 2001;10:231–41.
• [14] Deledalle CA, Tupin F, Denis L. Poisson NL means: Unsupervised nonlocal means for Poisson noise. Proceedings of 2010 IEEE 17th International Conference on Image Processing; 2010. p. 26–9.
• [15] Dabov K, Foi A, Katkovonik V, Egiazarian K. Image denoising with block-matching and 3D filtering. Proceedings of SPIE Electronic Imaging, 2006:06, no. 6064A-30, San Jose, California, USA; 2006.
• [16] Makitalo M, Foi A. Optimal inversion of generalized Anscombe transform for Poisson-Gaussian noise. IEEE Trans Image Process 2013;22:91–103.
• [17] Wang L, Lu J, Li Y, Yahagi T, Okamoto T. Noise removal for medical X-ray images in wavelet domain. Electr Eng Jpn 2008;163:37–46.
• [18] Subbuthai P, Kavithabharathi K, Muruanand S. Reduction of types of noises in dental images. Int J Comput Appl Technol Res 2013;2:436–42.
• [19] Du L, Wen Y, Ma J. Dual tree complex wavelet transform and Bayesian estimation based denoising of Poisson-corrupted X-ray images. Fourth International Conference on Intelligent Processing (ICICIP), June 9–11, 2013, Beijing, China; 2013.
• [20] Jisha JU, Sureshkumar V. Poisson noise removal in biomedical images using non-linear techniques. Int J Adv Res Electr Electron Instrum Eng 2014;3:131–6.
• [21] Ghaheri A, Shoar S, Naderan M, Hoseini SS. The applications of genetic algorithms in medicine. Oman Med J 2015;30:406–16.
• [22] Boyat AK, Joshi BK. Noise models in digital image processing. Signal Image Process 2015;6:63–75.
• [23] Li Y, Lu J, Wang L, Yahagi T. Noise removal for degraded images with Poisson noise using M-transformation and Bayes shrink method. Electr Eng Jpn 2007;90:503–12.
• [24] Vijayalakshmi A, Titus C, Lilly Beaulah H. Image denoising for different noise models by various filters: a brief survey. Int J Emerg Trends Technol Comput Sci 2014;3:42–5.
• [25] Thamotharan B, Menaka M, Vaidyanathan S, Ravikumar S. Survey on image processing in the field of denoising techniques edge detection techniques on radiographic images. J Theor Appl Inf Technol 2012;41:26–34.
• [26] Jacop RMR, Prabakar S, Porkumaran K. Fetal cardiac structure detection from ultrasound sequences. Int J Instrum Autom 2013;2:12–6.
• [27] Deepa P, Suganthi M. Performance evaluation of various denoising filters for medical image. Int J Comput Sci Inf Technol 2014;5:4205–9.
• [28] Shumulevich I, Arce GR. Spectral design of weighted median filters admitting negative weights. IEEE Signal Process Lett 2001;8:313–6.
• [29] Soni T, Rathor N. Removal of high density impulse noise use efficient median filter for digital image. Int J Comput Appl 2015;115:25–31.
• [30] Sami I, Thakur A, Kumar R. Image denoising for Gaussian noise reduction in bionics using DWT technique. Int J Electron Commun Technol 2013;4:62–7.
• [31] Chhabra T, Dua G, Malhotra T. Comparative analysis of methods to denoise CT scan images. Int J Adv Res Electr Electron Instrum Eng 2013;2:3363–9.
• [32] Hafizah WM, Supriyanto E. Comparative evaluation of ultrasound kidney image enhancement techniques. Int J Comput Appl 2011;21:15–9.
• [33] Ojha A, Tiwari N. A study on image denoising with its techniques and types of noise. Int J Adv Res Appl Sci Eng Technol 2015;3:455–61.
• [34] Kumbhakarna V, Patil VR, Kawathekar S. Review on Speckle noise reduction techniques for medical ultrasound image processing. Int J Comput Tech 2015;2:24–7.
• [35] Rafati M, Arabfard M, Rafati Rahimzadeh M, Maghsoudloo M. Assessment of noise reduction in ultrasound of common carotid and brachial arteries. IET Comput Vis 2016;10:1–8.
• [36] Sulochana S, Vidhya R, Vijayasekaran D, Mohanraj K. Denoising and dimensionality reduction of hyperspectral images using framelet with different shrinkage functions. Indian J Geo-Marine Sci 2016;45:978–86.
• [37] Rai RK, Asnani J, Sontakke TR. Review of shrinkage techniques for image denoising. Int J Comput Appl 2012;42:13–6.
• [38] Sivakumar R, Gayathri MK, Nedumaran D. Speckle filtering of ultrasound B-mode images – a comparative study single scale spatial adaptive filters, multiscale filter and diffusion filters. Int J Eng Technol 2010;2:514–23.
