|
1.IntroductionOptical coherence tomography (OCT) is a recently created imaging technique to illustrate different information about the internal structures of an object. As in ultrasound imaging, OCT is based on interferometric techniques, except that OCT uses light beams instead of sound profiles.1 Use of OCT images is more popular in the field of ophthalmology, where it has become a key diagnostic technology in the areas of retinal diseases.2 OCT images usually suffer from speckle noise, which restricts the ability of image interpretation. Hence, noise reduction techniques are an essential process for these images. In a wide division, OCT denoising methods can be classified into two basic groups: methods that reduce the noise by some modifications on OCT device imaging such as Refs. 3 and 4 (based on hardware) and the methods that work on the recorded data (based on software). Because of our limitation in access to hardware of devices, we focus more on the second group of denoising methods. Based on our categorization in Ref. 5, these methods can be applied on the spatial or transform domain. For reducing noise in OCT images in the spatial domain, usually some simple methods like low-pass filters, linear smoothing, mean, median, and Wiener filters are used. However, some developed methods like multiple uncorrelated B-scan averaging,6,7 nonlinear anisotropic filter,8,9 complex diffusion,10,11 directional filtering,12,13 adaptive vector-valued kernel function,14 support vector machine approach,15 and Bayesian estimations16 are also applied in the spatial domain. In the transform based group, some data adaptive methods like principle component analysis;17 dictionary learning;18,19 some nondata adaptive methods that are based on wavelets,20,21 dual-tree complex wavelet transform22,23 or curvelets;24,25 and a circular symmetric Laplacian mixture model in wavelet diffusion26 have been applied for denoising. Recently, some groups of investigators27 improved the result of denoising by combining dictionary learning and wavelet thresholding and by defining a proper data-dependent initial dictionary. In another point of view, the denoising problem may be solved in a deterministic or statistical framework.23 In the first framework, each pixel is considered an unknown deterministic variable, and non-Bayesian techniques are used for denoising. In the statistical framework, a random field is employed to model the data, and Bayesian methods are applied to estimate noise-free data. Thus, finding a suitable prior probability distribution function (pdf) for noise-free data plays an important role in the denoising problem.23 Although there is a large body of work on OCT image analysis, few studies have been done on OCT images from a statistical modeling point of view. One of these studies is the work of Grzywacz et al.28 in which a probability model for OCT data was suggested and used for early detection of diabetic retinopathy. The denoising method that is proposed in this paper is the second type (statistical framework), so it first needs to obtain an appropriate statistical model for OCT images. Another issue is that assumption of the Gaussianity plays a key role in many signal processing methods. For example, a Wiener filter is a linear minimum-mean-square error filter in which the observed and noise-free data are jointly Gaussian. It is proven that, for a Gaussian process, nonlinear filters do not lead to better results compared with a Wiener filter. However, sometimes researchers use this Wiener filtering method without considering this Gaussianity assumption, so they cannot fully benefit from the ability of the algorithm. In this paper, it is illustrated that holding this assumption has a notable effect on the denoising results. Therefore, in this work, a Gaussianization transform (GT) that maps the original distribution of the OCT data to Gaussian components is introduced, and, with this transform, all of the good characteristics of the Gaussian process can be used. In the rest of the paper, a powerful patch-based denoising method, namely the spatially constrained Gaussian mixture model (SC-GMM), is first explained in Sec. 2.1. Since SC-GMM is based on the Gaussian distribution assumption of noise-free data, which is not satisfied for OCT images, in Sec. 2.2 GT is applied on OCT data. By applying GT, the distribution of transformed OCT data is expressed by a combination of Gaussian pdfs. In this base, the proposed denoising method, which is a combination of Gaussianization and SC-GMM, is demonstrated in Sec. 2.3. The visual and numerical results of the proposed OCT denoising method are presented in Sec. 3, and Sec. 4 presents the discussion of our results in comparison with the state of the art methods. Finally, a summary of this paper is presented in Sec. 5. 