Intraretinal layer segmentation of macular optical coherence tomography images using optimal 3-D graph search

Thinning of Macular Neuroretinal Layers Contributes to Sleep Disorder in Patients With Type 2 Diabetes Without Clinical Evidences of Neuropathy and Retinopathy

Aims: To investigate the impact of thinning at individual grids of macular neuroretinal layers, clinical factors, and inadequate light exposure on the specific components of sleep disorder in patients with type 2 diabetes. Methods: One hundred twenty-four patients with type 2 diabetes without clinical evidences of diabetic retinopathy and neuropathy (HbA1c: 8.3%, diabetes duration; 8.7 years) and 54 age- and sex-matched control subjects (HbA1c: 5.6%) underwent detailed clinical, neurological, and ophthalmological examinations. The sleep disorder was assessed by the Pittsburgh Sleep Quality Index Japanese Version (PSQI-J). The temporal structures of daily life were assessed by the Munich Chronotype Questionnaire Japanese Version. The thickness at nine grids defined by the Early Treatment Diabetic Retinopathy Study of nine macular neuroretinal layers was determined by swept-source optical coherence tomography and OCT-Explorer. The associations between the individual components of sleep disorders and the thickness at each grid of macular neuroretinal layers, clinical factors, or the temporal structures of daily life were examined. Results: The prevalence of the sleep disorder, global score, and four individual PSQI-J scores in patients with type 2 diabetes were higher than control subjects. The thickness of two and five grids of two inner retinal layers and four to seven grids of four outer retinal layers in patients with type 2 diabetes was thinner than those in control subjects. The thickness at one to eight grids of four outer retinal layers in type 2 diabetic patients was inversely associated with global score and five individual scores of sleep disorder. The thinning at one to two grids of the inner plexiform layer was related to three high individual scores of sleep disorder. The inappropriate light exposure was associated with the sleep disorder and altered macular neuroretinal layers. The high HbA1c and LDL-cholesterol levels were related to the high global score and two individual scores of sleep disorder, respectively. Conclusion: In patients with type 2 diabetes, the thinning at grids of the inner plexiform layer and outer retinal layers was associated with the high scores of specific components of the sleep disorder. The sleep disorder was also related to hyperglycemia, dyslipidemia, and inappropriate light exposure.

Distribution of macular ganglion cell layer thickness in foveal hypoplasia: A new diagnostic criterion for ocular albinism

Background/Aims

To analyse the distribution of macular ganglion cell layer thickness (GCLT) in patients with foveal hypoplasia (FH) with or without albinism to obtain new insights into visual pathway anomalies in albinos.

Methods

Patients with FH who presented at our institution between 2013 and 2018 were retrospectively drawn for analysis. Mean GCLT was calculated after automated segmentation of spectral domain-optical coherence tomography (SD-OCT) scans. Patients with FH due to albinism (n = 13, termed ‘albinism FH’) or other kinds (n = 10, termed ‘non-albinism FH’) were compared with control subjects (n = 15). The areas: fovea (central), parafovea (nasal I, temporal I) and perifovea (nasal II, temporal II) along the horizontal meridian were of particular interest. Primary endpoints of this study were the ratios (GCLT-I- and GCLT-II-Quotient) between the GCLT measured in the temporal I or II and nasal I or II areas.

Results

There was a significant difference between the GCLT-I-Quotient of healthy controls and albinism FH (p<0.001), as well as between non-albinism FH and albinism FH (p = 0.004). GCLT-II-Quotient showed significant differences between healthy controls and albinism FH (p<0.001) and between non-albinism FH and albinism FH (p = 0.006). The best measure for distinguishing between non-albinism FH and albinism FH was the calculation of GCLT-II-Quotient (area temporal II divided by area nasal II), indicating albinism at a cut-off of <0.7169. The estimated specificity and sensitivity for this cut-off were 84.6% and 100.0%, respectively. The estimated area under the curve (AUC) was 0.892 [95%CI: 0.743–1.000, p = 0.002].

Conclusion

Macular GCLT-distribution showed a characteristic temporal to central shift in patients with FH due to albinism. Calculation of the GCLT-II-Quotient at a cut-off of <0.7169 presents a new diagnostic criterion for identification of ocular albinism.

Automated segmentation of peripapillary retinal boundaries in OCT combining a convolutional neural network and a multi-weights graph search

Quantitative analysis of the peripapillary retinal layers and capillary plexuses from optical coherence tomography (OCT) and OCT angiography images depend on two segmentation tasks - delineating the boundary of the optic disc and delineating the boundaries between retinal layers. Here, we present a method combining a neural network and graph search to perform these two tasks. A comparison of this novel method's segmentation of the disc boundary showed good agreement with the ground truth, achieving an overall Dice similarity coefficient of 0.91 ± 0.04 in healthy and glaucomatous eyes. The absolute error of retinal layer boundaries segmentation in the same cases was 4.10 ± 1.25 µm.

Increasing Accuracy of Optimal Surfaces Using Min-Marginal Energies

Optimal surface methods are a class of graph cut methods posing surface estimation as an n-ary ordered labeling problem. They are used in medical imaging to find interacting and layered surfaces optimally and in low order polynomial time. Representing continuous surfaces with discrete sets of labels, however, leads to discretization errors and, if graph representations are made dense, excessive memory usage. Limiting memory usage and computation time of graph cut methods are important and graphs that locally adapt to the problem has been proposed as a solution. Min-marginal energies computed using dynamic graph cuts offer a way to estimate solution uncertainty and these uncertainties have been used to decide where graphs should be adapted. Adaptive graphs, however, introduce extra parameters, complexity, and heuristics. We propose a way to use min-marginal energies to estimate continuous solution labels that does not introduce extra parameters and show empirically on synthetic and medical imaging datasets that it leads to improved accuracy. The increase in accuracy was consistent and in many cases comparable with accuracy otherwise obtained with graphs up to eight times denser, but with proportionally less memory usage and improvements in computation time.

