Fast acquisition and reconstruction of optical coherence tomography images via sparse representation

Resolution enhancement and realistic speckle recovery with generative adversarial modeling of micro-optical coherence tomography

A resolution enhancement technique for optical coherence tomography (OCT), based on Generative Adversarial Networks (GANs), was developed and investigated. GANs have been previously used for resolution enhancement of photography and optical microscopy images. We have adapted and improved this technique for OCT image generation. Conditional GANs (cGANs) were trained on a novel set of ultrahigh resolution spectral domain OCT volumes, termed micro-OCT, as the high-resolution ground truth (∼1 μm isotropic resolution). The ground truth was paired with a low-resolution image obtained by synthetically degrading resolution 4x in one of (1-D) or both axial and lateral axes (2-D). Cross-sectional image (B-scan) volumes obtained from in vivo imaging of human labial (lip) tissue and mouse skin were used in separate feasibility experiments. Accuracy of resolution enhancement compared to ground truth was quantified with human perceptual accuracy tests performed by an OCT expert. The GAN loss in the optimization objective, noise injection in both the generator and discriminator models, and multi-scale discrimination were found to be important for achieving realistic speckle appearance in the generated OCT images. The utility of high-resolution speckle recovery was illustrated by an example of micro-OCT imaging of blood vessels in lip tissue. Qualitative examples applying the models to image data from outside of the training data distribution, namely human retina and mouse bladder, were also demonstrated, suggesting potential for cross-domain transferability. This preliminary study suggests that deep learning generative models trained on OCT images from high-performance prototype systems may have potential in enhancing lower resolution data from mainstream/commercial systems, thereby bringing cutting-edge technology to the masses at low cost.

High signal-to-noise ratio reconstruction of low bit-depth optical coherence tomography using deep learning

SIGNIFICANCE

Reducing the bit depth is an effective approach to lower the cost of an optical coherence tomography (OCT) imaging device and increase the transmission efficiency in data acquisition and telemedicine. However, a low bit depth will lead to the degradation of the detection sensitivity, thus reducing the signal-to-noise ratio (SNR) of OCT images.

AIM

We propose using deep learning to reconstruct high SNR OCT images from low bit-depth acquisition.

APPROACH

The feasibility of our approach is evaluated by applying this approach to the quantized 3- to 8-bit data from native 12-bit interference fringes. We employ a pixel-to-pixel generative adversarial network (pix2pixGAN) architecture in the low-to-high bit-depth OCT image transition.

RESULTS

Extensively, qualitative and quantitative results show our method could significantly improve the SNR of the low bit-depth OCT images. The adopted pix2pixGAN is superior to other possible deep learning and compressed sensing solutions.

CONCLUSIONS

Our work demonstrates that the proper integration of OCT and deep learning could benefit the development of healthcare in low-resource settings.

Super-resolution technology to simultaneously improve optical & digital resolution of optical coherence tomography via deep learning

Optical coherence tomography (OCT) has stimulated a wide range of medical image-based diagnosis and treatment. In cardiac imaging, OCT has been used in assessing plaques before and after stenting. While needed in many scenarios, high resolution comes at the costs of demanding optical design and data storage/transmission. In OCT, there are two types of resolutions to characterize image quality: optical and digital resolutions. Although multiple existing works have heavily emphasized on improving the digital resolution, the studies on improving optical resolution or both resolutions remain scarce. In this paper, we focus on improving both resolutions. In particular, we investigate a deep learning method to address the problem of generating a high-resolution (HR) OCT image from a low optical and low digital resolution (L2R) image. To this end, we have modified the existing super-resolution generative adversarial network (SR-GAN) for OCT image reconstruction. Experimental results from the human coronary OCT images have demonstrated that the reconstructed images from highly compressed data could achieve high structural similarity and accuracy in comparison with the HR images. Besides, our method has obtained better denoising performance than the block-matching and 3D filtering (BM3D) and Denoising Convolutional Neural Networks (DnCNN) denoising method.

OCT Image Restoration Using Non-Local Deep Image Prior

In recent years, convolutional neural networks (CNN) have been widely used in image denoising for their high performance. One difficulty in applying the CNN to medical image denoising such as speckle reduction in the optical coherence tomography (OCT) image is that a large amount of high-quality data is required for training, which is an inherent limitation for OCT despeckling. Recently, deep image prior (DIP) networks have been proposed for image restoration without pre-training since the CNN structures have the intrinsic ability to capture the low-level statistics of a single image. However, the DIP has difficulty finding a good balance between maintaining details and suppressing speckle noise. Inspired by DIP, in this paper, a sorted non-local statics which measures the signal autocorrelation in the differences between the constructed image and the input image is proposed for OCT image restoration. By adding the sorted non-local statics as a regularization loss in the DIP learning, more low-level image statistics are captured by CNN networks in the process of OCT image restoration. The experimental results demonstrate the superior performance of the proposed method over other state-of-the-art despeckling methods, in terms of objective metrics and visual quality.

