Three-dimensional optical coherence tomography image denoising through multi-input fully-convolutional networks

Probabilistic volumetric speckle suppression in OCT using deep learning

We present a deep learning framework for volumetric speckle reduction in optical coherence tomography (OCT) based on a conditional generative adversarial network (cGAN) that leverages the volumetric nature of OCT data. In order to utilize the volumetric nature of OCT data, our network takes partial OCT volumes as input, resulting in artifact-free despeckled volumes that exhibit excellent speckle reduction and resolution preservation in all three dimensions. Furthermore, we address the ongoing challenge of generating ground truth data for supervised speckle suppression deep learning frameworks by using volumetric non-local means despeckling-TNode- to generate training data. We show that, while TNode processing is computationally demanding, it serves as a convenient, accessible gold-standard source for training data; our cGAN replicates efficient suppression of speckle while preserving tissue structures with dimensions approaching the system resolution of non-local means despeckling while being two orders of magnitude faster than TNode. We demonstrate fast, effective, and high-quality despeckling of the proposed network in different tissue types that are not part of the training. This was achieved with training data composed of just three OCT volumes and demonstrated in three different OCT systems. The open-source nature of our work facilitates re-training and deployment in any OCT system with an all-software implementation, working around the challenge of generating high-quality, speckle-free training data.

Tensor Ring Decomposition Guided Dictionary Learning for OCT Image Denoising

Optical coherence tomography (OCT) is a non-invasive and effective tool for the imaging of retinal tissue. However, the heavy speckle noise, resulting from multiple scattering of the light waves, obscures important morphological structures and impairs the clinical diagnosis of ocular diseases. In this paper, we propose a novel and powerful model known as tensor ring decomposition-guided dictionary learning (TRGDL) for OCT image denoising, which can simultaneously utilize two useful complementary priors, i.e., three-dimensional low-rank and sparsity priors, under a unified framework. Specifically, to effectively use the strong correlation between nearby OCT frames, we construct the OCT group tensors by extracting cubic patches from OCT images and clustering similar patches. Then, since each created OCT group tensor has a low-rank structure, to exploit spatial, non-local, and its temporal correlations in a balanced way, we enforce the TR decomposition model on each OCT group tensor. Next, to use the beneficial three-dimensional inter-group sparsity, we learn shared dictionaries in both spatial and temporal dimensions from all of the stacked OCT group tensors. Furthermore, we develop an effective algorithm to solve the resulting optimization problem by using two efficient optimization approaches, including proximal alternating minimization and the alternative direction method of multipliers. Finally, extensive experiments on OCT datasets from various imaging devices are conducted to prove the generality and usefulness of the proposed TRGDL model. Experimental simulation results show that the suggested TRGDL model outperforms state-of-the-art approaches for OCT image denoising both qualitatively and quantitatively.

Total variation regularized tensor ring decomposition for OCT image denoising and super-resolution

This paper suggests a novel hybrid tensor-ring (TR) decomposition and first-order tensor-based total variation (FOTTV) model, known as the TRFOTTV model, for super-resolution and noise suppression of optical coherence tomography (OCT) images. OCT imaging faces two fundamental problems undermining correct OCT-based diagnosis: significant noise levels and low sampling rates to speed up the capturing process. Inspired by the effectiveness of TR decomposition in analyzing complicated data structures, we suggest the TRFOTTV model for noise suppression and super-resolution of OCT images. Initially, we extract the nonlocal 3D patches from OCT data and group them to create a third-order low-rank tensor. Subsequently, using TR decomposition, we extract the correlations among all modes of the grouped OCT tensor. Finally, FOTTV is integrated into the TR model to enhance spatial smoothness in OCT images and conserve layer structures more effectively. The proximal alternating minimization and alternative direction method of multipliers are applied to solve the obtained optimization problem. The effectiveness of the suggested method is verified by four OCT datasets, demonstrating superior visual and numerical outcomes compared to state-of-the-art procedures.

