Multivariate Statistical Modeling of Retinal Optical Coherence Tomography

Optical coherence tomography image despeckling based on tensor singular value decomposition and fractional edge detection

Optical coherence tomography (OCT) imaging is a technique that is frequently used to diagnose medical conditions. However, coherent noise, sometimes referred to as speckle noise, can dramatically reduce the quality of OCT images, which has an adverse effect on how OCT images are used. In order to enhance the quality of OCT images, a speckle noise reduction technique is developed, and this method is modelled as a low-rank tensor approximation issue. The grouped 3D tensors are first transformed into the transform domain using tensor singular value decomposition (t-SVD). Then, to cut down on speckle noise, transform coefficients are thresholded. Finally, the inverse transform can be used to produce images with speckle suppression. To further enhance the despeckling results, a feature-guided thresholding approach based on fractional edge detection and an adaptive backward projection technique are also presented. Experimental results indicate that the presented algorithm outperforms several comparison methods in relation to speckle suppression, objective metrics, and edge preservation.

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.

Classification-based framework for binarization on mice eye image in vivo with optical coherence tomography

Optical coherence tomography (OCT) angiography has drawn much attention in the medical imaging field. Binarization plays an important role in quantitative analysis of eye with optical coherence tomography. To address the problem of few training samples and contrast-limited scene, we proposed a new binarization framework with specific-patch SVM (SPSVM) for low-intensity OCT image, which is open and classification-based framework. This new framework contains two phases: training model and binarization threshold. In the training phase, firstly, the patches of target and background from few training samples are extracted as the ROI and the background, respectively. Then, PCA is conducted on all patches to reduce the dimension and learn the eigenvector subspace. Finally, the classification model is trained from the features of patches to get the target value of different patches. In the testing phase, the learned eigenvector subspace is conducted on the pixels of each patch. The binarization threshold of patch is obtained with the learned SVM model. We acquire a new OCT mice eye (OCT-ME) database, which is publicly available at https://mip2019.github.io/spsvm. Extensive experiments were performed to demonstrate the effectiveness of the proposed SPSVM framework.

Statistical analysis of corneal OCT speckle: a non-parametric approach

In biomedical optics, it is often of interest to statistically model the amplitude of the speckle using some distributional approximations with their parameters acting as biomarkers. In this paper, a paradigm shift is being advocated in which non-parametric approaches are used. Specifically, a range of distances, evaluated in different domains, between an empirical non-parametric distribution of the normalized speckle amplitude sample and the benchmark Rayleigh distribution, is considered. Using OCT images from phantoms, two ex-vivo experiments with porcine corneas and an in-vivo experiment with human corneas, an evidence is provided that the non-parametric approach, despite its simplicity, could lead to equivalent or better results than the parametric approaches with distributional approximations. Concluding, in practice, the non-parametric approach should be considered as the first choice to speckle modeling before a particular distributional approximation is utilized.

Noise-Powered Disentangled Representation for Unsupervised Speckle Reduction of Optical Coherence Tomography Images

Due to its noninvasive character, optical coherence tomography (OCT) has become a popular diagnostic method in clinical settings. However, the low-coherence interferometric imaging procedure is inevitably contaminated by heavy speckle noise, which impairs both visual quality and diagnosis of various ocular diseases. Although deep learning has been applied for image denoising and achieved promising results, the lack of well-registered clean and noisy image pairs makes it impractical for supervised learning-based approaches to achieve satisfactory OCT image denoising results. In this paper, we propose an unsupervised OCT image speckle reduction algorithm that does not rely on well-registered image pairs. Specifically, by employing the ideas of disentangled representation and generative adversarial network, the proposed method first disentangles the noisy image into content and noise spaces by corresponding encoders. Then, the generator is used to predict the denoised OCT image with the extracted content features. In addition, the noise patches cropped from the noisy image are utilized to facilitate more accurate disentanglement. Extensive experiments have been conducted, and the results suggest that our proposed method is superior to the classic methods and demonstrates competitive performance to several recently proposed learning-based approaches in both quantitative and qualitative aspects. Code is available at: https://github.com/tsmotlp/DRGAN-OCT.

Statistical modeling of retinal optical coherence tomography using the Weibull mixture model

In this paper, a novel statistical model is proposed for retinal optical coherence tomography (OCT) images. According to the layered structure of the retina, a mixture of six Weibull distributions is proposed to describe the main statistical features of OCT images. We apply Weibull distribution to establish a more comprehensive model but with fewer parameters that has better goodness of fit (GoF) than previous models. Our new model also takes care of features such as asymmetry and heavy-tailed nature of the intensity distribution of retinal OCT data. In order to test the effectiveness of this new model, we apply it to improve the low quality of the OCT images. For this purpose, the spatially constrained Gaussian mixture model (SCGMM) is implemented. Since SCGMM is designed for data with Gaussian distribution, we convert our Weibull mixture model to a Gaussian mixture model using histogram matching before applying SCGMM. The denoising results illustrate the remarkable performance in terms of the contrast to noise ratio (CNR) and texture preservation (TP) compared to other peer methods. In another test to evaluate the efficiency of our proposed model, the parameters and GoF criteria are considered as a feature vector for support vector machine (SVM) to classify the healthy retinal OCT images from pigment epithelial detachment (PED) disease. The confusion matrix demonstrates the impact of the proposed model in our preliminary study on the OCT classification problem.

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.