2.MethodToday, patch-based image denoising methods are known as an effective way for denoising natural images.29–31 The proposed denoising method in this paper is also a patch-based technique; it is a modified version of the SC-GMM algorithm introduced by Niknejad et al.32 In Sec. 2.1, the SC-GMM method that is based on a Gaussian distribution assumption of similar image patches in a neighborhood is described. However, it is clear that this assumption is not satisfied for all kinds of datasets like OCT images. Thus, after investigation of the distribution of the original OCT image, it is necessary to convert it to a Gaussian distribution for which GT is used. These steps are explained in Sec. 2.2 and finally the proposed OCT denoising method, which is a combination of GT and SC-GMM, is introduced in Sec. 2.3. 2.1.SC-GMM Denoising MethodAs mentioned above, SC-GMM denoising is a patch-based method in which the whole of the image is partitioned into overlapping patches and it is assumed that each set of neighbor patches can be modeled using a multivariate Gaussian pdf with a specific mean vector and covariance matrix. For this purpose, some exemplar patches are uniformly chosen from the whole image; then, similar patches in the vicinity of each exemplar patch are grouped together to construct a region using the -nearest neighbors (KNN) algorithm. To determine these clusters of patches and estimate the parameters of Gaussian pdfs (covariance matrices and mean vectors), a two-step approach is applied.33 This estimation approach includes a clustering step and a denoising step. Assume is a noisy image, where is noise-free data and is an independent zero-mean Gaussian noise with known variance . Also, let denote the ’th exemplar patch with mean vector and covariance matrix for . After initialization, , the following steps are iteratively implemented: Clustering step. In this step, for each exemplar patch , KNN patches , , that have minimum dissimilarity (based on norm metric, i.e., ) with the exemplar patch are chosen. These and are estimated in the previous iteration or the initialization in the first step. Denoising step. The goal of this step is to restore the image using the clusters obtained in the clustering step. Thus, first the parameters of Gaussian distribution for each set of patches are estimated using the maximum likelihood method where shows the set of KNN patches in the ’th region. It should be noted that in our implementation the above sample covariance matrix is not invertible, so as with similar works,34 an eigenvalue regularization is applied using where is a small constant (here ) and is the identity matrix.After estimating the parameters of the Gaussian pdf, the denoised patch in the ’th region is found by maximizing a posteriori function , i.e., where is the corresponding noisy observed patch and Eq. (4) is derived from the assumption of the Gaussian pdf for noise-free patch and noise, i.e., and , respectively.By setting the derivative of Eq. (4) to zero, this optimization problem can be solved, which leads to the linear Wiener filter as follows: The last step for reconstructing the whole image is averaging the weighted restored patches. In this work, based on Ref. 32, these weights are considered proportional to similarity to Gaussian distributions. To be more explicit, patches that are more likely to be generated from the estimated Gaussian distribution of their allocated clusters benefit from higher weights. Thus, the weight of the patch in the ’th region is obtained by where is an appropriate scaling constant.Using these weights and averaging on all patches, the denoised image is found. Figure 1 shows the block diagram of the SC-GMM method for image denoising. 2.2.Gaussianization as a Preprocessing StepIn fact, the assumption of Gaussianity plays an important role in many signal processing methods. For example, in this work, the Gaussian distribution assumption for a dataset causes the derivation of the Wiener filter as an optimal linear filter for denoising. Thus, the best denoising result is reached when the initial assumption of Gaussianity is satisfied. However in Ref. 32 and other related works,34 holding this Gaussianity assumption for the pdf of data is not investigated, and here we demonstrate the importance of this assumption by converting the pdf of OCT intraretinal layers to Gaussian distribution and comparing denoising results with and without Gaussianization. For this purpose, the distribution of the OCT images should first be determined, and then an appropriate GT is designed to convert the OCT original distribution to a GMM and satisfy the initial assumption for our denoising algorithm. The block diagram of the Gaussianization process is displayed in Fig. 2. 