Segmentation of mouse skin layers in optical coherence tomography image data using deep convolutional neural networks

Optical coherence tomography (OCT) enables the non-invasive acquisition of high-resolution three-dimensional cross-sectional images at micrometer scale and is mainly used in the field of ophthalmology for diagnosis as well as monitoring of eye diseases. Also in other areas, such as dermatology, OCT is already well established. Due to its non-invasive nature, OCT is also employed for research studies involving animal models. Manual evaluation of OCT images of animal models is a challenging task due to the lack of imaging standards and the varying anatomy among models. In this paper, we present a deep learning algorithm for the automatic segmentation of several layers of mouse skin in OCT image data using a deep convolutional neural network (CNN). The architecture of our CNN is based on the U-net and is modified by densely connected convolutions. We compared our adapted CNN with our previous algorithm, a combination of a random forest classification and a graph-based refinement, and a baseline U-net. The results showed that, on average, our proposed CNN outperformed our previous algorithm and the baseline U-net. In addition, a reduction of outliers could be observed through the use of densely connected convolutions.

Diagnostic Capability of Three-Dimensional Macular Parameters for Glaucoma Using Optical Coherence Tomography Volume Scans

Purpose

To compare the diagnostic capability of three-dimensional (3D) macular parameters against traditional two-dimensional (2D) retinal nerve fiber layer (RNFL) thickness using spectral domain optical coherence tomography. To determine if manual correction and interpolation of B-scans improve the ability of 3D macular parameters to diagnose glaucoma.

Methods

A total of 101 open angle glaucoma patients (29 with early glaucoma) and 57 healthy subjects had peripapillary 2D RNFL thickness and 3D macular volume scans. Four parameters were calculated for six different-sized annuli: total macular thickness (M-thickness), total macular volume (M-volume), ganglion cell complex (GCC) thickness, and GCC volume of the innermost 3 macular layers (retinal nerve fiber layer + ganglion cell layer + inner plexiform layer). All macular parameters were calculated with and without correction and interpolation of frames with artifacts. The areas under the receiver operating characteristic curves (AUROC) were calculated for all the parameters.

Results

The 3D macular parameter with the best diagnostic performance was GCC-volume-34, with an inner diameter of 3 mm and an outer of 4 mm. The AUROC for RNFL thickness and GCC-volume-34 were statistically similar for all regions (global: RNFL thickness 0.956, GCC-volume-34 0.939, P value = 0.3827), except for the temporal GCC-volume-34, which was significantly better than temporal RNFL thickness (P value = 0.0067). Correction of artifacts did not significantly change the AUROC of macular parameters (P values between 0.8452 and 1.0000).

Conclusions

The diagnostic performance of best macular parameters (GCC-volume-34 and GCC-thickness-34) were similar to or better than 2D RNFL thickness. Manual correction of artifacts with data interpolation is unnecessary in the clinical setting.

Detection of retinal pigment epithelium detachment from OCT images using multiscale Gaussian filtering

Macular diseases, including neovascular age-related macular degeneration (nvAMD), are leading causes of irreversible blindness and visual impairment. One prominent feature of nvAMD is the detachment of the retinal pigment epithelium. The aim of this study is to implement an automated method for the segmentation of the pigment epithelial detachment (PED) using optical coherence tomography (OCT). OCT datasets from 8 patients with nvAMD were acquired during multiple sessions. At each session, 17 images with a resolution of 1020 × 640 pixels were obtained. The images were segmented using Gaussian filtering and template matching for the detection of the upper and lower border of the PED, respectively. The results of the method were compared with the ones obtained from the manual segmentation of the images by an expert. Four well-known metrics were used to evaluate the performance of the method with respect to the manual segmentation, resulting in high scores of consistency. Furthermore, the proposed method was also compared with four other well-known methods providing similar or superior performance.

Automatic Choroid Layer Segmentation from Optical Coherence Tomography Images Using Deep Learning

The choroid layer is a vascular layer in human retina and its main function is to provide oxygen and support to the retina. Various studies have shown that the thickness of the choroid layer is correlated with the diagnosis of several ophthalmic diseases. For example, diabetic macular edema (DME) is a leading cause of vision loss in patients with diabetes. Despite contemporary advances, automatic segmentation of the choroid layer remains a challenging task due to low contrast, inhomogeneous intensity, inconsistent texture and ambiguous boundaries between the choroid and sclera in Optical Coherence Tomography (OCT) images. The majority of currently implemented methods manually or semi-automatically segment out the region of interest. While many fully automatic methods exist in the context of choroid layer segmentation, more effective and accurate automatic methods are required in order to employ these methods in the clinical sector. This paper proposed and implemented an automatic method for choroid layer segmentation in OCT images using deep learning and a series of morphological operations. The aim of this research was to segment out Bruch's Membrane (BM) and choroid layer to calculate the thickness map. BM was segmented using a series of morphological operations, whereas the choroid layer was segmented using a deep learning approach as more image statistics were required to segment accurately. Several evaluation metrics were used to test and compare the proposed method against other existing methodologies. Experimental results showed that the proposed method greatly reduced the error rate when compared with the other state-of-the-art methods.

Automatic three-dimensional segmentation of endoscopic airway OCT images

Automatic delineation and segmentation of airway structures from endoscopic optical coherence tomography (OCT) images improve image analysis efficiency and thus has been of particular interest. Conventional two-dimensional automatic segmentation methods, such as the dynamic programming approach, ensures the edge-continuity in the xz-direction (intra-B-scan), but fails to preserve the surface-continuity when concerning the y-direction (inter-B-scan). To solve this, we present a novel automatic three-dimensional (3D) airway segmentation strategy. Our segmentation scheme includes an artifact-oriented pre-processing pipeline and a modified 3D optimal graph search algorithm incorporating adaptive tissue-curvature adjustment. The proposed algorithm is tested on endoscopic airway OCT image data sets acquired by different swept-source OCT platforms, and on different animal and human models. With our method, the results show continuous surface segmentation performance, which is both robust and accurate.