3D Shape Modeling and Analysis of Retinal Microvasculature in OCT-Angiography Images

3D optical coherence tomography angiography (OCT-A) is a novel and non-invasive imaging modality for analyzing retinal diseases. The studies of microvasculature in 2D en face projection images have been widely implemented, but comprehensive 3D analysis of OCT-A images with rich depth-resolved microvascular information is rarely considered. In this paper, we propose a robust, effective, and automatic 3D shape modeling framework to provide a high-quality 3D vessel representation and to preserve valuable 3D geometric and topological information for vessel analysis. Effective vessel enhancement and extraction steps by means of curvelet denoising and optimally oriented flux (OOF) filtering are first designed to produce 3D microvascular networks. Afterwards, a novel 3D data representation of OCT-A microvasculature is reconstructed via advanced mesh reconstruction techniques. Based on the 3D surfaces, shape analysis is established to extract novel shape-based microvascular area distortion via the Laplace-Beltrami eigen-projection. The extracted feature is integrated into a graph-cut segmentation system to categorize large vessels and small capillaries for more precise shape analysis. The proposed framework is validated on a dedicated repeated scan dataset including 260 volume images and shows high repeatability. Statistical analysis using the surface area biomarker is performed on small capillaries to avoid the effect of tailing artifact from large vessels. It shows significant differences ( ) between DR stages on 100 subjects in a OCTA-DR dataset. The proposed shape modeling and analysis framework opens the possibility for further investigating OCT-A microvasculature in a new perspective.

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.

Optical coherence tomography image denoising using a generative adversarial network with speckle modulation

Optical coherence tomography (OCT) is widely used for biomedical imaging and clinical diagnosis. However, speckle noise is a key factor affecting OCT image quality. Here, we developed a custom generative adversarial network (GAN) to denoise OCT images. A speckle-modulating OCT (SM-OCT) was built to generate low speckle images to be used as the ground truth. In total, 210 000 SM-OCT images were used for training and validating the neural network model, which we call SM-GAN. The performance of the SM-GAN method was further demonstrated using online benchmark retinal images, 3D OCT images acquired from human fingers and OCT videos of a beating fruit fly heart. The denoise performance of the SM-GAN model was compared to traditional OCT denoising methods and other state-of-the-art deep learning based denoise networks. We conclude that the SM-GAN model presented here can effectively reduce speckle noise in OCT images and videos while maintaining spatial and temporal resolutions.

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.

Ordered subsets Non-Local means constrained reconstruction for sparse view cone beam CT system

Sparse-view sampling scans reduce the patient's radiation dose by reducing the total exposure duration. CT reconstructions under such scan mode are often accompanied by severe artifacts due to the high ill-posedness of the problem. In this paper, we use a Non-Local means kernel as a regularization constraint to reconstruct image volumes from sparse-angle sampled cone-beam CT scans. To overcome the huge computational cost of the 3D reconstruction, we propose a sequential update scheme relying on ordered subsets in the image domain. It is shown through experiments on simulated and real data and comparisons with other methods that the proposed approach is robust enough to deal with the number of views reduced up to 1/10. When coupled with a CUDA parallel computing technique, the computation speed of the iterative reconstruction is greatly improved.

Optical oherence tomography image reconstruction Using Morphological Component Analysis

In this paper, we apply combination of sparse representations and a total variation for reconstruction of retinal optical coherence tomography (OCT) images. The OCT imaging is based on interferometry, therefore OCT images suffer from the existence of a high level of noise. Utilization of effective interpolation and denoising algorithms are necessary to reconstruct high-resolution OCT images, especially when the subsampling of data is done during acquisition. In this paper, we take total variational and Morphological Component Analysis (MCA) techniques to reduce noise and interpolate missing data. Different over-complete dictionaries are constructed by using curvelet transform, wavelet transform or DCT, which represent the texture and cartoon layers in B-scans. Comparative analysis of image interpolation is done by two combinations of dictionaries, which are (DCT+Curvelet) and (DWT+Curvelet) transforms. Layered structures are more distinguished in reconstructed image with curvelet dictionary and textures are mostly detectable by wavelet or DCT. Evaluations are done both visually and in terms of different performance measures. Our simulation results show that the (DCT+Curvelet) combination preserve the texture of the image well and the (DWT+Curvelet) combination has better performance in structure preservation.

A New Texture-Based Segmentation Method for Optical Coherence Tomography Images

Optical Coherence Tomography (OCT) is an imaging modality which facilitates capturing pictures from biological organs like retina. Accurate segmentation and verification of OCT images leads to the identification and treatment of harmful retinal diseases such as glaucoma. The main fact used for segmentation in this paper is that a considerable number of boundary pixels have similar features from texture point-of-view. Thus, a novel low-complexity segmentation method for OCT images is proposed paying attention to the texture feature of pixels on the boundaries. The simulation results show that the proposed method provides acceptable values for mean signed and unsigned errors compared to the result of manual segmentation.