2.2.1.OCT distribution estimationSince the speckle noise in the OCT images is a multiplicative noise and working with the additive noise is simpler and more common, first, a logarithm operator is used to convert this noise to an additive Gaussian noise. Thus, all the processes are implemented in the logarithmic domain. In Ref. 35, we discussed that, because of the layered structure of the retina, a mixture model can be well fitted to a whole OCT B-scan. Moreover, a monotonically decaying behavior of the OCT intensities in each layer means that leptokurtic distributions such as the Laplace pdf are good candidates for describing the statistical properties of layers.35 On the other hand, this image is corrupted with the additive white Gaussian noise in the logarithmic space, so an appropriate statistical model for an OCT image is a mixture distribution. Each component of this mixture model is composed of a Laplace random variable , plus a Gaussian noise . We called this model a normal-Laplace mixture (NLM) model and described it in detail in Ref. 35. Indeed, for each component of the mixture model, we would have , where the pdfs of and are shows the mean of the Laplace variable and and display the scaling parameters of the Laplace and Gaussian distributions, respectively. Since and the noise signal is assumed to be independent from the noise-free signal , the pdf of the normal-Laplace variable is given by the convolution After some mathematical computations, we have35 where .Thus, has a normal-Laplace distribution, and we show it by . Additionally, the pdf of the NLM model is presented by as follows: where is the pdf of each component, , , and is the number of mixture components. In Ref. 35, it has been shown that the choice of causes the best results.After finding a proper model, its parameters are estimated based on a used dataset. The EM algorithm36 is used to estimate parameters iteratively as follows:
In the M-step, the updated equations for are approximately estimated as37 where is a small positive constant number used to avoid numerical errors.2.2.2.Gaussianization transformAs mentioned before, SC-GMM has been designed based on Gaussianity assumption. However, the distribution of each OCT intraretinal layer can be modeled as a normal-Laplace pdf.35 Thus, if a GT is designed to map the original distribution to a Gaussian distribution, it is expected to obtain better denoising results. The core of this transform is solving the equation that compares the cumulative distribution function (CDF) of original dataset and Gaussian distribution. Assume expresses the CDF of a Gaussian variable () with and as the mean and standard deviation of , respectively, and . Also, by computing the integral of in Eq. (10), the CDF of a normal-Laplace variable is found as By equating these two CDFs, one can find an equation that expresses each value of variable in the initial distribution, in terms of the equivalent value of in Gaussian space where erfinv is the inverse of the error function.2.2.3.Construct a GMM distributionAfter Gaussianization, the distribution of each component of the NLM model, , , becomes Gaussian; by combining these Gaussian components, an image with the GMM pdf is constructed and can be used as the input of the SC-GMM denoising method. In Ref. 38, it is shown that the averaged maximum a posterior (AMAP) method is a suitable way for defining the weights of summation for mixture models. In this method, the weight of each component is defined as , so , as the Gaussianized image with GMM distribution, is obtained as follows: Also, in Ref. 39, it was discussed that instead of using the univariate weighting function , employing multivariate weighting function leads to better results. Thus, for an OCT image of size , a local window (where and are odd) is placed around each pixel for , ; and the multivariate function for the central pixel of window () is calculated by multiplying all univariate in that window i.e. Figure 3 shows how the multivariate function is produced. Hence, Eq. (18) is replaced with 2.3.Proposed Denoising MethodAccording to Secs. 2.2.1 and 2.2.2, our proposed OCT denoising method is obtained by combining GT and the SC-GMM method as shown in Fig. 4. In this method, the OCT image in the log domain is first Gaussianized using the block diagram of Fig. 2, and then the Gaussianized image is denoised by the SC-GMM method using the block diagram of Fig. 1. Fig. 4Block diagram of the proposed combined denoising method, in this figure, third block “GT” includes all the blocks in Fig. 2 (except the Log block) and fourth block “SC-GMM denoising method” is equivalent to the block diagram of Fig. 1. ![]() The proposed denoising algorithm can be summarized in the following steps:
3.ResultsIn this section, some simulation results performed on our dataset are presented. This dataset consists of thirteen three-dimensional (3-D) macular spectral domain OCT images obtained from eyes without pathologies using a Topcon 3DOCT-1000 imaging system in the Ophthalmology Department of Feiz Hospital, Isfahan, Iran. The , , size of the obtained volumes was , , voxel size . From this dataset, 130 B-scans were selected randomly (10 B-scans from each subject), and these randomly selected B-scans were denoised with the methods described previously in the paper: once images were denoised only using the SC-GMM method and they were then despeckled by a combination of GT and the SC-GMM according to our method. Considering the constant values and parameters, for each region, nearest neighbor patches were accumulated. The exemplar patches were selected every 10 pixels