Fast esophageal layer segmentation in OCT images of guinea pigs based on sparse Bayesian classification and graph search

Endoscopic optical coherence tomography (OCT) devices are capable of generating high-resolution images of esophageal structures at high speed. To make the obtained data easy to interpret and reveal the clinical significance, an automatic segmentation algorithm is needed. This work proposes a fast algorithm combining sparse Bayesian learning and graph search (termed as SBGS) to automatically identify six layer boundaries on esophageal OCT images. The SBGS first extracts features, including multi-scale gradients, averages and Gabor wavelet coefficients, to train the sparse Bayesian classifier, which is used to generate probability maps indicating boundary positions. Given these probability maps, the graph search method is employed to create the final continuous smooth boundaries. The segmentation performance of the proposed SBGS algorithm was verified by esophageal OCT images from healthy guinea pigs and the eosinophilic esophagitis (EoE) models. Experiments confirmed that the SBGS method is able to implement robust esophageal segmentation for all the tested cases. In addition, benefiting from the sparse model of SBGS, the segmentation efficiency is significantly improved compared to other widely used techniques.

Automatic Segmentation of Retinal Layer in OCT Images With Choroidal Neovascularization

Age-related macular degeneration is one of the main causes of blindness. However, the internal structures of retinas are complex and difficult to be recognized due to the occurrence of neovascularization. Traditional surface detection methods may fail in the layer segmentation. In this paper, a supervised method is reported for simultaneously segmenting layers and neovascularization. Three spatial features, seven gray-level-based features, and 14 layer-like features are extracted for the neural network classifier. The coarse surfaces of different optical coherence tomography (OCT) images can thus be found. To describe and enhance retinal layers with different thicknesses and abnormalities, multi-scale bright and dark layer detection filters are introduced. A constrained graph search algorithm is also proposed to accurately detect retinal surfaces. The weights of nodes in the graph are computed based on these layer-like responses. The proposed method was evaluated on 42 spectral-domain OCT images with age-related macular degeneration. The experimental results show that the proposed method outperforms state-of-the-art methods.

Optic nerve head three-dimensional shape analysis

We present a method for optic nerve head (ONH) 3-D shape analysis from retinal optical coherence tomography (OCT). The possibility to noninvasively acquire in vivo high-resolution 3-D volumes of the ONH using spectral domain OCT drives the need to develop tools that quantify the shape of this structure and extract information for clinical applications. The presented method automatically generates a 3-D ONH model and then allows the computation of several 3-D parameters describing the ONH. The method starts with a high-resolution OCT volume scan as input. From this scan, the model-defining inner limiting membrane (ILM) as inner surface and the retinal pigment epithelium as outer surface are segmented, and the Bruch's membrane opening (BMO) as the model origin is detected. Based on the generated ONH model by triangulated 3-D surface reconstruction, different parameters (areas, volumes, annular surface ring, minimum distances) of different ONH regions can then be computed. Additionally, the bending energy (roughness) in the BMO region on the ILM surface and 3-D BMO-MRW surface area are computed. We show that our method is reliable and robust across a large variety of ONH topologies (specific to this structure) and present a first clinical application.

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.

Statistical Models of Signal and Noise and Fundamental Limits of Segmentation Accuracy in Retinal Optical Coherence Tomography

Optical coherence tomography (OCT) has revolutionized diagnosis and prognosis of ophthalmic diseases by visualization and measurement of retinal layers. To speed up the quantitative analysis of disease biomarkers, an increasing number of automatic segmentation algorithms have been proposed to estimate the boundary locations of retinal layers. While the performance of these algorithms has significantly improved in recent years, a critical question to ask is how far we are from a theoretical limit to OCT segmentation performance. In this paper, we present the Cramèr-Rao lower bounds (CRLBs) for the problem of OCT layer segmentation. In deriving the CRLBs, we address the important problem of defining statistical models that best represent the intensity distribution in each layer of the retina. Additionally, we calculate the bounds under an optimal affine bias, reflecting the use of prior knowledge in many segmentation algorithms. Experiments using in vivo images of human retina from a commercial spectral domain OCT system are presented, showing potential for improvement of automated segmentation accuracy. Our general mathematical model can be easily adapted for virtually any OCT system. Furthermore, the statistical models of signal and noise developed in this paper can be utilized for the future improvements of OCT image denoising, reconstruction, and many other applications.

Automated segmentation of retinal layer boundaries and capillary plexuses in wide-field optical coherence tomographic angiography

Advances in the retinal layer segmentation of structural optical coherence tomography (OCT) images have allowed the separation of capillary plexuses in OCT angiography (OCTA). With the increased scanning speeds of OCT devices and wider field images (≥10 mm on fast-axis), greater retinal curvature and anatomic variations have introduced new challenges. In this study, we developed a novel automated method to segment seven retinal layer boundaries and two retinal plexuses in wide-field OCTA images. The algorithm was initialized by a series of points forming a guidance point array that estimates the location of retinal layer boundaries. A guided bidirectional graph search method consisting of an improvement of our previous segmentation algorithm was used to search for the precise boundaries. We validated the method on normal and diseased eyes, demonstrating subpixel accuracy for all groups. By allowing independent visualization of the superficial and deep plexuses, this method shows potential for the detection of plexus-specific peripheral vascular abnormalities.

Quantified elasticity mapping of retinal layers using synchronized acoustic radiation force optical coherence elastography

Age-related macular degeneration (AMD) is the leading cause of blindness in the elderly (over the age of 60 years) in western countries. In the early stages of the disease, structural changes may be subtle and cannot be detected. Recently it has been postulated that the mechanical properties of the retina may change with the onset of AMD. In this manuscript, we present a novel, non-invasive means that utilizes synchronized acoustic radiation force optical coherence elastography (ARF-OCE) to measure and estimate the elasticity of cadaver porcine retina. Both regions near the optic nerve and in the peripheral retina were studied. An acoustic force is exerted on the tissue for excitation and the resulting tissue vibrations, often in the nanometer scale, are detected with high-resolution optical methods. Segmentation has been performed to isolate individual layers and the Young's modulus has been estimated for each. The results have been successfully compared and mapped to corresponding histological results using H&E staining. Finally, 64 elastograms of the retina were analyzed, as well as the elastic properties, with stiffness ranging from 1.3 to 25.9 kPa in the ganglion to the photoreceptor sides respectively. ARF-OCE allows for the elasticity mapping of anatomical retinal layers. This imaging approach needs further evaluation but has the potential to allow physicians to gain a better understanding of the elasticity of retinal layers in retinal diseases such as AMD.