STIR-Net: Deep Spatial-Temporal Image Restoration Net for Radiation Reduction in CT Perfusion

Computed Tomography Perfusion (CTP) imaging is a cost-effective and fast approach to provide diagnostic images for acute stroke treatment. Its cine scanning mode allows the visualization of anatomic brain structures and blood flow; however, it requires contrast agent injection and continuous CT scanning over an extended time. In fact, the accumulative radiation dose to patients will increase health risks such as skin irritation, hair loss, cataract formation, and even cancer. Solutions for reducing radiation exposure include reducing the tube current and/or shortening the X-ray radiation exposure time. However, images scanned at lower tube currents are usually accompanied by higher levels of noise and artifacts. On the other hand, shorter X-ray radiation exposure time with longer scanning intervals will lead to image information that is insufficient to capture the blood flow dynamics between frames. Thus, it is critical for us to seek a solution that can preserve the image quality when the tube current and the temporal frequency are both low. We propose STIR-Net in this paper, an end-to-end spatial-temporal convolutional neural network structure, which exploits multi-directional automatic feature extraction and image reconstruction schema to recover high-quality CT slices effectively. With the inputs of low-dose and low-resolution patches at different cross-sections of the spatio-temporal data, STIR-Net blends the features from both spatial and temporal domains to reconstruct high-quality CT volumes. In this study, we finalize extensive experiments to appraise the image restoration performance at different levels of tube current and spatial and temporal resolution scales.The results demonstrate the capability of our STIR-Net to restore high-quality scans at as low as 11% of absorbed radiation dose of the current imaging protocol, yielding an average of 10% improvement for perfusion maps compared to the patch-based log likelihood method.

Simultaneous denoising and super-resolution of optical coherence tomography images based on generative adversarial network

Optical coherence tomography (OCT) has become a very promising diagnostic method in clinical practice, especially for ophthalmic diseases. However, speckle noise and low sampling rates have intensively reduced the quality of OCT images, which prevents the development of OCT-assisted diagnosis. Therefore, we propose a generative adversarial network-based approach (named SDSR-OCT) to simultaneously denoise and super-resolve OCT images. Moreover, we trained three different super-resolution models with different upscale factors (2× , 4× and 8×) to adapt to the corresponding downsampling rates. We also quantitatively and qualitatively compared our proposed method with some well-known algorithms. The experimental results show that our approach can effectively suppress speckle noise and can super-resolve OCT images at different scales.

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

In recent years, there has been a growing interest in applying convolutional neural networks (CNNs) to low-level vision tasks such as denoising and super-resolution. Due to the coherent nature of the image formation process, the optical coherence tomography (OCT) images are inevitably affected by noise. This paper proposes a new method named the multi-input fully-convolutional networks (MIFCN) for denoising of OCT images. In contrast to recently proposed natural image denoising CNNs, the proposed architecture allows the exploitation of high degrees of correlation and complementary information among neighboring OCT images through pixel by pixel fusion of multiple FCNs. The parameters of the proposed multi-input architecture are learned by considering the consistency between the overall output and the contribution of each input image. The proposed MIFCN method is compared with the state-of-the-art denoising methods adopted on OCT images of normal and age-related macular degeneration eyes in a quantitative and qualitative manner.

Sparse Range-Constrained Learning and Its Application for Medical Image Grading

Sparse learning has been shown to be effective in solving many real-world problems. Finding sparse representations is a fundamentally important topic in many fields of science including signal processing, computer vision, genome study, and medical imaging. One important issue in applying sparse representation is to find the basis to represent the data, especially in computer vision and medical imaging where the data are not necessary incoherent. In medical imaging, clinicians often grade the severity or measure the risk score of a disease based on images. This process is referred to as medical image grading. Manual grading of the disease severity or risk score is often used. However, it is tedious, subjective, and expensive. Sparse learning has been used for automatic grading of medical images for different diseases. In the grading, we usually begin with one step to find a sparse representation of the testing image using a set of reference images or atoms from the dictionary. Then in the second step, the selected atoms are used as references to compute the grades of the testing images. Since the two steps are conducted sequentially, the objective function in the first step is not necessarily optimized for the second step. In this paper, we propose a novel sparse range-constrained learning (SRCL) algorithm for medical image grading. Different from most of existing sparse learning algorithms, SRCL integrates the objective of finding a sparse representation and that of grading the image into one function. It aims to find a sparse representation of the testing image based on atoms that are most similar in both the data or feature representation and the medical grading scores. We apply the new proposed SRCL to two different applications, namely, cup-to-disc ratio (CDR) computation from retinal fundus images and cataract grading from slit-lamp lens images. Experimental results show that the proposed method is able to improve the accuracy in CDR computation and cataract grading.

Robust layer segmentation of esophageal OCT images based on graph search using edge-enhanced weights

Automatic segmentation of esophageal layers in OCT images is crucial for studying esophageal diseases and computer-assisted diagnosis. This work aims to improve the current techniques to increase the accuracy and robustness for esophageal OCT image segmentation. A two-step edge-enhanced graph search (EEGS) framework is proposed in this study. Firstly, a preprocessing scheme is applied to suppress speckle noise and remove the disturbance in the esophageal structure. Secondly, the image is formulated into a graph and layer boundaries are located by graph search. In this process, we propose an edge-enhanced weight matrix for the graph by combining the vertical gradients with a Canny edge map. Experiments on esophageal OCT images from guinea pigs demonstrate that the EEGS framework is more robust and more accurate than the current segmentation method. It can be potentially useful for the early detection of esophageal diseases.