along both the column and row directions of the image. The size of the constraining window around each exemplar patch was set to , and the size of patches was selected as . Also, the size of local window around each pixel for obtaining multivariate was . All of these values were selected based on previous related work and our implementation experiences. Both the qualitative and quantitative performance of the proposed combined method and SC-GMM were provided. The results of denoising with a simple Wiener filter was also prepared to compare with the proposed approach and prove the need and benefit of GT in the proposed method. Contrast to noise ratio (CNR), edge preservation (EP), and texture preservation (TP) as quantitative measures were computed for each denoising method. The mentioned values were computed based on methods discussed in Ref. 40, and regions for analysis of each criterion are shown in Fig. 5. Fig. 5Selected ROIs for calculation of CNR, EP, and TP. The larger elliptical region outside the retinal layers is used as background ROI and other circles represent foreground ROIs for CNR calculation. Rectangular ROIs are used for TP and EP. ![]() CNR measures the contrast between a feature of interest and background noise. EP computes the correlation between edges in the denoised image and the noisy image over the locally selected region of interest (ROI). TP shows the degree of preserving texture in an ROI. Both the TP and EP measures range between 0 and 1 and, in the best condition, go to 1. In addition, to illustrate the power of the proposed method, its ability in OCT denoising was compared with the BM3D as a benchmark denoising algorithm and recently reported state-of-the-art algorithm in this field.27 Kafieh et al.27 proposed a strong method in speckle reduction of OCT datasets in two-dimensional and 3-D by the combination of dictionary learning and wavelet thresholding. They improved the performance of simple dual-tree complex wavelets by taking advantage of adaptability in dictionary learning methods and introducing complex wavelet-based K-SVD. They also compared their algorithm by other previous outstanding researches in this filed like Fang et al.,18 Yang et al.,41, and Luan and Wu17 and demonstrated the superiority of their method. Thus, this complex wavelet-based K-SVD method (3DCWT-KSVD)27 is chosen as a proper reference to evaluate our proposed method. Figures 6 and 7 show some samples of datasets after application of each one of the mentioned denoising methods (simple Wiener, SC-GMM, 3DCWT-KSVD, BM3D, and the proposed method). Also, the value of the quantitative measurements for each denoising method on all randomly selected slices is summarized in Table 1. Furthermore, to have a comparison between time complexity of the evaluated denoising methods, the mean of the needed computation time for each slice on a PC with Microsoft Windows X32 edition, Intel core2 Duo CPU at 3.00 GHz, 4 GB RAM is reported in Table 1. Fig. 6Denoising results in a sample B-scan. The second and third columns show an enlargement of the specified regions of first column images. (a), (g), (m) Original noisy image; (b), (h), (n) simple Wiener; (c), (i), (o) SC-GMM; (d), (j), (p) BM3D; (e), (k), (q) 3DCWT-KSVD; (f), (l), (r) proposed method. ![]() Fig. 7Denoising results in a sample B-scan. The second and third columns show an enlargement of the specified regions of first column images. (a), (g), (m) Original noisy image; (b), (h), (n) simple Wiener; (c), (i), (o) SC-GMM; (d), (j), (p) BM3D; (e), (k), (q) 3DCWT-KSVD; and (f), (l), (r) proposed method. ![]() Table 1Evaluation measure results; averaged over 130 OCT B-scans from the Topcon device.
Before analyzing the results of Table 1, it should be noted that visual results of a simple Wiener filter (like those shown in Figs. 6 and 7) indicate the weakness of it in OCT image denoising, and the high value of TP and EP for the Wiener filter in Table 1 is because of the definition of these two measures in which the similarity of the denoised image to the original one plays an important role. However, the low value of CNR for the Wiener filter emphasizes the weakness of this denoising method. Regarding the other mentioned denoising algorithms, according to Table 1, the performance of the proposed method is considerably better than the other methods in TP, which is obviously visible in Figs. 6 and 7. Performance of all of the studied methods is close to each other in EP, and the SC-GMM has the highest EP, which is obtained because of the least difference appearing in the resulting image visually. However, it cannot be considered a positive point lonely, since the values of CNR and TP for this method are very low and indeed this method does not show the proper features as a powerful method for OCT denoising. Regarding the CNR measure, the proposed method and 3DCWT-KSVD have remarkably better results than others. Although 3DCWT-KSVD has the highest CNR among all studied methods, it cannot be the winner in this denoising competition because of its weak results in TP and EP; visual results in Figs. 6 and 7 also confirm this matter. 