• [39] Khmag A, Ramli AR, Hashim SJ, Al-Haddad SAR. Review of image denoising algorithms based on the wavelet transformation. Int J Adv Trends Comput Sci Eng 2013;2:1–7.
• [40] Jansen M, Uytterhoeven G, Bultheel A. Image de-noising by integer wavelet transforms and generalized cross validation. Med Phys 1999;26:622–30.
• [41] Geethalakshmi SN, Sugunia J. Hybrid models for denoising ultrasonic images. J Global Res Comput Sci 2010;1:38–45.
• [42] You YL, Kaveh M. Fourth-order partial differential equations for noise removal. IEEE Trans Image Process 2000;9:1723–30.
• [43] Nikpour M, Hassanpour H. Using diffusion equations for improving performance of wavelet-based image denoising techniques. IET Image Process 2010;4:452–62.
• [44] Khanian M, Feizi A, Davari A. An optimal partial differential equations-based stopping criterion for medical denoising. J Med Signals Sens 2014;4:72–83.
• [45] Nadernejad E, Koohi H, Hassanpour H. PDEs-based method for image enhancement. Appl Math Sci 2008;2:981–93.
• [46] Hajiaboli MR. An anisotropic fourth-order diffusion filter for image noise removal. Int J Comput Vis 2011;92:177–91.
• [47] Rudin LI, Osher S, Fatemi E. Nonlinear total variation based noise removal algorithms. Physica D 1999;60:259–68.
• [48] Zhang Y, Cheng HD, Chen Y, Huang J. A novel noise removal method based on fractional anisotropic diffusion and subpixel approach. New Math Nat Comput 2011;1:173–85.
• [49] Kittisuwan P. Medical image denoising using simple form of MMSE estimation in Poisson-Gaussian noise model. Int J Biomath 2016;9:1–9. http://dx.doi.org/10.1142/S1793524516500200.
• [50] Frasio I, Oliveira C, Lucchese M, Borghese NA, Boccacci P. Bayesian denoising in digital radiography: a comparison in the dental field. Comput Med Imaging Graph 2013;37:28–39.
• [51] Al Shalabi L, Shaaban Z, Kasasbeh B. Data mining: a preprocessing engine. J Comput Sci 2006;9:735–9.
• [52] Rosenfeld A, Pealtz JL. Sequential operations in digital picture processing. J Assoc Comput Mach 1966;13:471–97.
• [53] Darmanayagam SE, Harichandran KN, Cyril SRR, Arputharaj K. A novel supervised approach for segmentation of lung parenchyma from chest CT for computer-aided diagnosis. J Digit Imaging 2013;26:496–509.
• [54] Choukri D, Mehdi A. A new predictive approach to variables selection through genetic algorithm and fuzzy adaptive resonance theory using medical diagnosis as a case. The 8th International Conference on Ambient Systems, Networks and Technologies (ANT2017). 2017. pp. 448–57.
• [55] Kaushik D, Singh U, Singhal P, Singh V. Medical image segmentation using genetic algorithm. Int J Comput Appl 2013;81:10–5.
• [56] Hole KR, Gulhane VS, Shellokar ND. Application of Genetic algorithm for image enhancement and segmentation. Int J Adv Res Comput Eng Technol 2013;2:1342–6.
• [57] Girish C, Ferat S. A survey on feature selection methods. Comput Electr Eng 2014;40:16–28.
• [58] Canny J. A computational approach to edge detection. IEEE Trans Pattern Anal Mach Intell 1986;8:679–98.
• [59] Abo-Zahhad M, Gharieb RR, Ahmad SM, Donkol AAE. Edge detection with a preprocessing approach. J Signal Inf Process 2014;5:123–34.
• [60] Rafati M, Arabfard M, Rafati-Rahimzadeh M. Comparison of different edge detections and noise reduction on ultrasound images of carotid and brachial arteries using a speckle reducing anisotropic diffusion filter. Iran Red Crescent Med J 2014;16:1–9. http://dx.doi.org/10.5812/ircmj.e14658.
• [61] Frasio I, Borghese NA. Statistical based impulsive noise removal in digital radiography. IEEE Trans Med Imaging 2009;28:1–16.
• [62] Eftekhari Moghadam A, Mardani M, Hasanzadeh H, Rafati M. Assessment of absorbed dose in critical organs in OPG: a phantom study. J Paramed Sci 2015;6:44–9.
• [63] Rafati M, Arabfard M, Rafati Rahimzadeh M, Voshtani H, Moladoust H. A comparison study of three speckle reducing methods for intima-media thickness ultrasound images. Iran Red Crescent Med J 2015;17:1–8. http://dx.doi.org/10.5812/ircmj.e2513.