Volumetric non-local-means based speckle reduction for optical coherence tomography

We present a novel tomographic non-local-means based despeckling technique, TNode, for optical coherence tomography. TNode is built upon a weighting similarity criterion derived for speckle in a three-dimensional similarity window. We present an implementation using a two-dimensional search window, enabling the despeckling of volumes in the presence of motion artifacts, and an implementation using a three-dimensional window with improved performance in motion-free volumes. We show that our technique provides effective speckle reduction, comparable with B-scan compounding or out-of-plane averaging, while preserving isotropic resolution, even to the level of speckle-sized structures. We demonstrate its superior despeckling performance in a phantom data set, and in an ophthalmic data set we show that small, speckle-sized retinal vessels are clearly preserved in intensity images en-face and in two orthogonal, cross-sectional views. TNode does not rely on dictionaries or segmentation and therefore can readily be applied to arbitrary optical coherence tomography volumes. We show that despeckled esophageal volumes exhibit improved image quality and detail, even in the presence of significant motion artifacts.

Speckle noise reduction of multi-frame optical coherence tomography data using multi-linear principal component analysis

Optical coherence tomography (OCT) is an important interferometric diagnostic technique extensively applied in medical sciences. However, OCT images inevitably suffer from speckle noise, which reduces the accuracy of the diagnosis of ocular diseases. To deal with this problem, a speckle noise reduction method based on multi-linear principal component analysis (MPCA) is presented to denoise multi-frame OCT data. To well preserve local image features, nonlocal similar 3D blocks extracted from the data are first grouped using k-means++ clustering method. MPCA transform is then performed on each group and the transform coefficients are shrunk to remove speckle noise. Finally, the filtered OCT volume is obtained by inverse MPCA transform and aggregation. Experimental results show that the proposed method outperforms other compared approaches in terms of both speckle noise reduction and fine detail preservation.

Fast Image Super-Resolution via Local Adaptive Gradient Field Sharpening Transform

This paper proposes a single-image super-resolution scheme by introducing a gradient field sharpening transform that converts the blurry gradient field of upsampled low-resolution (LR) image to a much sharper gradient field of original high-resolution (HR) image. Different from the existing methods that need to figure out the whole gradient profile structure and locate the edge points, we derive a new approach that sharpens the gradient field adaptively only based on the pixels in a small neighborhood. To maintain image contrast, image gradient is adaptively scaled to keep the integral of gradient field stable. Finally, the HR image is reconstructed by fusing the LR image with the sharpened HR gradient field. Experimental results demonstrate that the proposed algorithm can generate more accurate gradient field and produce super-resolved images with better objective and visual qualities. Another advantage is that the proposed gradient sharpening transform is very fast and suitable for low-complexity applications.

Deep learning approach for the detection and quantification of intraretinal cystoid fluid in multivendor optical coherence tomography

We developed a deep learning algorithm for the automatic segmentation and quantification of intraretinal cystoid fluid (IRC) in spectral domain optical coherence tomography (SD-OCT) volumes independent of the device used for acquisition. A cascade of neural networks was introduced to include prior information on the retinal anatomy, boosting performance significantly. The proposed algorithm approached human performance reaching an overall Dice coefficient of 0.754 ± 0.136 and an intraclass correlation coefficient of 0.936, for the task of IRC segmentation and quantification, respectively. The proposed method allows for fast quantitative IRC volume measurements that can be used to improve patient care, reduce costs, and allow fast and reliable analysis in large population studies.

Optical coherence tomography retinal image reconstruction via nonlocal weighted sparse representation

We present a nonlocal weighted sparse representation (NWSR) method for reconstruction of retinal optical coherence tomography (OCT) images. To reconstruct a high signal-to-noise ratio and high-resolution OCT images, utilization of efficient denoising and interpolation algorithms are necessary, especially when the original data were subsampled during acquisition. However, the OCT images suffer from the presence of a high level of noise, which makes the estimation of sparse representations a difficult task. Thus, the proposed NWSR method merges sparse representations of multiple similar noisy and denoised patches to better estimate a sparse representation for each patch. First, the sparse representation of each patch is independently computed over an overcomplete dictionary, and then a nonlocal weighted sparse coefficient is computed by averaging representations of similar patches. Since the sparsity can reveal relevant information from noisy patches, combining noisy and denoised patches' representations is beneficial to obtain a more robust estimate of the unknown sparse representation. The denoised patches are obtained by applying an off-the-shelf image denoising method and our method provides an efficient way to exploit information from noisy and denoised patches' representations. The experimental results on denoising and interpolation of spectral domain OCT images demonstrated the effectiveness of the proposed NWSR method over existing state-of-the-art methods.

Shared-hole graph search with adaptive constraints for 3D optic nerve head optical coherence tomography image segmentation

Optic nerve head (ONH) is a crucial region for glaucoma detection and tracking based on spectral domain optical coherence tomography (SD-OCT) images. In this region, the existence of a "hole" structure makes retinal layer segmentation and analysis very challenging. To improve retinal layer segmentation, we propose a 3D method for ONH centered SD-OCT image segmentation, which is based on a modified graph search algorithm with a shared-hole and locally adaptive constraints. With the proposed method, both the optic disc boundary and nine retinal surfaces can be accurately segmented in SD-OCT images. An overall mean unsigned border positioning error of 7.27 ± 5.40 µm was achieved for layer segmentation, and a mean Dice coefficient of 0.925 ± 0.03 was achieved for optic disc region detection.