4.DiscussionThe main objective of this paper is to prove the effect of Gaussianization in the result of the OCT denoising by a Wiener-based denoising method. As our results in Table 1 and Figs. 6 and 7 show, it is obviously clear that using the proposed combined method has been much more successful than the SC-GMM method, which assumes Gaussianity for the noise-free image without any justification for proposing this assumption on OCT datasets. Our second goal in this work is to generally propose a significant method for OCT denoising. To investigate the power of the proposed method, a comparison with the 3DCWT-KSVD algorithm as a recent state of the art in this field and BM3D as a powerful denoising method was done. Visual results in Figs. 6 and 7 demonstrate better noise reduction using the proposed method while desired textural features are preserved simultaneously. Also, in Table 1, this matter is emphasized by checking the high value of TP in the proposed method compared with the 3DCWT-KSVD and BM3D algorithms. Regarding the CNR measures, 3DCWT-KSVD could provide higher CNR because of the very good speckle removing in the background area, but it does not mean that this method is better for next OCT processing because the main goal behind the OCT denoising is providing an appropriate dataset for the next OCT processing, such as layer segmentation42 or lesions identification, while the denoised image obtained by the 3DCWT-KSVD method does not show this ability very well. To demonstrate this superiority in our proposed method, A-scans of each denoised image were analyzed because many OCT segmentation methods perform based on gradient information from B-scans or analysis of A-scans in OCT datasets.43 The high level of speckle noise in the original noisy OCT image does not allow features of the image to be detectable in segmentation processes; however, applying a good denoising algorithm that suppresses much of the speckle noise and preserves features of the image can provide more reliable segmentation. Figure 8 shows the ability of the proposed method to reduce the speckle noise and protect identifiable feature peaks and valleys. In fact, because of producing the clean and almost noiseless B-scan images in the proposed method [Fig. 8(f)], its A-scans obviously include a peak or valley for each layer of the retina, and the signal amplitude at the boundary layers can be greatly altered. In the other words, an important benefit of the proposed method is using contrast enhancement and denoising together. As depicted in our previous work,35 applying GT on OCT images leads to contrast enhancement of the image and combination of GT and SC-GMM is a proper algorithm for simultaneously denoising and contrast enhancement. Fig. 8The cross-section signal along the white solid line. (a) Original noisy image, (b) simple Wiener, (c) SC-GMM, (d) BM3D, (e) 3DCWT-KSVD, (f) proposed method. Red stars on the A-scans show the place of each of 12 boundaries of retinal layers. The name of these layers is ILM, internal limiting membrane; NFL, nerve fiber layer; GCL, ganglion cell layer; IPL, inner plexiform layer; INL, inner nuclear layer; OPL, outer plexiform layer; ONL, outer nuclear layer; IS, inner segment of rods and cones; CL, connecting cilia layer; OS, outer segment of rods and cones, RPE, retinal pigment epithelium, respectively, from top to down. RPE includes two surfaces and three last boundaries in our figures. Green indicators in (f) display some examples of the superiority of the proposed method in reducing the speckle noise and protecting identifiable feature peaks and valleys, compared with 3DCWT-KSVD [orange indicators in (e)]. ![]() Another way to evaluate the performance of the proposed method is by analyzing the intraretinal layer segmentation results. For this purpose, a diffusion map-based method introduced in Ref. 43 for OCT boundaries segmentation was used. This segmentation method was tested once on original OCT B-scans and another time on images denoised by each of the aforementioned denoising algorithms. For each case, the error values were calculated as the difference of computed layer position by a diffusion map segmentation method and manually labeled values by an expert observer. Tables 2 and 3 show the mean signed and unsigned border positioning errors for each boundary, which is obtained for 130 randomly selected B-scans from the Topcon dataset. The numbering of retinal surfaces in these tables is based on Fig. 8. Table 2Summary of mean signed border positioning errors on 12 boundaries from the Topcon dataset.
Table 3Summary of mean unsigned border positioning errors on 12 boundaries from the Topcon dataset.