Denoising of Optical Coherence Tomography Images in Ophthalmology Using Deep Learning: A Systematic Review

Imaging from optical coherence tomography (OCT) is widely used for detecting retinal diseases, localization of intra-retinal boundaries, etc. It is, however, degraded by speckle noise. Deep learning models can aid with denoising, allowing clinicians to clearly diagnose retinal diseases. Deep learning models can be considered as an end-to-end framework. We selected denoising studies that used deep learning models with retinal OCT imagery. Each study was quality-assessed through image quality metrics (including the peak signal-to-noise ratio-PSNR, contrast-to-noise ratio-CNR, and structural similarity index metric-SSIM). Meta-analysis could not be performed due to heterogeneity in the methods of the studies and measurements of their performance. Multiple databases (including Medline via PubMed, Google Scholar, Scopus, Embase) and a repository (ArXiv) were screened for publications published after 2010, without any limitation on language. From the 95 potential studies identified, a total of 41 were evaluated thoroughly. Fifty-four of these studies were excluded after full text assessment depending on whether deep learning (DL) was utilized or the dataset and results were not effectively explained. Numerous types of OCT images are mentioned in this review consisting of public retinal image datasets utilized purposefully for denoising OCT images (n = 37) and the Optic Nerve Head (ONH) (n = 4). A wide range of image quality metrics was used; PSNR and SNR that ranged between 8 and 156 dB. The minority of studies (n = 8) showed a low risk of bias in all domains. Studies utilizing ONH images produced either a PSNR or SNR value varying from 8.1 to 25.7 dB, and that of public retinal datasets was 26.4 to 158.6 dB. Further analysis on denoising models was not possible due to discrepancies in reporting that did not allow useful pooling. An increasing number of studies have investigated denoising retinal OCT images using deep learning, with a range of architectures being implemented. The reported increase in image quality metrics seems promising, while study and reporting quality are currently low.

Artifact Correction in Retinal Nerve Fiber Layer Thickness Maps Using Deep Learning and Its Clinical Utility in Glaucoma

Purpose

Correcting retinal nerve fiber layer thickness (RNFLT) artifacts in glaucoma with deep learning and evaluate its clinical usefulness.

Methods

We included 24,257 patients with optical coherence tomography and reliable visual field (VF) measurements within 30 days and 3,233 patients with reliable VF series of at least five measurements over ≥4 years. The artifacts are defined as RNFLT less than the known floor value of 50 µm. We selected 27,319 high-quality RNFLT maps with an artifact ratio (AR) of <2% as the ground truth. We created pseudo-artifacts from 21,722 low-quality RNFLT maps with AR of >5% and superimposed them on high-quality RNFLT maps to predict the artifact-free ground truth. We evaluated the impact of artifact correction on the structure-function relationship and progression forecasting.

Results

The mean absolute error and Pearson correlation of the artifact correction were 9.89 µm and 0.90 (P < 0.001), respectively. Artifact correction improved R2 for VF prediction in RNFLT maps with AR of >10% and AR of >20% up to 0.03 and 0.04 (P < 0.001), respectively. Artifact correction improved (P < 0.05) the AUC for progression prediction in RNFLT maps with AR of ≤10%, >10%, and >20%: (1) total deviation pointwise progression: 0.68 to 0.69, 0.62 to 0.63, and 0.62 to 0.64; and (2) mean deviation fast progression: 0.67 to 0.68, 0.54 to 0.60, and 0.45 to 0.56.

Conclusions

Artifact correction for RNFLTs improves VF and progression prediction in glaucoma.

Translational Relevance

Our model improves clinical usability of RNFLT maps with artifacts.

Deep learning segmentation of the tear fluid reservoir under the sclera lens in optical coherence tomography images

The tear fluid reservoir (TFR) under the sclera lens is a unique characteristic providing optical neutralization of any aberrations from corneal irregularities. Anterior segment optical coherence tomography (AS-OCT) has become an important imaging modality for sclera lens fitting and visual rehabilitation therapy in both optometry and ophthalmology. Herein, we aimed to investigate whether deep learning can be used to segment the TFR from healthy and keratoconus eyes, with irregular corneal surfaces, in OCT images. Using AS-OCT, a dataset of 31850 images from 52 healthy and 46 keratoconus eyes, during sclera lens wear, was obtained and labeled with our previously developed algorithm of semi-automatic segmentation. A custom-improved U-shape network architecture with a full-range multi-scale feature-enhanced module (FMFE-Unet) was designed and trained. A hybrid loss function was designed to focus training on the TFR, to tackle the class imbalance problem. The experiments on our database showed an IoU, precision, specificity, and recall of 0.9426, 0.9678, 0.9965, and 0.9731, respectively. Furthermore, FMFE-Unet was found to outperform the other two state-of-the-art methods and ablation models, suggesting its strength in segmenting the TFR under the sclera lens depicted on OCT images. The application of deep learning for TFR segmentation in OCT images provides a powerful tool to assess changes in the dynamic tear film under the sclera lens, improving the efficiency and accuracy of lens fitting, and thus supporting the promotion of sclera lenses in clinical practice.