Three-dimensional graph-based skin layer segmentation in optical coherence tomography images for roughness estimation

Automatic skin layer segmentation in optical coherence tomography (OCT) images is important for a topographic assessment of skin or skin disease detection. However, existing methods cannot deal with the problem of shadowing in OCT images due to the presence of hair, scales, etc. In this work, we propose a method to segment the topmost layer of the skin (or the skin surface) using 3D graphs with a novel cost function to deal with shadowing in OCT images. 3D graph cuts use context information across B-scans when segmenting the skin surface, which improves the segmentation as compared to segmenting each B-scan separately. The proposed method reduces the segmentation error by more than 20% as compared to the best performing related work. The method has been applied to roughness estimation and shows a high correlation with a manual assessment. Promising results demonstrate the usefulness of the proposed method for skin layer segmentation and roughness estimation in both normal OCT images and OCT images with shadowing.

Pixel-wise segmentation of severely pathologic retinal pigment epithelium and choroidal stroma using multi-contrast Jones matrix optical coherence tomography

Tissue segmentation of retinal optical coherence tomography (OCT) is widely used in ophthalmic diagnosis. However, its performance in severe pathologic cases is still insufficient. We propose a pixel-wise segmentation method that uses the multi-contrast measurement capability of Jones matrix OCT (JM-OCT). This method is applicable to both normal and pathologic retinal pigment epithelium (RPE) and choroidal stroma. In this method, "features," which are sensitive to specific tissues of interest, are synthesized by combining the multi-contrast images of JM-OCT, including attenuation coefficient, degree-of-polarization-uniformity, and OCT angiography. The tissue segmentation is done by simple thresholding of the feature. Compared with conventional segmentation methods for pathologic maculae, the proposed method is less computationally intensive. The segmentation method was validated by applying it to images from normal and severely pathologic cases. The segmentation results enabled the development of several types of en face visualizations, including melano-layer thickness maps, RPE elevation maps, choroidal thickness maps, and choroidal stromal attenuation coefficient maps. These facilitate close examination of macular pathology. The melano-layer thickness map is very similar to a near infrared fundus autofluorescence image, so the map can be used to identify the source of a hyper-autofluorescent signal.

Machine-learning based segmentation of the optic nerve head using multi-contrast Jones matrix optical coherence tomography with semi-automatic training dataset generation

A pixel-by-pixel tissue classification framework using multiple contrasts obtained by Jones matrix optical coherence tomography (JM-OCT) is demonstrated. The JM-OCT is an extension of OCT that provides OCT, OCT angiography, birefringence tomography, degree-of-polarization uniformity tomography, and attenuation coefficient tomography, simultaneously. The classification framework consists of feature engineering, k-means clustering that generates a training dataset, training of a tissue classifier using the generated training dataset, and tissue classification by the trained classifier. The feature engineering process generates synthetic features from the primary optical contrasts obtained by JM-OCT. The tissue classification is performed in the feature space of the engineered features. We applied this framework to the in vivo analysis of optic nerve heads of posterior eyes. This classified each JM-OCT pixel into prelamina, lamina cribrosa (lamina beam), and retrolamina tissues. The lamina beam segmentation results were further utilized for birefringence and attenuation coefficient analysis of lamina beam.

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.

EFFECT OF OPTIC DISK-FOVEA DISTANCE ON MEASUREMENTS OF INDIVIDUAL MACULAR INTRARETINAL LAYERS IN NORMAL SUBJECTS

PURPOSE

To investigate the effect of optic disk-fovea distance (DFD) on measurements of macular intraretinal layers using spectral domain optical coherence tomography in normal subjects.

METHODS

One hundred and eighty-two eyes from 182 normal subjects were imaged using spectral domain optical coherence tomography. The average thicknesses of eight macular intraretinal layers were measured using an automatic segmentation algorithm. Partial correlation test and multiple regression analysis were used to determine the effect of DFD on thicknesses of intraretinal layers.

RESULTS

Disk-fovea distance correlated negatively with the overall average thickness in all the intraretinal layers (r ≤ -0.17, all P ≤ 0.025) except the ganglion cell layer and photoreceptor. In multiple regression analysis, greater DFD was associated with thinner nerve fiber layer (6.78 μm decrease per each millimeter increase in DFD, P < 0.001), thinner ganglion cell-inner plexiform layer (2.16 μm decrease per each millimeter increase in DFD, P = 0.039), thinner ganglion cell complex (8.94 μm decrease per each millimeter increase in DFD, P < 0.001), thinner central macular thickness (18.16 μm decrease per each millimeter increase in DFD, P < 0.001), and thinner total macular thickness (15.94 μm decrease per each millimeter increase in DFD, P < 0.001).

CONCLUSION

Thinner measurements of macular intraretinal layers were significantly associated with greater DFD. A clinical assessment of macular intraretinal layers in the evaluation of various macular diseases should always be interpreted in the context of DFD.

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.

A Survey of Graph Cuts/Graph Search Based Medical Image Segmentation

Medical image segmentation is a fundamental and challenging problem for analyzing medical images. Among different existing medical image segmentation methods, graph-based approaches are relatively new and show good features in clinical applications. In the graph-based method, pixels or regions in the original image are interpreted into nodes in a graph. By considering Markov random field to model the contexture information of the image, the medical image segmentation problem can be transformed into a graph-based energy minimization problem. This problem can be solved by the use of minimum s-t cut/ maximum flow algorithm. This review is devoted to cut-based medical segmentation methods, including graph cuts and graph search for region and surface segmentation. Different varieties of cut-based methods, including graph-cuts-based methods, model integrated graph cuts methods, graph-search-based methods, and graph search/graph cuts based methods, are systematically reviewed. Graph cuts and graph search with deep learning technique are also discussed.

Segmentation of Retinal Cysts From Optical Coherence Tomography Volumes Via Selective Enhancement

Automated and accurate segmentation of cystoid structures in optical coherence tomography (OCT) is of interest in the early detection of retinal diseases. It is, however, a challenging task. We propose a novel method for localizing cysts in 3-D OCT volumes. The proposed work is biologically inspired and based on selective enhancement of the cysts, by inducing motion to a given OCT slice. A convolutional neural network is designed to learn a mapping function that combines the result of multiple such motions to produce a probability map for cyst locations in a given slice. The final segmentation of cysts is obtained via simple clustering of the detected cyst locations. The proposed method is evaluated on two public datasets and one private dataset. The public datasets include the one released for the OPTIMA cyst segmentation challenge (OCSC) in MICCAI 2015 and the DME dataset. After training on the OCSC train set, the method achieves a mean dice coefficient (DC) of 0.71 on the OCSC test set. The robustness of the algorithm was examined by cross validation on the DME and AEI (private) datasets and a mean DC values obtained were 0.69 and 0.79, respectively. Overall, the proposed system has the highest performance on all the benchmarks. These results underscore the strengths of the proposed method in handling variations in both data acquisition protocols and scanners.