Based on Tables 2 and 3, the proposed method seems superior to the other mentioned algorithms in the segmentation of some boundaries (8th to 12th boundaries). However, to illustrate the statistically significant improvement of the proposed method over the other algorithms, Table 4 shows the obtained -values. Based on Table 4, it can be seen that the 8th to 12th boundaries, which are more difficult to identify because of lack of contrast, are significantly better localized in the proposed method compared with the SC-GMM algorithm. Regarding the BM3D and 3DCWT-KSVD algorithms, this superiority is significant just for the 11th and 12th boundaries (-value ). Table 4Improvement of the proposed method compared with SC-GMM, BM3D, and 3DCWT-KSVD algorithm, on the 8th to 12th boundaries of retinal OCT.
Furthermore, given that the ultimate goal of all the works in the medical image processing field is to help physicians determine better and more accurate diagnosis and treatment of disease, ranking mentioned denoising methods by an expert was considered another acceptable criterion for evaluating our method. Accordingly, an ophthalmologist was asked to score the denoised images by each method (raw data, denoised images by SC-GMM, 3DCWT-KSVD, and the proposed method) between one and four; the score of one to four is assigned “best,” “very good,” “good,” and “worst,” respectively. This ranking was done on all 130 randomly selected B-scans (some sample images are illustrated in Figs. 6 and 7) and the average score on all B-scans for our method was 1.2846 (for 110 slices of all 130 B-scans, the proposed method achieved score one), while this value for raw images was 1.8538, for SC-GMM was 2.8231, and for 3DCWT-KSVD was 3.9615. Based on this result, the superiority of the proposed method in clinical applications is also obvious. Another noticeable issue is that in this research we worked on single-frame images provided by Topcon imaging system; hence the proposed method may become a useful step in OCT image processing approaches, where single frame detection is a must (where the data acquisition time or system restrictions do not allow for multiframe acquisition). However, to make a good judgment on the power of the method in general, it should be compared with results from a multiframe approach (as angular compounding for example), and hopefully this research can be used as a starting point for further and deeper discussions in this field in the OCT community. 5.ConclusionIn this paper, a developed denoising method for speckle reduction in OCT images was introduced. Our main issue was the effect of holding the assumptions in different statistical methods. Particularly, in this work, the employed denoising algorithm (SC-GMM) was based on the Wiener filter, and in this method both noise-free data and noise are assumed to be Gaussian; however, holding this assumption has not been investigated in previous research. Since OCT datasets do not satisfy this assumption and an NLM model is fitted on these datasets, a transform to Gaussianize each component of this mixture model was needed. After constructing an image underlying GMM, SC-GMM was used for denoising. The visual and numerical results show the superiority of this combined method and encourage us to compare the proposed method with BM3D and 3DCWT-KSVD algorithms as the state-of-the-art studies in this field. Indeed, the advantage of our method, in addition to appropriate noise reduction, is in preserving and highlighting the features of the image like textures and edges that provide a suitable dataset for the next OCT processing such as layer segmentation or object detection. This matter was demonstrated by investigating the behavior of A-scans in all mentioned denoising methods. In addition, the method was shown to improve segmentation accuracy of some intraretinal layers. Furthermore, as another way to prove the superiority of the proposed method in clinical applications, the result of ranking different methods by an ophthalmologist shows predominance of the proposed method. AcknowledgmentsThe authors would like to thank Dr. MR Akhlaghi from Feiz Eye Hospital for his contribution in clinical evaluation of denoising algorithms and Prof. Sina Farsiu from Duke Eye Center for his valuable comments for improving the technical content of this paper. ReferencesD. Huang et al.,
“Optical coherence tomography,”
Science, 254
(5035), 1178
–1181
(1991). http://dx.doi.org/10.1126/science.1957169 SCIEAS 0036-8075 Google Scholar
M. R. Hee et al.,
“Optical coherence tomography of the human retina,”
Arch. Ophthalmol., 113
(3), 325
–332
(1995). http://dx.doi.org/10.1001/archopht.1995.01100030081025 AROPAW 0003-9950 Google Scholar
M. Pircher et al.,
“Speckle reduction in optical coherence tomography by frequency compounding,”
J. Biomed. Opt., 8
(3), 565
–569
(2003). http://dx.doi.org/10.1117/1.1578087 JBOPFO 1083-3668 Google Scholar
B. F. Kennedy et al.,
“Speckle reduction in optical coherence tomography by strain compounding,”
Opt. Lett., 35
(14), 2445
–2447
(2010). http://dx.doi.org/10.1364/OL.35.002445 OPLEDP 0146-9592 Google Scholar
Z. Amini and H. Rabbani,
“Classification of medical image modeling methods: a review,”
Curr. Med. Imaging Rev., 12
(2), 130
–148
(2016). Google Scholar
T. M. Jørgensen et al.,
“Enhancing the signal-to-noise ratio in ophthalmic optical coherence tomography by image registration—method and clinical examples,”