Mixed multiscale BM4D for three-dimensional optical coherence tomography denoising

A multiscale extension for the well-known block matching and 4D filtering (BM4D) method is proposed by analyzing and extending the wavelet subbands denoising method in such a way that the proposed method avoids directly denoising detail subbands, which considerably simplifies the computations and makes the multiscale processing feasible in 3D. To this end, we first derive the multiscale construction method in 2D and propose multiscale extensions for three 2D natural image denoising methods. Then, the derivation is extended to 3D by proposing mixed multiscale BM4D (mmBM4D) for optical coherence tomography (OCT) image denoising. We tested mmBM4D on three public OCT datasets captured by various imaging devices. The experiments revealed that mmBM4D significantly outperforms its original counterpart and performs on par with the state-of-the-art OCT denoising methods. In terms of peak-signal-to-noise-ratio (PSNR), mmBM4D surpasses the original BM4D by more than 0.68 decibels over the first dataset. In the second and third datasets, significant improvements in the mean to standard deviation ratio, contrast to noise ratio, and equivalent number of looks were achieved. Furthermore, on the downstream task of retinal layer segmentation, the layer quality preservation of the compared OCT denoising methods is evaluated.

Multi-task generative adversarial network for retinal optical coherence tomography image denoising

Objective. Optical coherence tomography (OCT) has become an essential imaging modality for the assessment of ophthalmic diseases. However, speckle noise in OCT images obscures subtle but important morphological details and hampers its clinical applications. In this work, a novel multi-task generative adversarial network (MGAN) is proposed for retinal OCT image denoising.Approach. To strengthen the preservation of retinal structural information in the OCT denoising procedure, the proposed MGAN integrates adversarial learning and multi-task learning. Specifically, the generator of MGAN simultaneously undertakes two tasks, including the denoising task and the segmentation task. The segmentation task aims at the generation of the retinal segmentation map, which can guide the denoising task to focus on the retina-related region based on the retina-attention module. In doing so, the denoising task can enhance the attention to the retinal region and subsequently protect the structural detail based on the supervision of the structural similarity index measure loss.Main results. The proposed MGAN was evaluated and analyzed on three public OCT datasets. The qualitative and quantitative comparisons show that the MGAN method can achieve higher image quality, and is more effective in both speckle noise reduction and structural information preservation than previous denoising methods.Significance. We have presented a MGAN for retinal OCT image denoising. The proposed method provides an effective way to strengthen the preservation of structural information while suppressing speckle noise, and can promote the OCT applications in the clinical observation and diagnosis of retinopathy.

Convolutional Neural Network for Denoising Left Ventricle Magnetic Resonance Images

Medical image processing is critical in disease detection and prediction. For example, they locate lesions and measure an organ's morphological structures. Currently, cardiac magnetic resonance imaging (CMRI) plays an essential role in cardiac motion tracking and analyzing regional and global heart functions with high accuracy and reproducibility. Cardiac MRI datasets are images taken during the heart's cardiac cycles. These datasets require expert labeling to accurately recognize features and train neural networks to predict cardiac disease. Any erroneous prediction caused by image impairment will impact patients' diagnostic decisions. As a result, image preprocessing is used, including enhancement tools such as filtering and denoising. This paper introduces a denoising algorithm that uses a convolution neural network (CNN) to delineate left ventricle (LV) contours (endocardium and epicardium borders) from MRI images. With only a small amount of training data from the EMIDEC database, this network performs well for MRI image denoising.