A basis for customising perimetric locations within the macula in glaucoma

PURPOSE

It has been recognised that the 24-2 grid used for perimetry may poorly sample the macula, which has been recently identified as a critical region for diagnosing and managing patients with glaucoma. We compared data derived from patients and controls to investigate the efficacy of a basis for customising perimetric locations within the macula, guided by en face images of retinal nerve fibre layer (RNFL) bundles.

METHODS

We used SD-OCT en face montages (www.heidelbergengineering.com) of the RNFL in 10 patients with glaucoma (ages 56-80 years, median 67.5 years) and 30 age-similar controls (ages 47-77, median 58). These patients were selected because of either the absence of perimetric defect while glaucomatous damage to the RNFL bundles was observed, or because of perimetric defect that did not reflect the extent and locations of the glaucomatous damage that appeared in the RNFL images. We used a customised blob stimulus for perimetric testing (a Gaussian blob with 0.25° standard deviation) at 10-2 grid locations, to assess the correspondence between perimetric defects and damaged RNFL bundles observed on en face images and perimetric defects. Data from the age-similar controls were used to compute total deviation (TD) and pattern deviation (PD) values at each location; a perimetric defect for a location was defined as a TD or PD value of -0.5 log unit or deeper. A McNemar's test was used to compare the proportions of locations with perimetric defects that fell outside the damaged RNFL bundles, with and without accounting for displacement of ganglion cell bodies.

RESULTS

All patients but one had perimetric defects that were consistent with the patterns of damaged RNFL bundles observed on the en face images. We found six abnormal perimetric locations of 2040 tested in controls and 132 abnormal perimetric locations of 680 tested in patients. The proportions of abnormal locations that fell outside the damaged RNFL bundles, with and without accounting for displacement of the ganglion cell bodies were 0.08 and 0.07, respectively. The difference between the two proportions did not reach statistical significance (p = 0.5 for a one-tailed test).

CONCLUSIONS

We demonstrated that it is effective to customise perimetric locations within the macula, guided by en face images of the RNFL bundles. The perimetric losses found with a 10-2 grid demonstrated similar patterns as the damaged RNFL bundles observed on the en face images.

Bone marrow cavity segmentation using graph-cuts with wavelet-based texture feature

Emerging bioimaging technologies enable us to capture various dynamic cellular activities [Formula: see text]. As large amounts of data are obtained these days and it is becoming unrealistic to manually process massive number of images, automatic analysis methods are required. One of the issues for automatic image segmentation is that image-taking conditions are variable. Thus, commonly, many manual inputs are required according to each image. In this paper, we propose a bone marrow cavity (BMC) segmentation method for bone images as BMC is considered to be related to the mechanism of bone remodeling, osteoporosis, and so on. To reduce manual inputs to segment BMC, we classified the texture pattern using wavelet transformation and support vector machine. We also integrated the result of texture pattern classification into the graph-cuts-based image segmentation method because texture analysis does not consider spatial continuity. Our method is applicable to a particular frame in an image sequence in which the condition of fluorescent material is variable. In the experiment, we evaluated our method with nine types of mother wavelets and several sets of scale parameters. The proposed method with graph-cuts and texture pattern classification performs well without manual inputs by a user.

Avoiding Clinical Misinterpretation and Artifacts of Optical Coherence Tomography Analysis of the Optic Nerve, Retinal Nerve Fiber Layer, and Ganglion Cell Layer

Background:

Optical coherence tomography (OCT) has become an important tool for diagnosing optic nerve disease. The structural details and reproducibility of OCT continues to improve with further advances in technology. However, artifacts and misinterpretation of OCT can lead to clinical misdiagnosis of diseases if they go unrecognized.

Evidence Acquisition:

A literature review using PubMed combined with clinical and research experience.

Results:

We describe the most common artifacts and errors in interpretation seen on OCT in both optic nerve and ganglion cell analyses. We provide examples of the artifacts, discuss the causes, and provide methods of detecting them. In addition, we discuss a systematic approach to OCT analysis to facilitate the recognition of artifacts and to avoid clinical misinterpretation.

Conclusions:

While OCT is invaluable in diagnosing optic nerve disease, we need to be cognizant of the artifacts that can occur with OCT. Failure to recognize some of these artifacts can lead to misdiagnoses and inappropriate investigations.

Non-destructive analysis of flake properties in automotive paints with full-field optical coherence tomography and 3D segmentation

Automotive coating systems are designed to protect vehicle bodies from corrosion and enhance their aesthetic value. The number, size and orientation of small metallic flakes in the base coat of the paint has a significant effect on the appearance of automotive bodies. It is important for quality assurance (QA) to be able to measure the properties of these small flakes, which are approximately 10μm in radius, yet current QA techniques are limited to measuring layer thickness. We design and develop a time-domain (TD) full-field (FF) optical coherence tomography (OCT) system to scan automotive panels volumetrically, non-destructively and without contact. We develop and integrate a segmentation method to automatically distinguish flakes and allow measurement of their properties. We test our integrated system on nine sections of five panels and demonstrate that this integrated approach can characterise small flakes in automotive coating systems in 3D, calculating the number, size and orientation accurately and consistently. This has the potential to significantly impact QA testing in the automotive industry.