J. Biomed. Opt., 12
(4), 041208
(2007). http://dx.doi.org/10.1117/1.2772879 JBOPFO 1083-3668 Google Scholar
D. Alonso-Caneiro, S. A. Read and M. J. Collins,
“Speckle reduction in optical coherence tomography imaging by affine-motion image registration,”
J. Biomed. Opt., 16
(11), 116027
(2011). http://dx.doi.org/10.1117/1.3652713 JBOPFO 1083-3668 Google Scholar
D. C. Fernández et al.,
“Comparing total macular volume changes measured by optical coherence tomography with retinal lesion volume estimated by active contours,”
Invest. Ophthalmol. Visual Sci., 45
(13), 3072
(2004). IOVSDA 0146-0404 Google Scholar
P. Puvanathasan and K. Bizheva,
“Interval type-II fuzzy anisotropic diffusion algorithm for speckle noise reduction in optical coherence tomography images,”
Opt. Express, 17
(2), 733
–746
(2009). http://dx.doi.org/10.1364/OE.17.000733 Google Scholar
R. Bernardes et al.,
“Improved adaptive complex diffusion despeckling filter,”
Opt. Express, 18
(23), 24048
–24059
(2010). http://dx.doi.org/10.1364/OE.18.024048 Google Scholar
H. M. Salinas and D. C. Fernández,
“Comparison of PDE-based nonlinear diffusion approaches for image enhancement and denoising in optical coherence tomography,”
IEEE Trans. Med. Imaging, 26
(6), 761
–771
(2007). http://dx.doi.org/10.1109/TMI.2006.887375 ITMID4 0278-0062 Google Scholar
A. M. Bagci et al.,
“Thickness profiles of retinal layers by optical coherence tomography image segmentation,”
Am. J. Ophthalmol., 146
(5), 679
–687.e1
(2008). http://dx.doi.org/10.1016/j.ajo.2008.06.010 Google Scholar
J. Rogowska and M. E. Brezinski,
“Evaluation of the adaptive speckle suppression filter for coronary optical coherence tomography imaging,”
IEEE Trans. Med. Imaging, 19
(12), 1261
–1266
(2000). http://dx.doi.org/10.1109/42.897820 Google Scholar
A. Mishra et al.,
“Intra-retinal layer segmentation in optical coherence tomography images,”
Opt. Express, 17
(26), 23719
–23728
(2009). http://dx.doi.org/10.1364/OE.17.023719 OPEXFF 1094-4087 Google Scholar
A. R. Fuller et al.,
“Segmentation of three-dimensional retinal image data,”
IEEE Trans. Visual Comput. Graphics, 13
(6), 1719
–1726
(2007). http://dx.doi.org/10.1109/TVCG.2007.70590 Google Scholar
A. Wong et al.,
“General Bayesian estimation for speckle noise reduction in optical coherence tomography retinal imagery,”
Opt. Express, 18
(8), 8338
–8352
(2010). http://dx.doi.org/10.1364/OE.18.008338 OPEXFF 1094-4087 Google Scholar
F. Luan and Y. Wu,
“Application of RPCA in optical coherence tomography for speckle noise reduction,”
Laser Phys. Lett., 10
(3), 035603
(2013). http://dx.doi.org/10.1088/1612-2011/10/3/035603 1612-2011 Google Scholar
L. Fang et al.,
“Sparsity based denoising of spectral domain optical coherence tomography images,”
Biomed. Opt. Express, 3
(5), 927
–942
(2012). http://dx.doi.org/10.1364/BOE.3.000927 BOEICL 2156-7085 Google Scholar
L. Fang et al.,
“Fast acquisition and reconstruction of optical coherence tomography images via sparse representation,”
IEEE Trans. Med. Imaging, 32
(11), 2034
–2049
(2013). http://dx.doi.org/10.1109/TMI.2013.2271904 ITMID4 0278-0062 Google Scholar
D. C. Adler, T. H. Ko and J. G. Fujimoto,
“Speckle reduction in optical coherence tomography images by use of a spatially adaptive wavelet filter,”
Opt. Lett., 29
(24), 2878
–2880
(2004). http://dx.doi.org/10.1364/OL.29.002878 OPLEDP 0146-9592 Google Scholar
V. Gupta et al.,
“Computerized automation of wavelet based denoising method to reduce speckle noise in OCT images,”
in Int. Conf. on Information Technology and Applications in Biomedicine (ITAB 2008),
(2008). http://dx.doi.org/10.1109/ITAB.2008.4570582 Google Scholar
M. A. Mayer et al.,
“Wavelet denoising of multiframe optical coherence tomography data,”
Biomed. Opt. Express, 3
(3), 572
–589
(2012). http://dx.doi.org/10.1364/BOE.3.000572 BOEICL 2156-7085 Google Scholar
H. Rabbani, M. Sonka and M. D. Abramoff,
“Optical coherence tomography noise reduction using anisotropic local bivariate Gaussian mixture prior in 3D complex wavelet domain,”
J. Biomed. Imaging, 2013 417491
(2013). http://dx.doi.org/10.1155/2013/417491 Google Scholar
Z. Jian et al.,
“Speckle attenuation in optical coherence tomography by curvelet shrinkage,”
Opt. Lett., 34
(10), 1516
–1518
(2009). http://dx.doi.org/10.1364/OL.34.001516 OPLEDP 0146-9592 Google Scholar
Z. Jian et al.,
“Three-dimensional speckle suppression in optical coherence tomography based on the curvelet transform,”
Opt. Express, 18
(2), 1024
–1032
(2010). http://dx.doi.org/10.1364/OE.18.001024 OPEXFF 1094-4087 Google Scholar
R. Kafieh et al.,
“Curvature correction of retinal OCTs using graph-based geometry detection,”
Phys. Med. Biol., 58
(9), 2925
–2938
(2013). http://dx.doi.org/10.1088/0031-9155/58/9/2925 PHMBA7 0031-9155 Google Scholar
R. Kafieh, H. Rabbani and I. Selesnick,
“Three dimensional data-driven multi scale atomic representation of optical coherence tomography,”
IEEE Trans. Med. Imaging, 34
(5), 1042
–1062
(2015). http://dx.doi.org/10.1109/TMI.2014.2374354 ITMID4 0278-0062 Google Scholar