Retinal optical coherence tomography image analysis by a restricted Boltzmann machine

Optical coherence tomography (OCT) is an emerging imaging technique for ophthalmic disease diagnosis. Two major problems in OCT image analysis are image enhancement and image segmentation. Deep learning methods have achieved excellent performance in image analysis. However, most of the deep learning-based image analysis models are supervised learning-based approaches and need a high volume of training data (e.g., reference clean images for image enhancement and accurate annotated images for segmentation). Moreover, acquiring reference clean images for OCT image enhancement and accurate annotation of the high volume of OCT images for segmentation is hard. So, it is difficult to extend these deep learning methods to the OCT image analysis. We propose an unsupervised learning-based approach for OCT image enhancement and abnormality segmentation, where the model can be trained without reference images. The image is reconstructed by Restricted Boltzmann Machine (RBM) by defining a target function and minimizing it. For OCT image enhancement, each image is independently learned by the RBM network and is eventually reconstructed. In the reconstruction phase, we use the ReLu function instead of the Sigmoid function. Reconstruction of images given by the RBM network leads to improved image contrast in comparison to other competitive methods in terms of contrast to noise ratio (CNR). For anomaly detection, hyper-reflective foci (HF) as one of the first signs in retinal OCTs of patients with diabetic macular edema (DME) are identified based on image reconstruction by RBM and post-processing by removing the HFs candidates outside the area between the first and the last retinal layers. Our anomaly detection method achieves a high ability to detect abnormalities.

Spatially adaptive blind deconvolution methods for optical coherence tomography

Optical coherence tomography (OCT) is a powerful noninvasive imaging technique for detecting microvascular abnormalities. Following optical imaging principles, an OCT image will be blurred in the out-of-focus domain. Digital deconvolution is a commonly used method for image deblurring. However, the accuracy of traditional digital deconvolution methods, e.g., the Richardson-Lucy method, depends on the prior knowledge of the point spread function (PSF), which varies with the imaging depth and is difficult to determine. In this paper, a spatially adaptive blind deconvolution framework is proposed for recovering clear OCT images from blurred images without a known PSF. First, a depth-dependent PSF is derived from the Gaussian beam model. Second, the blind deconvolution problem is formalized as a regularized energy minimization problem using the least squares method. Third, the clear image and imaging depth are simultaneously recovered from blurry images using an alternating optimization method. To improve the computational efficiency of the proposed method, an accelerated alternating optimization method is proposed based on the convolution theorem and Fourier transform. The proposed method is numerically implemented with various regularization terms, including total variation, Tikhonov, and l₁ norm terms. The proposed method is used to deblur synthetic and experimental OCT images. The influence of the regularization term on the deblurring performance is discussed. The results show that the proposed method can accurately deblur OCT images. The proposed acceleration method can significantly improve the computational efficiency of blind demodulation methods.

Real-time OCT image denoising using a self-fusion neural network

Optical coherence tomography (OCT) has become the gold standard for ophthalmic diagnostic imaging. However, clinical OCT image-quality is highly variable and limited visualization can introduce errors in the quantitative analysis of anatomic and pathologic features-of-interest. Frame-averaging is a standard method for improving image-quality, however, frame-averaging in the presence of bulk-motion can degrade lateral resolution and prolongs total acquisition time. We recently introduced a method called self-fusion, which reduces speckle noise and enhances OCT signal-to-noise ratio (SNR) by using similarity between from adjacent frames and is more robust to motion-artifacts than frame-averaging. However, since self-fusion is based on deformable registration, it is computationally expensive. In this study a convolutional neural network was implemented to offset the computational overhead of self-fusion and perform OCT denoising in real-time. The self-fusion network was pretrained to fuse 3 frames to achieve near video-rate frame-rates. Our results showed a clear gain in peak SNR in the self-fused images over both the raw and frame-averaged OCT B-scans. This approach delivers a fast and robust OCT denoising alternative to frame-averaging without the need for repeated image acquisition. Real-time self-fusion image enhancement will enable improved localization of OCT field-of-view relative to features-of-interest and improved sensitivity for anatomic features of disease.