• [64] Sivakumar R, Gayathri MK, Nedumaran D. Speckle filtering of ultrasound B-mode images – a comparative study single scale spatial adaptive filters, multiscale filter and diffusion filters. Int J Eng Technol 2010;2:514–23.
• [65] Kumar N, Kumar S. Image quality assessment techniques. Int J Adv Res Comput Sci Softw Eng 2013;3:636–40.
• [66] Varan CS, Jagan A, Kaur J, Jyoti D, Rao DS. Image quality assessment techniques pn spatial domain. Int J Comput Sci Technol 2011;2:177–84.
• [67] Wang Z, Sheik HR, Bovik AC. No-reference perceptual quality assessment of JPEG compressed images. Proc ICIPo2, vol. 1. 2002;p. 477–80.
• [68] Available at: http://sipi.usc.edu/database/database.php.
• [69] Available at: http://www.o.ntust.edu.tw/cweiwang/ISBI2015.
• [70] Wang CW, Huang CT, Lee JH, Li CH, Chang SW, Siao MJ, et al. A benchmark for comparison of dental radiography analysis algorithms. Med Image Anal 2016;31:63–76.
• [71] Chugh T, Jain AK, Jaiswal RK, Mehrota P, Mehrotra R. Bone density and its importance in orthodontics. J Oral Craniofac Res 2013;3:92–7.
• [72] Govindraju P, Chandra P. Radiomorphometric indices of mandible – an indicator of osteoporosis. J Clin Diagn Res 2014;8:195–8.
• [73] Le T, Chartrand R, Asaki TJ. A variation approach to reconstructing images corrupted by Poisson noise. J Math Imaging Vis 2007. http://dx.doi.org/10.1007/s10851-007-0652-y.
• [74] Shruthi G, Usha BS, Sandya S. A novel approach for Speckle reduction and enhancement for ultrasound images. Int J Comput Appl 2012;45:14–20.
• [75] Saxena C, Kourav D. Noises and image denoising techniques: a brief survey. Int J Emerg Technol Adv Eng 2014;4:878–85.
• [76] Karthikeyan K, Chandrasekar C. Speckle noise reduction of medical ultrasound images using Bayesshrink wavelet threshold. Int J Comput Appl 2011;22:8–14.
• [77] Rajan J, Kannan K, Kaimal MR. An improved hybrid model for molecular image denoising. J Math Imaging Vis 2008;31:73–9.
• [78] Strong D, Chan T. Edge-preserving and scale-dependent properties of total variation regularization. Inverse Probl 2003;19:165–87.
• [79] Raj VNP, Venkateswarlu T. Denoising of medical images using total variation method. Signal Image Process 2012;3:131–42.
• [80] Khursheed S, Khaliq AA, Malik SA, Shah JA, Khan S. Poisson noise removal using wavelet transform. Sci Int (Lahore) 2014;27:287–92.
• [81] Avhad S, Patil RA. Denoising techniques for biomedical images. Int J Eng Res Gen Sci 2016;4:706–10.
• [82] Beg AH, Islam MZ. Advantages and limitation of genetic algorithms for clustering records. IEEE 11th conference on Industrial Electronics and Applications. 2016. pp. 2478–83.
• [83] Foi A, Trimeche M, Katkovonik V, Egiazarian K. Practical Poissonian-Gaussian noise modeling and fitting for single-image raw-data. IEEE Trans Image Process 2008;17:1737–54.
• [84] Luisier F, Blu T, Unser M. Image denoising in mixed Poisson-Gaussian noise. IEEE Trans Image Process 2011;20:696–708.
• [85] Bansal B, Saini JS, Bansal V, Kaur G. Comparison of various edge detection techniques. J Inf Oper Manag 2012;3:103–6.
• [86] Makitalo M, Foi A. Optimal inversion of the Anscombe transformation in low-count Poisson image denoising. IEEE Int Trans Image Process 2010;20:99–108.
• [87] Hessenian S, Arefi H. Assessment of restoration methods of X-ray images with emphasis on medical photogrammetric usage. Int Arch Photogramm Remote Sens Spat Inf Sci 2016; XLi-B5:835–40.
• [88] Borges LR, de Oliveira HCR, Nunes PF, Bakic PR, Maidment ADA, Vieira MAC. Method for simulating dose reduction in digital mammography using the Anscombe transformation. Med Phys 2016;43:2704–14.
• [89] Fan Z, Sun Q, Ji Z, Ruan F, Zhao L. An image filter arithmetic based on GA, PDE, and TV. Int J Future Gen Commun Netw 2013;6:147–56.