N. M. Grzywacz et al.,
“Statistics of optical coherence tomography data from human retina,”
IEEE Trans. Med. Imaging, 29
(6), 1224
–1237
(2010). http://dx.doi.org/10.1109/TMI.2009.2038375 ITMID4 0278-0062 Google Scholar
A. Buades, B. Coll and J.-M. Morel,
“A non-local algorithm for image denoising,”
in IEEE Computer Society Conf. on Computer Vision and Pattern Recognition (CVPR 2005),
(2005). http://dx.doi.org/10.1109/CVPR.2005.38 Google Scholar
M. Elad and M. Aharon,
“Image denoising via sparse and redundant representations over learned dictionaries,”
IEEE Trans. Image Process., 15
(12), 3736
–3745
(2006). http://dx.doi.org/10.1109/TIP.2006.881969 IIPRE4 1057-7149 Google Scholar
K. Dabov et al.,
“Image denoising by sparse 3-D transform-domain collaborative filtering,”
IEEE Trans. Image Process., 16
(8), 2080
–2095
(2007). http://dx.doi.org/10.1109/TIP.2007.901238 IIPRE4 1057-7149 Google Scholar
M. Niknejad, H. Rabbani and M. Babaie-Zadeh,
“Image restoration using Gaussian mixture models with spatially constrained patch clustering,”
IEEE Trans. Image Process., 24
(11), 3624
–3636
(2015). http://dx.doi.org/10.1109/TIP.2015.2447836 IIPRE4 1057-7149 Google Scholar
X. Li,
“Exemplar-based EM-like image denoising via manifold reconstruction,”
in 17th IEEE Int. Conf. on Image Processing (ICIP 2010),
(2010). http://dx.doi.org/10.1109/ICIP.2010.5652529 Google Scholar
G. Yu, G. Sapiro and S. Mallat,
“Solving inverse problems with piecewise linear estimators: from Gaussian mixture models to structured sparsity,”
IEEE Trans. Image Process., 21
(5), 2481
–2499
(2012). http://dx.doi.org/10.1109/TIP.2011.2176743 IIPRE4 1057-7149 Google Scholar
Z. Amini and H. Rabbani,
“Statistical modeling of retinal optical coherent tomography,”
IEEE Trans. Med. Imaging, 35
(6), 1544
(2016). http://dx.doi.org/10.1109/TMI.2016.2519439 Google Scholar
A. P. Dempster, N. M. Laird and D. B. Rubin,
“Maximum likelihood from incomplete data via the EM algorithm,”
J. Royal Stat. Soc. Ser. B (Methodol.), 39
(1), 1
–38
(1977). Google Scholar
H. Rabbani et al.,
“Speckle noise reduction of medical ultrasound images in complex wavelet domain using mixture priors,”
IEEE Trans. Biomed. Eng., 55
(9), 2152
–2160
(2008). http://dx.doi.org/10.1109/TBME.2008.923140 IEBEAX 0018-9294 Google Scholar
H. Rabbani, M. Vafadust and S. Gazor,
“Image denoising based on a mixture of Laplace distributions with local parameters in complex wavelet domain,”
in IEEE Int. Conf. on Image Processing,
(2006). http://dx.doi.org/10.1109/ICIP.2006.313018 Google Scholar
H. Rabbani, R. Nezafat and S. Gazor,
“Wavelet-domain medical image denoising using bivariate Laplacian mixture model,”
IEEE Trans. Biomed. Eng., 56
(12), 2826
–2837
(2009). http://dx.doi.org/10.1109/TBME.2009.2028876 IEBEAX 0018-9294 Google Scholar
A. Pizurica et al.,
“Multiresolution denoising for optical coherence tomography: a review and evaluation,”
Curr. Med. Imaging Rev., 4
(4), 270
–284
(2008). http://dx.doi.org/10.2174/157340508786404044 Google Scholar
Q. Yang et al.,
“Automated layer segmentation of macular OCT images using dual-scale gradient information,”
Opt. Express, 18
(20), 21293
–21307
(2010). http://dx.doi.org/10.1364/OE.18.021293 OPEXFF 1094-4087 Google Scholar
L. Fang et al.,
“Segmentation based sparse reconstruction of optical coherence tomography images,”
IEEE Trans. Med. Imaging, 36
(2), 407
–421
(2016). http://dx.doi.org/10.1109/TMI.2016.2611503 Google Scholar
R. Kafieh et al.,
“Intra-retinal layer segmentation of 3D optical coherence tomography using coarse grained diffusion map,”
Med. Image Anal., 17
(8), 907
–928
(2013). http://dx.doi.org/10.1016/j.media.2013.05.006 Google Scholar
BiographyZahra Amini received her BSc degree from Isfahan University of Technology (IUT), Iran, in 2007, her MSc degree from the University of Yazd, Iran, in 2011, both in electrical engineering (communications), and her PhD in biomedical engineering from Isfahan University of Medical Sciences, Iran, in 2016. She is currently an assistant professor in the Department of Biomedical Engineering, School of Advanced Technologies in Medicine, Isfahan University of Medical Sciences. Her research interests include medical image modeling, signal and image processing, sparse transforms, and brain computer interface. Hossein Rabbani received his BSc degree in electrical engineering from Isfahan University of Technology in 2000 with the highest honors, and his MSc degree and PhD in bioelectrical engineering in 2002 and 2008, respectively, from Tehran Polytechnic. In 2007, he was at Queen’s University, as a visiting researcher; in 2011 at University of Iowa as a postdoctoral research scholar; and from 2013 to 2014 at Duke University Eye Center as a postdoctoral fellow. He is now senior member of IEEE and an associate professor in Biomedical Engineering Department and MISP Research Center, Isfahan University of Medical Sciences. His main research interests are medical image analysis and modeling, sparse transforms, and image restoration. He has published more than 110 papers as an author or coauthor in these areas. |