Deep learning based joint segmentation and characterization of multi-class retinal fluid lesions on OCT scans for clinical use in anti-VEGF therapy

BACKGROUND

In anti-vascular endothelial growth factor (anti-VEGF) therapy, an accurate estimation of multi-class retinal fluid (MRF) is required for the activity prescription and intravitreal dose. This study proposes an end-to-end deep learning-based retinal fluids segmentation network (RFS-Net) to segment and recognize three MRF lesion manifestations, namely, intraretinal fluid (IRF), subretinal fluid (SRF), and pigment epithelial detachment (PED), from multi-vendor optical coherence tomography (OCT) imagery. The proposed image analysis tool will optimize anti-VEGF therapy and contribute to reducing the inter- and intra-observer variability.

METHOD

The proposed RFS-Net architecture integrates the atrous spatial pyramid pooling (ASPP), residual, and inception modules in the encoder path to learn better features and conserve more global information for precise segmentation and characterization of MRF lesions. The RFS-Net model is trained and validated using OCT scans from multiple vendors (Topcon, Cirrus, Spectralis), collected from three publicly available datasets. The first dataset consisted of OCT volumes obtained from 112 subjects (a total of 11,334 B-scans) is used for both training and evaluation purposes. Moreover, the remaining two datasets are only used for evaluation purposes to check the trained RFS-Net's generalizability on unseen OCT scans. The two evaluation datasets contain a total of 1572 OCT B-scans from 1255 subjects. The performance of the proposed RFS-Net model is assessed through various evaluation metrics.

RESULTS

The proposed RFS-Net model achieved the mean F₁ scores of 0.762, 0.796, and 0.805 for segmenting IRF, SRF, and PED. Moreover, with the automated segmentation of the three retinal manifestations, the RFS-Net brings a considerable gain in efficiency compared to the tedious and demanding manual segmentation procedure of the MRF.

CONCLUSIONS

Our proposed RFS-Net is a potential diagnostic tool for the automatic segmentation of MRF (IRF, SRF, and PED) lesions. It is expected to strengthen the inter-observer agreement, and standardization of dosimetry is envisaged as a result.

Modeling of Retinal Optical Coherence Tomography Based on Stochastic Differential Equations: Application to Denoising

In this paper a statistical modeling, based on stochastic differential equations (SDEs), is proposed for retinal Optical Coherence Tomography (OCT) images. In this method, pixel intensities of image are considered as discrete realizations of a Levy stable process. This process has independent increments and can be expressed as response of SDE to a white symmetric alpha stable (s [Formula: see text]) noise. Based on this assumption, applying appropriate differential operator makes intensities statistically independent. Mentioned white stable noise can be regenerated by applying fractional Laplacian operator to image intensities. In this way, we modeled OCT images as s [Formula: see text] distribution. We applied fractional Laplacian operator to image and fitted s [Formula: see text] to its histogram. Statistical tests were used to evaluate goodness of fit of stable distribution and its heavy tailed and stability characteristics. We used modeled s [Formula: see text] distribution as prior information in maximum a posteriori (MAP) estimator in order to reduce the speckle noise of OCT images. Such a statistically independent prior distribution simplified denoising optimization problem to a regularization algorithm with an adjustable shrinkage operator for each image. Alternating Direction Method of Multipliers (ADMM) algorithm was utilized to solve the denoising problem. We presented visual and quantitative evaluation results of the performance of this modeling and denoising methods for normal and abnormal images. Applying parameters of model in classification task as well as indicating effect of denoising in layer segmentation improvement illustrates that the proposed method describes OCT data more accurately than other models that do not remove statistical dependencies between pixel intensities.

Reconstruction of Optical Coherence Tomography Images Using Mixed Low Rank Approximation and Second Order Tensor Based Total Variation Method