Speckle attenuation by adaptive singular value shrinking with generalized likelihood matching in optical coherence tomography

As a high-resolution imaging mode of biological tissues and materials, optical coherence tomography (OCT) is widely used in medical diagnosis and analysis. However, OCT images are often degraded by annoying speckle noise inherent in its imaging process. Employing the bilateral sparse representation an adaptive singular value shrinking method is proposed for its highly sparse approximation of image data. Adopting the generalized likelihood ratio as similarity criterion for block matching and an adaptive feature-oriented backward projection strategy, the proposed algorithm can restore better underlying layered structures and details of the OCT image with effective speckle attenuation. The experimental results demonstrate that the proposed algorithm achieves a state-of-the-art despeckling performance in terms of both quantitative measurement and visual interpretation.

Automatic detection of the foveal center in optical coherence tomography

We propose a method for automatic detection of the foveal center in optical coherence tomography (OCT). The method is based on a pixel-wise classification of all pixels in an OCT volume using a fully convolutional neural network (CNN) with dilated convolution filters. The CNN-architecture contains anisotropic dilated filters and a shortcut connection and has been trained using a dynamic training procedure where the network identifies its own relevant training samples. The performance of the proposed method is evaluated on a data set of 400 OCT scans of patients affected by age-related macular degeneration (AMD) at different severity levels. For 391 scans (97.75%) the method identified the foveal center with a distance to a human reference less than 750 μm, with a mean (± SD) distance of 71 μm ± 107 μm. Two independent observers also annotated the foveal center, with a mean distance to the reference of 57 μm ± 84 μm and 56 μm ± 80 μm, respectively. Furthermore, we evaluate variations to the proposed network architecture and training procedure, providing insight in the characteristics that led to the demonstrated performance of the proposed method.

Statistical model for OCT image denoising

Optical coherence tomography (OCT) is a non-invasive technique with a large array of applications in clinical imaging and biological tissue visualization. However, the presence of speckle noise affects the analysis of OCT images and their diagnostic utility. In this article, we introduce a new OCT denoising algorithm. The proposed method is founded on a numerical optimization framework based on maximum-a-posteriori estimate of the noise-free OCT image. It combines a novel speckle noise model, derived from local statistics of empirical spectral domain OCT (SD-OCT) data, with a Huber variant of total variation regularization for edge preservation. The proposed approach exhibits satisfying results in terms of speckle noise reduction as well as edge preservation, at reduced computational cost.

Dual-stage deep learning framework for pigment epithelium detachment segmentation in polypoidal choroidal vasculopathy

Worldwide, polypoidal choroidal vasculopathy (PCV) is a common vision-threatening exudative maculopathy, and pigment epithelium detachment (PED) is an important clinical characteristic. Thus, precise and efficient PED segmentation is necessary for PCV clinical diagnosis and treatment. We propose a dual-stage learning framework via deep neural networks (DNN) for automated PED segmentation in PCV patients to avoid issues associated with manual PED segmentation (subjectivity, manual segmentation errors, and high time consumption).The optical coherence tomography scans of fifty patients were quantitatively evaluated with different algorithms and clinicians. Dual-stage DNN outperformed existing PED segmentation methods for all segmentation accuracy parameters, including true positive volume fraction (85.74 ± 8.69%), dice similarity coefficient (85.69 ± 8.08%), positive predictive value (86.02 ± 8.99%) and false positive volume fraction (0.38 ± 0.18%). Dual-stage DNN achieves accurate PED quantitative information, works with multiple types of PEDs and agrees well with manual delineation, suggesting that it is a potential automated assistant for PCV management.

Optical coherence tomography image denoising using Gaussianization transform

We demonstrate the power of the Gaussianization transform (GT) for modeling image content by applying GT for optical coherence tomography (OCT) denoising. The proposed method is a developed version of the spatially constrained Gaussian mixture model (SC-GMM) method, which assumes that each cluster of similar patches in an image has a Gaussian distribution. SC-GMM tries to find some clusters of similar patches in the image using a spatially constrained patch clustering and then denoise each cluster by the Wiener filter. Although in this method GMM distribution is assumed for the noisy image, holding this assumption on a dataset is not investigated. We illustrate that making a Gaussian assumption on a noisy dataset has a significant effect on denoising results. For this purpose, a suitable distribution for OCT images is first obtained and then GT is employed to map this original distribution of OCT images to a GMM distribution. Then, this Gaussianized image is used as the input of the SC-GMM algorithm. This method, which is a combination of GT and SC-GMM, remarkably improves the results of OCT denoising compared with earlier version of SC-GMM and even produces better visual and numerical results than the state-of-the art works in this field. Indeed, the main advantage of the proposed OCT despeckling method is texture preservation, which is important for main image processing tasks like OCT inter- and intraretinal layer analysis. Thus, to prove the efficacy of the proposed method for this analysis, an improvement in the segmentation of intraretinal layers using the proposed method as a preprocessing step is investigated. Furthermore, the proposed method can achieve the best expert ranking between other contending methods, and the results show the helpfulness and usefulness of the proposed method in clinical applications.