Fully Automated Segmentation of Fluid/Cyst Regions in Optical Coherence Tomography Images With Diabetic Macular Edema Using Neutrosophic Sets and Graph Algorithms

This paper presents a fully automated algorithm to segment fluid-associated (fluid-filled) and cyst regions in optical coherence tomography (OCT) retina images of subjects with diabetic macular edema. The OCT image is segmented using a novel neutrosophic transformation and a graph-based shortest path method. In neutrosophic domain, an image is transformed into three sets: (true), (indeterminate) that represents noise, and (false). This paper makes four key contributions. First, a new method is introduced to compute the indeterminacy set , and a new -correction operation is introduced to compute the set in neutrosophic domain. Second, a graph shortest-path method is applied in neutrosophic domain to segment the inner limiting membrane and the retinal pigment epithelium as regions of interest (ROI) and outer plexiform layer and inner segment myeloid as middle layers using a novel definition of the edge weights . Third, a new cost function for cluster-based fluid/cyst segmentation in ROI is presented which also includes a novel approach in estimating the number of clusters in an automated manner. Fourth, the final fluid regions are achieved by ignoring very small regions and the regions between middle layers. The proposed method is evaluated using two publicly available datasets: Duke, Optima, and a third local dataset from the UMN clinic which is available online. The proposed algorithm outperforms the previously proposed Duke algorithm by 8% with respect to the dice coefficient and by 5% with respect to precision on the Duke dataset, while achieving about the same sensitivity. Also, the proposed algorithm outperforms a prior method for Optima dataset by 6%, 22%, and 23% with respect to the dice coefficient, sensitivity, and precision, respectively. Finally, the proposed algorithm also achieves sensitivity of 67.3%, 88.8%, and 76.7%, for the Duke, Optima, and the university of minnesota (UMN) datasets, respectively.

Algorithms for the Automated Analysis of Age-Related Macular Degeneration Biomarkers on Optical Coherence Tomography: A Systematic Review

PURPOSE

To assess the quality of optical coherence tomography (OCT) grading algorithms for retinal biomarkers of age-related macular degeneration (AMD).

METHODS

Following a systematic review of the literature data on detection and quantification of AMD retinal biomarkers by available algorithms were extracted and descriptively synthesized. Algorithm quality was assessed using a modified version of the Quality Assessment of Diagnostic Accuracy Studies 2 checklist with a focus on accuracy against established reference standards and risk of bias.

RESULTS

Thirty five studies reporting computer-aided diagnosis (CAD) tools for qualitative analysis or algorithms for quantitative analysis were identified. Compared with manual assessment in reference standards correlation coefficients ranged from 0.54 to 0.97 for drusen, 0.80 to 0.98 for geographic atrophy (GA), and 0.30 to 0.98 for intra- or subretinal fluid and pigment epithelial detachment (PED) detection by automated algorithms. CAD tools achieved area under the curve (AUC) values of 0.94 to 0.99, sensitivity of 0.90 to 1.00, and specificity of 0.89 to 0.92.

CONCLUSIONS

Automated analysis of AMD biomarkers on OCT is promising. However, most of the algorithm validation was performed in preselected patients, exhibiting the targeted biomarker only. In addition, type and quality of reported algorithm validation varied substantially.

TRANSLATIONAL RELEVANCE

The development of algorithms for combined, simultaneous analysis of multiple AMD biomarkers including AMD staging and the agreement on standardized validation procedures would be of considerable translational value for the clinician and the clinical researcher.

Robust total retina thickness segmentation in optical coherence tomography images using convolutional neural networks

We developed a fully automated system using a convolutional neural network (CNN) for total retina segmentation in optical coherence tomography (OCT) that is robust to the presence of severe retinal pathology. A generalized U-net network architecture was introduced to include the large context needed to account for large retinal changes. The proposed algorithm outperformed qualitative and quantitatively two available algorithms. The algorithm accurately estimated macular thickness with an error of 14.0 ± 22.1 µm, substantially lower than the error obtained using the other algorithms (42.9 ± 116.0 µm and 27.1 ± 69.3 µm, respectively). These results highlighted the proposed algorithm's capability of modeling the wide variability in retinal appearance and obtained a robust and reliable retina segmentation even in severe pathological cases.

A Framework for Classification and Segmentation of Branch Retinal Artery Occlusion in SD-OCT

Branch retinal artery occlusion (BRAO) is an ocular emergency, which could lead to blindness. Quantitative analysis of the BRAO region in the retina is necessary for the assessment of the severity of retinal ischemia. In this paper, a fully automatic framework was proposed to segment BRAO regions based on 3D spectral-domain optical coherence tomography (SD-OCT) images. To the best of our knowledge, this is the first automatic 3D BRAO segmentation framework. First, the input 3D image is automatically classified into BRAO of acute phase and BRAO of chronic phase or normal retina using an AdaBoost classifier based on combining local structural, intensity, textural features with our new feature distribution analyzing strategy. Then, BRAO regions of acute phase and chronic phase are segmented separately. A thickness model is built to segment BRAO in the chronic phase. While for segmenting BRAO in the acute phase, a two-step segmentation strategy is performed: rough initialization and refine segmentation. The proposed method was tested on SD-OCT images of 35 patients (12 BRAO acute phase, 11 BRAO chronic phase, and 12 normal eyes) using the leave-one-out strategy. The classification accuracy for BRAO acute phase, BRAO chronic phase, and normal retina were 100%, 90.9%, and 91.7%, respectively. The overall true positive volume fraction (TPVF) and false positive volume fraction (FPVF) for the acute phase were 91.1% and 5.5% and for the chronic phase were 92.7% and 8.4%, respectively.

The Pattern of Visual Fixation Eccentricity and Instability in Optic Neuropathy and Its Spatial Relationship to Retinal Ganglion Cell Layer Thickness

Purpose

The purpose of this study was to assess whether clinically useful measures of fixation instability and eccentricity can be derived from retinal tracking data obtained during optical coherence tomography (OCT) in patients with optic neuropathy (ON) and to develop a method for relating fixation to the retinal ganglion cell complex (GCC) thickness.

Methods

Twenty-nine patients with ON underwent macular volume OCT with 30 seconds of confocal scanning laser ophthalmoscope (cSLO)-based eye tracking during fixation. Kernel density estimation quantified fixation instability and fixation eccentricity from the distribution of fixation points on the retina. Preferred ganglion cell layer loci (PGCL) and their relationship to the GCC thickness map were derived, accounting for radial displacement of retinal ganglion cell soma from their corresponding cones.