This paper proposes a mixed low-rank approximation and second-order tensor-based total variation (LRSOTTV) approach for the super-resolution and denoising of retinal optical coherence tomography (OCT) images through effective utilization of nonlocal spatial correlations and local smoothness properties. OCT imaging relies on interferometry, which explains why OCT images suffer from a high level of noise. In addition, data subsampling is conducted during OCT A-scan and B-scan acquisition. Therefore, using effective super-resolution algorithms is necessary for reconstructing high-resolution clean OCT images. In this paper, a low-rank regularization approach is proposed for exploiting nonlocal self-similarity prior to OCT image reconstruction. To benefit from the advantages of the redundancy of multi-slice OCT data, we construct a third-order tensor by extracting the nonlocal similar three-dimensional blocks and grouping them by applying the k-nearest-neighbor method. Next, the nuclear norm is used as a regularization term to shrink the singular values of the constructed tensor in the non-local correlation direction. Further, the regularization approaches of the first-order tensor-based total variation (FOTTV) and SOTTV are proposed for better preservation of retinal layers and suppression of artifacts in OCT images. The alternative direction method of multipliers (ADMM) technique is then used to solve the resulting optimization problem. Our experiments show that integrating SOTTV instead of FOTTV into a low-rank approximation model can achieve noticeably improved results. Our experimental results on the denoising and super-resolution of OCT images demonstrate that the proposed model can provide images whose numerical and visual qualities are higher than those obtained by using state-of-the-art methods.

SiameseGAN: A Generative Model for Denoising of Spectral Domain Optical Coherence Tomography Images

Optical coherence tomography (OCT) is a standard diagnostic imaging method for assessment of ophthalmic diseases. The speckle noise present in the high-speed OCT images hampers its clinical utility, especially in Spectral-Domain Optical Coherence Tomography (SDOCT). In this work, a new deep generative model, called as SiameseGAN, for denoising Low signal-to-noise ratio (LSNR) B-scans of SDOCT has been developed. SiameseGAN is a Generative Adversarial Network (GAN) equipped with a siamese twin network. The siamese network module of the proposed SiameseGAN model helps the generator to generate denoised images that are closer to groundtruth images in the feature space, while the discriminator helps in making sure they are realistic images. This approach, unlike baseline dictionary learning technique (MSBTD), does not require an apriori high-quality image from the target imaging subject for denoising and takes less time for denoising. Moreover, various deep learning models that have been shown to be effective in performing denoising task in the SDOCT imaging were also deployed in this work. A qualitative and quantitative comparison on the performance of proposed method with these state-of-the-art denoising algorithms has been performed. The experimental results show that the speckle noise can be effectively mitigated using the proposed SiameseGAN along with faster denoising unlike existing approaches.

Multivariate Statistical Modeling of Retinal Optical Coherence Tomography

In this paper a new statistical multivariate model for retinal Optical Coherence Tomography (OCT) B-scans is proposed. Due to the layered structure of OCT images, there is a horizontal dependency between adjacent pixels at specific distances, which led us to propose a more accurate multivariate statistical model to be employed in OCT processing applications such as denoising. Due to the asymmetric form of the probability density function (pdf) in each retinal layer, a generalized version of multivariate Gaussian Scale Mixture (GSM) model, which we refer to as GM-GSM model, is proposed for each retinal layer. In this model, the pixel intensities in each retinal layer are modeled with an asymmetric Bessel K Form (BKF) distribution as a specific form of the GM-GSM model. Then, by combining some layers together, a mixture of GM-GSM model with eight components is proposed. The proposed model is then easily converted to a multivariate Gaussian Mixture model (GMM) to be employed in the spatially constrained GMM denoising algorithm. The Q-Q plot is utilized to evaluate goodness of fit of each component of the final mixture model. The improvement in the noise reduction results based on the GM-GSM model, indicates that the proposed statistical model describes the OCT data more accurately than other competing methods that do not consider spatial dependencies between neighboring pixels.

Towards label-free 3D segmentation of optical coherence tomography images of the optic nerve head using deep learning

Recently proposed deep learning (DL) algorithms for the segmentation of optical coherence tomography (OCT) images to quantify the morphological changes to the optic nerve head (ONH) tissues during glaucoma have limited clinical adoption due to their device specific nature and the difficulty in preparing manual segmentations (training data). We propose a DL-based 3D segmentation framework that is easily translatable across OCT devices in a label-free manner (i.e. without the need to manually re-segment data for each device). Specifically, we developed 2 sets of DL networks: the 'enhancer' (enhance OCT image quality and harmonize image characteristics from 3 devices) and the 'ONH-Net' (3D segmentation of 6 ONH tissues). We found that only when the 'enhancer' was used to preprocess the OCT images, the 'ONH-Net' trained on any of the 3 devices successfully segmented ONH tissues from the other two unseen devices with high performance (Dice coefficients > 0.92). We demonstrate that is possible to automatically segment OCT images from new devices without ever needing manual segmentation data from them.