Merging computational fluid dynamics and 4D Flow MRI using proper orthogonal decomposition and ridge regression

Time resolved phase-contrast magnetic resonance imaging 4D-PCMR (also called 4D Flow MRI) data while capable of non-invasively measuring blood velocities, can be affected by acquisition noise, flow artifacts, and resolution limits. In this paper, we present a novel method for merging 4D Flow MRI with computational fluid dynamics (CFD) to address these limitations and to reconstruct de-noised, divergence-free high-resolution flow-fields. Proper orthogonal decomposition (POD) is used to construct the orthonormal basis of the local sampling of the space of all possible solutions to the flow equations both at the low-resolution level of the 4D Flow MRI grid and the high-level resolution of the CFD mesh. Low-resolution, de-noised flow is obtained by projecting in vivo 4D Flow MRI data onto the low-resolution basis vectors. Ridge regression is then used to reconstruct high-resolution de-noised divergence-free solution. The effects of 4D Flow MRI grid resolution, and noise levels on the resulting velocity fields are further investigated. A numerical phantom of the flow through a cerebral aneurysm was used to compare the results obtained using the POD method with those obtained with the state-of-the-art de-noising methods. At the 4D Flow MRI grid resolution, the POD method was shown to preserve the small flow structures better than the other methods, while eliminating noise. Furthermore, the method was shown to successfully reconstruct details at the CFD mesh resolution not discernible at the 4D Flow MRI grid resolution. This method will improve the accuracy of the clinically relevant flow-derived parameters, such as pressure gradients and wall shear stresses, computed from in vivo 4D Flow MRI data.

Automated intraretinal segmentation of SD-OCT images in normal and age-related macular degeneration eyes

This work introduces and evaluates an automated intra-retinal segmentation method for spectral-domain optical coherence (SD-OCT) retinal images. While quantitative assessment of retinal features in SD-OCT data is important, manual segmentation is extremely time-consuming and subjective. We address challenges that have hindered prior automated methods, including poor performance with diseased retinas relative to healthy retinas, and data smoothing that obscures image features such as small retinal drusen. Our novel segmentation approach is based on the iterative adaptation of a weighted median process, wherein a three-dimensional weighting function is defined according to image intensity and gradient properties, and a set of smoothness constraints and pre-defined rules are considered. We compared the segmentation results for 9 segmented outlines associated with intra-retinal boundaries to those drawn by hand by two retinal specialists and to those produced by an independent state-of-the-art automated software tool in a set of 42 clinical images (from 14 patients). These images were obtained with a Zeiss Cirrus SD-OCT system, including healthy, early or intermediate AMD, and advanced AMD eyes. As a qualitative evaluation of accuracy, a highly experienced third independent reader blindly rated the quality of the outlines produced by each method. The accuracy and image detail of our method was superior in healthy and early or intermediate AMD eyes (98.15% and 97.78% of results not needing substantial editing) to the automated method we compared against. While the performance was not as good in advanced AMD (68.89%), it was still better than the manual outlines or the comparison method (which failed in such cases). We also tested our method's performance on images acquired with a different SD-OCT manufacturer, collected from a large publicly available data set (114 healthy and 255 AMD eyes), and compared the data quantitatively to reference standard markings of the internal limiting membrane and inner boundary of retinal pigment epithelium, producing a mean unsigned positioning error of 6.04 ± 7.83µm (mean under 2 pixels). Our automated method should be applicable to data from different OCT manufacturers and offers detailed layer segmentations in healthy and AMD eyes.

Involuntary eye motion correction in retinal optical coherence tomography: Hardware or software solution?

In this paper, we review state-of-the-art techniques to correct eye motion artifacts in Optical Coherence Tomography (OCT) imaging. The methods for eye motion artifact reduction can be categorized into two major classes: (1) hardware-based techniques and (2) software-based techniques. In the first class, additional hardware is mounted onto the OCT scanner to gather information about the eye motion patterns during OCT data acquisition. This information is later processed and applied to the OCT data for creating an anatomically correct representation of the retina, either in an offline or online manner. In software based techniques, the motion patterns are approximated either by comparing the acquired data to a reference image, or by considering some prior assumptions about the nature of the eye motion. Careful investigations done on the most common methods in the field provides invaluable insight regarding future directions of the research in this area. The challenge in hardware-based techniques lies in the implementation aspects of particular devices. However, the results of these techniques are superior to those obtained from software-based techniques because they are capable of capturing secondary data related to eye motion during OCT acquisition. Software-based techniques on the other hand, achieve moderate success and their performance is highly dependent on the quality of the OCT data in terms of the amount of motion artifacts contained in them. However, they are still relevant to the field since they are the sole class of techniques with the ability to be applied to legacy data acquired using systems that do not have extra hardware to track eye motion.

Segmentation Based Sparse Reconstruction of Optical Coherence Tomography Images

We demonstrate the usefulness of utilizing a segmentation step for improving the performance of sparsity based image reconstruction algorithms. In specific, we will focus on retinal optical coherence tomography (OCT) reconstruction and propose a novel segmentation based reconstruction framework with sparse representation, termed segmentation based sparse reconstruction (SSR). The SSR method uses automatically segmented retinal layer information to construct layer-specific structural dictionaries. In addition, the SSR method efficiently exploits patch similarities within each segmented layer to enhance the reconstruction performance. Our experimental results on clinical-grade retinal OCT images demonstrate the effectiveness and efficiency of the proposed SSR method for both denoising and interpolation of OCT images.