Results

Fixation instability was increased in ON eyes (0.21 deg²) compared with normal eyes (0.06982 deg²; P < 0.001), and fixation eccentricity was increased in ON eyes (0.48°) compared with normal eyes (0.24°; P = 0.03). Fixation instability and eccentricity each correlated moderately with logMAR acuity and were highly predictive of central visual field loss. Twenty-six of 35 ON eyes had PGCL skewed toward local maxima of the GCC thickness map. Patients with bilateral dense central scotomas had PGCL in homonymous retinal locations with respect to the fovea.

Conclusions

Fixation instability and eccentricity measures obtained during cSLO-OCT assess the function of perifoveal retinal elements and predict central visual field loss in patients with ON. A model relating fixation to the GCC thickness map offers a method to assess the structure–function relationship between fixation and areas of preserved GCC in patients with ON.

Machine learning techniques for diabetic macular edema (DME) classification on SD-OCT images

BACKGROUND

Spectral domain optical coherence tomography (OCT) (SD-OCT) is most widely imaging equipment used in ophthalmology to detect diabetic macular edema (DME). Indeed, it offers an accurate visualization of the morphology of the retina as well as the retina layers.

METHODS

The dataset used in this study has been acquired by the Singapore Eye Research Institute (SERI), using CIRRUS TM (Carl Zeiss Meditec, Inc., Dublin, CA, USA) SD-OCT device. The dataset consists of 32 OCT volumes (16 DME and 16 normal cases). Each volume contains 128 B-scans with resolution of 1024 px × 512 px, resulting in more than 3800 images being processed. All SD-OCT volumes are read and assessed by trained graders and identified as normal or DME cases based on evaluation of retinal thickening, hard exudates, intraretinal cystoid space formation, and subretinal fluid. Within the DME sub-set, a large number of lesions has been selected to create a rather complete and diverse DME dataset. This paper presents an automatic classification framework for SD-OCT volumes in order to identify DME versus normal volumes. In this regard, a generic pipeline including pre-processing, feature detection, feature representation, and classification was investigated. More precisely, extraction of histogram of oriented gradients and local binary pattern (LBP) features within a multiresolution approach is used as well as principal component analysis (PCA) and bag of words (BoW) representations.

RESULTS AND CONCLUSION

Besides comparing individual and combined features, different representation approaches and different classifiers are evaluated. The best results are obtained for LBP[Formula: see text] vectors while represented and classified using PCA and a linear-support vector machine (SVM), leading to a sensitivity(SE) and specificity (SP) of 87.5 and 87.5%, respectively.

Segmentation of Locally Varying Numbers of Outer Retinal Layers by a Model Selection Approach

Extraction of image-based biomarkers, such as the presence, visibility, or thickness of a certain layer, from 3-D optical coherence tomography data provides relevant clinical information. We present a method to simultaneously determine the number of visible layers in the outer retina and segment them. The method is based on a model selection approach with special attention given to the balance between the quality of a fit and model complexity. This will ensure that a more complex model is selected only if this is sufficiently supported by the data. The performance of the method was evaluated on healthy and retinitis pigmentosa (RP) affected eyes. In addition, the reproducibility of automatic method and manual annotations was evaluated on healthy eyes. Good agreement between the segmentation performed manually by a medical doctor and results obtained from the automatic segmentation was found. The mean unsigned deviation for all outer retinal layers in healthy and RP affected eyes varied between 2.6 and 4.9 μm. The reproducibility of the automatic method was similar to the reproducibility of the manual segmentation. Overall, the method provides a flexible and accurate solution for determining the visibility and location of outer retinal layers and could be used as an aid for the disease diagnosis and monitoring.

Joint Segmentation of Retinal Layers and Focal Lesions in 3-D OCT Data of Topologically Disrupted Retinas

Accurate quantification of retinal structures in 3-D optical coherence tomography data of eyes with pathologies provides clinically relevant information. We present an approach to jointly segment retinal layers and lesions in eyes with topology-disrupting retinal diseases by a loosely coupled level set framework. In the new approach, lesions are modeled as an additional space-variant layer delineated by auxiliary interfaces. Furthermore, the segmentation of interfaces is steered by local differences in the signal between adjacent retinal layers, thereby allowing the approach to handle local intensity variations. The accuracy of the proposed method of both layer and lesion segmentation has been evaluated on eyes affected by central serous retinopathy and age-related macular degeneration. In addition, layer segmentation of the proposed approach was evaluated on eyes without topology-disrupting retinal diseases. Good agreement between the segmentation performed manually by a medical doctor and results obtained from the automatic segmentation was found for all data types. The mean unsigned error for all interfaces varied between 2.3 and 11.9 μm (0.6-3.1 pixels). Furthermore, lesion segmentation showed a Dice coefficient of 0.68 for drusen and 0.89 for fluid pockets. Overall, the method provides a flexible and accurate solution to jointly segment lesions and retinal layers.

Automatic and robust segmentation of endoscopic OCT images and optical staining

We report a generic method for automatic segmentation of endoscopic optical coherence tomography (OCT) images. In this method, OCT images are first processed with L₁ -L₀ norm minimization based de-noising and smoothing algorithms to increase the signal-to-noise ratio (SNR) and enhance the contrast between adjacent layers. The smoothed images are then formulated into cost graphs based on their vertical gradients. After that, tissue-layer segmentation is performed with the shortest path search algorithm. The efficacy and capability of this method are demonstrated by automatically and robustly identifying all five interested layers of guinea pig esophagus from in vivo endoscopic OCT images. Furthermore, thanks to the ultrahigh resolution, high SNR of endoscopic OCT images and the high segmentation accuracy, this method permits in vivo optical staining histology and facilitates quantitative analysis of tissue geometric properties, which can be very useful for studying tissue pathologies and potentially aiding clinical diagnosis in real time.

Automatic Subretinal Fluid Segmentation of Retinal SD-OCT Images With Neurosensory Retinal Detachment Guided by Enface Fundus Imaging

OBJECTIVE

Accurate segmentation of neurosensory retinal detachment (NRD) associated subretinal fluid in spectral domain optical coherence tomography (SD-OCT) is vital for the assessment of central serous chorioretinopathy (CSC). A novel two-stage segmentation algorithm was proposed, guided by Enface fundus imaging.

