Document Type : Full Research Paper


1 Ph.D. Student, Bioelectric Department, Biomedical Engineering Faculty, Amirkabir University of Technology, Tehran, Iran

2 Assistant Professor, Bioelectric Department, Biomedical Engineering Faculty, Amirkabir University of Technology, Tehran, Iran

3 Associate Professor, Bioelectric Department, Biomedical Engineering Faculty, Amirkabir University of Technology, Tehran, Iran


Noise removal is one of the most important steps in digital image processing. Cone beam computed tomography (CBCT) is increasingly utilized in maxillofacial and dental imaging. Compared to conventional CT, CBCT images have diffrent noise and artifacts due to much less applied dose and their reconstruction algorithm. Therefore, the use of noise reduction techniques in these images is necessary to increase the signal-to-noise ratio. In this paper, the independent component analysis (ICA) method has been used to seperate noise from CBCT images and three different ICA algorithms, NG-FICA, ERICA and FastICA were investigated. In addition, two powerful noise reduction method, 2D discrete wavelet thresholding and optimized anisotropic diffusion filter is used to evaluate the results. Our proposed method has been validated on 12 different images in the presence of Gaussian and Spectral noise and the results are evaluated using processing time criteria, PSNR, MSE and SSIM. The results show that the ICA methods have advantage in noise reduction from CBCT images compared to the other noise reduction methods and among the three studied ICA algorithms, the NG-FICA algorithm has better performance in terms of processing time, preserving image quality and noise reduction.


Main Subjects

[1]   Chindasombatjaroen Jira, Naoya Kakimoto, Shumei Murakami, Yoshinobu Maeda, and Souhei Furukawa. "Quantitative analysis of metallic artifacts caused by dental metals: comparison of cone-beam and multi-detector row CT scanners." Oral Radiology 27, no. 2 (2011): 114-120.
[2]   Hatcher David C. "Operational principles for cone-beam computed tomography." The Journal of the american dental association 141 (2010): 3S-6S.
[3]   Feldkamp L. A., L. C. Davis, and J. W. Kress. "Practical cone-beam algorithm." JOSA A 1, no. 6 (1984): 612-619.
[4]   Chlewicki W., C. Badea, and N. Pallikarakis. "Cone based 3D reconstruction: a FDK-SART comparison for limited number of projections."Proc. MEDICON 2001 (Pula, Croatia, 12–15 June) (2001): 495-497.
[5]   Strid Karl-Gustav. "Significance of quantum fluctuations in roentgen imaging." Acta Radiologica: Oncology 19, no. 2 (1980): 129-138.
[6]   Schulze R., U. Heil, D. Groβ, D. D. Bruellmann, E. Dranischnikow, U. Schwanecke, and E. Schoemer. "Artefacts in CBCT: areview." Dentomaxillofacial Radiology (2014).
[7]   Altunbas M. C., C. C. Shaw, L. Chen, C. Lai, X. Liu, T. Han, and T. Wang. "A post-reconstruction method to correct cupping artifacts in cone beam breast computed tomography." Medical physics 34, no. 7 (2007): 3109-3118.
[8]   Tofts P. S., and J. C. Gore. "Some sources of artefact in computed tomography." Physics in medicine and biology 25, no. 1 (1980): 117.
[9]   Epp Edward R., and Herbert Weiss. "Experimental study of the photon energy spectrum of primary diagnostic x-rays." Physics in medicine and biology 11, no. 2 (1966): 225.
[10]De Man Bruno, Johan Nuyts, Patrick Dupont, Guy Marchal, and Paul Suetens. "Metal streak artifacts in X-ray computed tomography: a simulation study." IEEE Transactions on Nuclear Science 46, no. 3 (1999): 691-696.
[11]Siddon Robert L. "Fast calculation of the exact radiological path for a three‐dimensional CT array." Medical physics 12, no. 2 (1985): 252-255.
[12]De Man Bruno and Samit Basu. "Distance-driven projection and backprojection in three dimensions." Physics in medicine and biology 49, no. 11 (2004): 2463.
[13]Chen, Yen-Wei, Guifang Duan, Akinori Fujita, Ken Hirooka, and Yoshihiro Ueno. "Ring artifacts reduction in cone-beam CT images based on independent component analysis." In Instrumentation and Measurement Technology Conference, 2009. I2MTC'09. IEEE, pp. 1734-1737. IEEE, 2009.
[14]Kroon Dirk-Jan. "Segmentation of the mandibular canal in cone-beam CT data".   University of Twente [Host], 2011.
[15]مریم محسن زاده، على رفیعى، محسن معصومى،" ارائه روشى نوین در حذف نویز تصاویر MRI سه‌بعدی با استفاده از تابع ویولت مختلط درختى دوگانه"، اولین همایش ملى مهندسى برق و کامپیوتر در شمال کشور،1393.
[16]Shashi Jangra, Mr. Samit Yadav, "Rician Noise Reduction in MRI Images using Wave Atom Transform," Journal of Compute Science and Information Technology, vol. 3, no. 6, p. 215 – 222, 2014.
[17]Hyvärinen, Aapo, Juha Karhunen, and Erkki Oja. Independent component analysis. Vol. 46. John Wiley & Sons, 2004.
[18]سمیه اربابی، رضا قادری و عطالله ابراهیم­زاده، "جداسازی کور تصاویر ترکیبی اسکن شده، برمبنای پیش‌پردازش غیرخطی و اعمال تابع  رقابت مابین اجزا فرکانس بالا"، مجله علمی پژوهشی رایانش نرم و فناوری اطلاعات، جلد 1، شماره 1، 1391.
[19]Hyvärinen, Aapo. "Independent component analysis of images." Encyclopedia of Computational Neuroscience (2013): 1-5.
[20]Bingham, Ella, and Aapo Hyvärinen. "A fast fixed-point algorithm for independent component analysis of complex valued signals." International journal of neural systems 10.01 (2000): 1-8.
[21]Cruces, Sergio, Luis Castedo, and Andrzej Cichocki. "Robust blind source separation algorithms using cumulants." Neurocomputing 49.1 (2002): 87-118.
[22]Choi, Seungjin, Andrzej Cichocki, and Shun-Ichi Amari. "Flexible independent component analysis." Journal of VLSI signal processing systems for signal, image and video technology 26.1-2 (2000): 25-38.
[23]Weckx Annelies, Jimoh Olubanwo Agbaje, Yi Sun, Reinhilde Jacobs, and Constantinus Politis. "Visualization techniques of the inferior alveolar nerve (IAN): a narrative review." Surgical and Radiologic Anatomy 38, no. 1 (2016): 55-63.
[24]بهاره شالچیان، حسین رجبی، حمید سلطانیان­زاده. "کاهش نویز در تصاویر شبیه سازی شده PET با استفاده از تبدیل موجک"، مجله فیزیک پزشکی ایران، دوره 6، شماره 2، 1388.
[25]Sukhatme, Neelabh, and Shailja Shukla. "Independent Component Analysis based Denoising of Magnetic Resonance Images." International Journal of Computer Applications 54, no. 2 (2012).
[26]Thakur, Anita, et al. "CBCT image noise reduction and enhancement using Bi-Histogram method with bent activation function." Information Technology (InCITe)-The Next Generation IT Summit on the Theme-Internet of Things: Connect your Worlds, International Conference on. IEEE, 2016.
[27]Zhao, Shuyang, Jianwu Li, and Qirun Huo. "Removing Ring Artifacts in Cbct Images Via Generative Adversarial Network." 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2018.