Fully automated macular pathology detection in retina optical coherence tomography images using sparse coding and dictionary learning

We propose a framework for automated detection of dry age-related macular degeneration (AMD) and diabetic macular edema (DME) from retina optical coherence tomography (OCT) images, based on sparse coding and dictionary learning. The study aims to improve the classification performance of state-of-the-art methods. First, our method presents a general approach to automatically align and crop retina regions; then it obtains global representations of images by using sparse coding and a spatial pyramid; finally, a multiclass linear support vector machine classifier is employed for classification. We apply two datasets for validating our algorithm: Duke spectral domain OCT (SD-OCT) dataset, consisting of volumetric scans acquired from 45 subjects—15 normal subjects, 15 AMD patients, and 15 DME patients; and clinical SD-OCT dataset, consisting of 678 OCT retina scans acquired from clinics in Beijing—168, 297, and 213 OCT images for AMD, DME, and normal retinas, respectively. For the former dataset, our classifier correctly identifies 100%, 100%, and 93.33% of the volumes with DME, AMD, and normal subjects, respectively, and thus performs much better than the conventional method; for the latter dataset, our classifier leads to a correct classification rate of 99.67%, 99.67%, and 100.00% for DME, AMD, and normal images, respectively.

Speckle Reduction in 3D Optical Coherence Tomography of Retina by A-Scan Reconstruction

Optical coherence tomography (OCT) is a micrometer-scale, cross-sectional imaging modality for biological tissue. It has been widely used for retinal imaging in ophthalmology. Speckle noise is problematic in OCT. A raw OCT image/volume usually has very poor image quality due to speckle noise, which often obscures the retinal structures. Overlapping scan is often used for speckle reduction in a 2D line-scan. However, it leads to an increase of the data acquisition time. Therefore, it is unpractical in 3D scan as it requires a much longer data acquisition time. In this paper, we propose a new method for speckle reduction in 3D OCT. The proposed method models each A -scan as the sum of underlying clean A -scan and noise. Based on the assumption that neighboring A -scans are highly similar in the retina, the method reconstructs each A -scan from its neighboring scans. In the method, the neighboring A -scans are aligned/registered to the A -scan to be reconstructed and form a matrix together. Then low rank matrix completion using bilateral random projection is utilized to iteratively estimate the noise and recover the underlying clean A -scan. The proposed method is evaluated through the mean square error, peak signal to noise ratio and the mean structure similarity index using high quality line-scan images as reference. Experimental results show that the proposed method performs better than other methods. In addition, the subsequent retinal layer segmentation also shows that the proposed method makes the automatic retinal layer segmentation more accurate. The technology can be embedded into current OCT machines to enhance the image quality for visualization and subsequent analysis such as retinal layer segmentation.

Smoothed l0 Norm Regularization for Sparse-View X-Ray CT Reconstruction

Low-dose computed tomography (CT) reconstruction is a challenging problem in medical imaging. To complement the standard filtered back-projection (FBP) reconstruction, sparse regularization reconstruction gains more and more research attention, as it promises to reduce radiation dose, suppress artifacts, and improve noise properties. In this work, we present an iterative reconstruction approach using improved smoothed l₀ (SL0) norm regularization which is used to approximate l₀ norm by a family of continuous functions to fully exploit the sparseness of the image gradient. Due to the excellent sparse representation of the reconstruction signal, the desired tissue details are preserved in the resulting images. To evaluate the performance of the proposed SL0 regularization method, we reconstruct the simulated dataset acquired from the Shepp-Logan phantom and clinical head slice image. Additional experimental verification is also performed with two real datasets from scanned animal experiment. Compared to the referenced FBP reconstruction and the total variation (TV) regularization reconstruction, the results clearly reveal that the presented method has characteristic strengths. In particular, it improves reconstruction quality via reducing noise while preserving anatomical features.

Application of Independent Component Analysis Techniques in Speckle Noise Reduction of Retinal OCT Images

Optical Coherence Tomography (OCT) is an emerging technique in the field of biomedical imaging, with applications in ophthalmology, dermatology, coronary imaging etc. OCT images usually suffer from a granular pattern, called speckle noise, which restricts the process of interpretation. Therefore the need for speckle noise reduction techniques is of high importance. To the best of our knowledge, use of Independent Component Analysis (ICA) techniques has never been explored for speckle reduction of OCT images. Here, a comparative study of several ICA techniques (InfoMax, JADE, FastICA and SOBI) is provided for noise reduction of retinal OCT images. Having multiple B-scans of the same location, the eye movements are compensated using a rigid registration technique. Then, different ICA techniques are applied to the aggregated set of B-scans for extracting the noise-free image. Signal-to-Noise-Ratio (SNR), Contrast-to-Noise-Ratio (CNR) and Equivalent-Number-of-Looks (ENL), as well as analysis on the computational complexity of the methods, are considered as metrics for comparison. The results show that use of ICA can be beneficial, especially in case of having fewer number of B-scans.