METHODS

In the first stage, Enface fundus image was segmented using thickness map prior to detecting the fluid-associated abnormalities with diffuse boundaries. In the second stage, the locations of the abnormalities were used to restrict the spatial extent of the fluid region, and a fuzzy level set method with a spatial smoothness constraint was applied to subretinal fluid segmentation in the SD-OCT scans.

RESULTS

Experimental results from 31 retinal SD-OCT volumes with CSC demonstrate that our method can achieve a true positive volume fraction (TPVF), false positive volume fraction (FPVF), and positive predicative value (PPV) of 94.3%, 0.97%, and 93.6%, respectively, for NRD regions. Our approach can also discriminate NRD-associated subretinal fluid from subretinal pigment epithelium fluid associated with pigment epithelial detachment with a TPVF, FPVF, and PPV of 93.8%, 0.40%, and 90.5%, respectively.

CONCLUSION

We report a fully automatic method for the segmentation of subretinal fluid.

SIGNIFICANCE

Our method shows the potential to improve clinical therapy for CSC.

Handheld optical coherence tomography angiography

We developed a handheld optical coherence tomography angiography (OCTA) system using a 100-kHz swept-source laser. The handheld probe weighs 0.4 kg and measures 20.6 × 12.8 × 4.6 cm³. The system has dedicated features for handheld operation. The probe is equipped with a mini iris camera for easy alignment. Real-time display of the en face OCT and cross-sectional OCT images in the system allows accurately locating the imaging target. Fast automatic focusing was achieved by an electrically tunable lens controlled by a golden-section search algorithm. An extended axial imaging range of 6 mm allows easy alignment. A registration algorithm using cross-correlation to register adjacent OCT B-frames with propagation from the central frame was used to effectively minimize motion artifacts in volumetric OCTA images captured in relatively short durations of 1 and 2.1 seconds. 2.5 × 2.5 mm (200 × 200 pixels) and 3.5 × 3.5 mm (300 × 300 pixels) retinal angiograms were demonstrated on two awake adult human subjects without the use of any mydriatic eye drops.

Ganglion cell-inner plexiform layer and retinal nerve fiber layer thickness according to myopia and optic disc area: a quantitative and three-dimensional analysis

Background

To determine the influences of myopia and optic disc size on ganglion cell-inner plexiform layer (GCIPL) and peripapillary retinal nerve fiber layer (RNFL) thickness profiles obtained by spectral domain optical coherence tomography (OCT).

Methods

One hundred and sixty-eight eyes of 168 young myopic subjects were recruited and assigned to one of three groups according to their spherical equivalent (SE) values and optic disc area. All underwent Cirrus HD-OCT imaging. The influences of myopia and optic disc size on the GCIPL and RNFL thickness profiles were evaluated by multiple comparisons and linear regression analysis. Three-dimensional surface plots of GCIPL and RNFL thickness corresponding to different combinations of myopia and optic disc size were constructed.

Results

Each of the quadrant RNFL thicknesses and their overall average were significantly thinner in high myopia compared to low myopia, except for the temporal quadrant (all Ps ≤0.003). The average and all-sectors GCIPL were significantly thinner in high myopia than in moderate- and/or low-myopia (all Ps ≤0.002). The average OCT RNFL thickness was correlated significantly with SE (0.81 μm/diopter, P < 0.001), axial length (-1.44 μm/mm, P < 0.001), and optic disc area (5.35 μm/mm², P < 0.001) by linear regression analysis. As for the OCT GCIPL parameters, average GCIPL thickness showed a significant correlation with SE (0.84 μm/diopter, P < 0.001) and axial length (-1.65 μm/mm, P < 0.001). There was no significant correlation of average GCIPL thickness with optic disc area. Three-dimensional curves showed that larger optic discs were associated with increased average RNFL thickness and that more-myopic eyes were associated with decreased average GCIPL and RNFL thickness.

Conclusion

Myopia can significantly affect GCIPL and RNFL thickness profiles, and optic disc size has a significant influence on RNFL thickness. The current OCT maps employed in the evaluation of glaucoma should be analyzed in consideration of refractive status and optic disc size.

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.

Automated boundary detection of the optic disc and layer segmentation of the peripapillary retina in volumetric structural and angiographic optical coherence tomography

To improve optic disc boundary detection and peripapillary retinal layer segmentation, we propose an automated approach for structural and angiographic optical coherence tomography. The algorithm was performed on radial cross-sectional B-scans. The disc boundary was detected by searching for the position of Bruch's membrane opening, and retinal layer boundaries were detected using a dynamic programming-based graph search algorithm on each B-scan without the disc region. A comparison of the disc boundary using our method with that determined by manual delineation showed good accuracy, with an average Dice similarity coefficient ≥0.90 in healthy eyes and eyes with diabetic retinopathy and glaucoma. The layer segmentation accuracy in the same cases was on average less than one pixel (3.13 μm).

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.

A Digital Staining Algorithm for Optical Coherence Tomography Images of the Optic Nerve Head

Purpose

To digitally stain spectral-domain optical coherence tomography (OCT) images of the optic nerve head (ONH), and highlight either connective or neural tissues.

Methods

OCT volumes of the ONH were acquired from one eye of 10 healthy subjects. We processed all volumes with adaptive compensation to remove shadows and enhance deep tissue visibility. For each ONH, we identified the four most dissimilar pixel-intensity histograms, each of which was assumed to represent a tissue group. These four histograms formed a vector basis on which we ‘projected' each OCT volume in order to generate four digitally stained volumes P1 to P4. Digital staining was also verified using a digital phantom, and compared with k-means clustering for three and four clusters.

Results

Digital staining was able to isolate three regions of interest from the proposed phantom. For the ONH, the digitally stained images P1 highlighted mostly connective tissues, as demonstrated through an excellent contrast increase across the anterior lamina cribrosa boundary (3.6 ± 0.6 times). P2 highlighted the nerve fiber layer and the prelamina, P3 the remaining layers of the retina, and P4 the image background. Further, digital staining was able to separate ONH tissue layers that were not well separated by k-means clustering.

Conclusion

We have described an algorithm that can digitally stain connective and neural tissues in OCT images of the ONH.

Translational Relevance

Because connective and neural tissues are considerably altered in glaucoma, digital staining of the ONH tissues may be of interest in the clinical management of this pathology.