Deep learning on image denoising: An overview

Deep learning techniques have received much attention in the area of image denoising. However, there are substantial differences in the various types of deep learning methods dealing with image denoising. Specifically, discriminative learning based on deep learning can ably address the issue of Gaussian noise. Optimization models based on deep learning are effective in estimating the real noise. However, there has thus far been little related research to summarize the different deep learning techniques for image denoising. In this paper, we offer a comparative study of deep techniques in image denoising. We first classify the deep convolutional neural networks (CNNs) for additive white noisy images; the deep CNNs for real noisy images; the deep CNNs for blind denoising and the deep CNNs for hybrid noisy images, which represents the combination of noisy, blurred and low-resolution images. Then, we analyze the motivations and principles of the different types of deep learning methods. Next, we compare the state-of-the-art methods on public denoising datasets in terms of quantitative and qualitative analyses. Finally, we point out some potential challenges and directions of future research.

Super-Resolution of Optical Coherence Tomography Images by Scale Mixture Models

In this paper, a new statistical model is proposed for the single image super-resolution of retinal Optical Coherence Tomography (OCT) images. OCT imaging relies on interfero-metry, which explains why OCT images suffer from a high level of noise. Moreover, data subsampling is carried out during the acquisition of OCT A-scans and B-scans. So, it is necessary to utilize effective super-resolution algorithms to reconstruct high-resolution clean OCT images. In this paper, a nonlocal sparse model-based Bayesian framework is proposed for OCT restoration. For this reason, by characterizing nonlocal patches with similar structures, known as a group, the sparse coefficients of each group of OCT images are modeled by the scale mixture models. In this base, the coefficient vector is decomposed into the point-wise product of a random vector and a positive scaling variable. Estimation of the sparse coefficients depends on the proposed distribution for the random vector and scaling variable where the Laplacian random vector and Generalized Extreme-Value (GEV) scale parameter (Laplacian+GEV model) show the best goodness of fit for each group of OCT images. Finally, a new OCT super-resolution method based on this new scale mixture model is introduced, where the maximum a posterior estimation of both sparse coefficients and scaling variables are calculated efficiently by applying an alternating minimization method. Our experimental results prove that the proposed OCT super-resolution method based on the Laplacian+GEV model outperforms other competing methods in terms of both subjective and objective visual qualities.

Three-dimensional curvelet-based dictionary learning for speckle noise removal of optical coherence tomography

Optical coherence tomography (OCT) is a recently emerging non-invasive diagnostic tool useful in several medical applications such as ophthalmology, cardiology, gastroenterology and dermatology. One of the major problems with OCT pertains to its low contrast due to the presence of multiplicative speckle noise, which limits the signal-to-noise ratio (SNR) and obscures low-intensity and small features. In this paper, we recommend a new method using the 3D curvelet based K-times singular value decomposition (K-SVD) algorithm for speckle noise reduction and contrast enhancement of the intra-retinal layers of 3D Spectral-Domain OCT (3D-SDOCT) images. In order to benefit from the near-optimum properties of curvelet transform (such as good directional selectivity) on top of dictionary learning, we propose a new plan in dictionary learning by using the curvelet atoms as the initial dictionary. For this reason, the curvelet transform of the noisy image is taken and then the noisy coefficients matrix in each scale, rotation and spatial coordinates is passed through the K-SVD denoising algorithm with predefined 3D initial dictionary that is adaptively selected from thresholded coefficients in the same subband of the image. During the denoising of curvelet coefficients, we can also modify them for the purpose of contrast enhancement of intra-retinal layers. We demonstrate the ability of our proposed algorithm in the speckle noise reduction of 17 publicly available 3D OCT data sets, each of which contains 100 B-scans of size 512×1000 with and without neovascular age-related macular degeneration (AMD) images acquired using SDOCT, Bioptigen imaging systems. Experimental results show that an improvement from 1.27 to 7.81 in contrast to noise ratio (CNR), and from 38.09 to 1983.07 in equivalent number of looks (ENL) is achieved, which would outperform existing state-of-the-art OCT despeckling methods.