Adaptive anisotropic diffusion for noise reduction of phase images in Fourier domain Doppler optical coherence tomography

Phase image in Fourier domain Doppler optical coherence tomography offers additional flow information of investigated samples, which provides valuable evidence towards accurate medical diagnosis. High quality phase images are thus desirable. We propose a noise reduction method for phase images by combining a synthetic noise estimation criteria based on local noise estimator (LNE) and distance median value (DMV) with anisotropic diffusion model. By identifying noise and signal pixels accurately and diffusing them with different coefficients respectively and adaptive iteration steps, we demonstrated the effectiveness of our proposed method in both phantom and mouse artery images. Comparison with other methods such as filtering method (mean, median filtering), wavelet method, probabilistic method and partial differential equation based methods in terms of peak signal-to-noise ratio (PSNR), equivalent number of looks (ENL) and contrast-to-noise ratio (CNR) showed the advantages of our method in reserving image energy and removing noise.

Three-dimensional Segmentation of Retinal Cysts from Spectral-domain Optical Coherence Tomography Images by the Use of Three-dimensional Curvelet Based K-SVD

This paper presents a new three-dimensional curvelet transform based dictionary learning for automatic segmentation of intraretinal cysts, most relevant prognostic biomarker in neovascular age-related macular degeneration, from 3D spectral-domain optical coherence tomography (SD-OCT) images. In particular, we focus on the Spectralis SD-OCT (Heidelberg Engineering, Heidelberg, Germany) system, and show the applicability of our algorithm in the segmentation of these features. For this purpose, we use recursive Gaussian filter and approximate the corrupted pixels from its surrounding, then in order to enhance the cystoid dark space regions and future noise suppression we introduce a new scheme in dictionary learning and take curvelet transform of filtered image then denoise and modify each noisy coefficients matrix in each scale with predefined initial 3D sparse dictionary. Dark pixels between retinal pigment epithelium and nerve fiber layer that were extracted with graph theory are considered as cystoid spaces. The average dice coefficient for the segmentation of cystoid regions in whole 3D volume and with-in central 3 mm diameter on the MICCAI 2015 OPTIMA Cyst Segmentation Challenge dataset were found to be 0.65 and 0.77, respectively.

Length-adaptive graph search for automatic segmentation of pathological features in optical coherence tomography images

We introduce a metric in graph search and demonstrate its application for segmenting retinal optical coherence tomography (OCT) images of macular pathology. Our proposed “adjusted mean arc length” (AMAL) metric is an adaptation of the lowest mean arc length search technique for automated OCT segmentation. We compare this method to Dijkstra’s shortest path algorithm, which we utilized previously in our popular graph theory and dynamic programming segmentation technique. As an illustrative example, we show that AMAL-based length-adaptive segmentation outperforms the shortest path in delineating the retina/vitreous boundary of patients with full-thickness macular holes when compared with expert manual grading.

Probability-based non-local means filter for speckle noise suppression in optical coherence tomography images

In this Letter, a probability-based non-local means filter is proposed for speckle reduction in optical coherence tomography (OCT). Originally developed for additive white Gaussian noise, the non-local means filter is not suitable for multiplicative speckle noise suppression. This Letter presents a two-stage non-local means algorithm using the uncorrupted probability of each pixel to effectively reduce speckle noise in OCT. Experiments on real OCT images demonstrate that the proposed filter is competitive with other state-of-the-art speckle removal techniques and able to accurately preserve edges and structural details with small computational cost.

INTRAOPERATIVE SPECTRAL DOMAIN OPTICAL COHERENCE TOMOGRAPHY IMAGING AFTER INTERNAL LIMITING MEMBRANE PEELING IN IDIOPATHIC EPIRETINAL MEMBRANE WITH CONNECTING STRANDS

PURPOSE

To report the intraoperative optical coherence tomography findings in idiopathic epiretinal membrane (ERM) with connecting strands and to describe the postoperative outcomes.

METHODS

A retrospective, case series study within a prospective observational intraoperative optical coherence tomography imaging study was performed. Epiretinal membranes with connecting strands were characterized on preoperative spectral domain optical coherence tomography images and assessed against corresponding intraoperative (after internal limiting membrane [ILM] peeling) and postoperative spectral domain optical coherence tomography images.

RESULTS

Eleven locations of the connecting strands in 7 eyes were studied. The connecting strands had visible connections from the inner retinal surface to the ERM in all locations, and the reflectivity was moderate in 8 locations and high in 3 locations. After ERM and ILM peeling, disconnected strands were identified in all of the intraoperative optical coherence tomography images. The reflectivity of the remaining intraoperative strands was higher than that of the preoperative lesions and appeared as "finger-like" and branching projections. The remaining disconnected lesions were contiguous with the inner retinal layers. Postoperatively, the intraoperative lesions disappeared completely in all locations, and recurrent formation of ERM was not identified in any eyes.

CONCLUSION

In ERM eyes with connecting strands, intraoperative spectral domain optical coherence tomography imaging showed moderately to highly reflective sub-ILM finger-like lesions that persist immediately after membrane and ILM peeling. Postoperatively, the hyperreflective lesions disappeared spontaneously without localized nerve fiber layer loss. The sub-ILM connecting strands may represent glial retinal attachments.