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

OCT-Leakage Mapping: A New Automated Method of OCT Data Analysis to Identify and Locate Abnormal Fluid in Retinal Edema

PURPOSE

To test OCT-Leakage, a new method of analyzing and mapping sites of lower optical reflectivity found on OCT, by examining eyes with various types of retinal edema to identify abnormal increases in retinal extracellular fluid.

DESIGN

Prospective analysis of a cohort of cases.

PARTICIPANTS

Healthy eyes and eyes with retinal edema in the setting of different retinal diseases.

METHODS

Prospective OCT-Leakage analysis of 12 eyes with various types of retinal edema, such as diabetic macular edema, branch retinal vein occlusion, idiopathic perifoveal telangiectasia, and Irvine-Gass syndrome, representing intraretinal edema and eyes with idiopathic central serous chorioretinopathy and neovascular age-related macular degeneration representing subretinal fluid accumulation, in order to compare with OCT-Leakage analysis of a series of 41 eyes of 24 healthy controls. Raw scan data from the OCT images were exported and used to calculate lower than normal optical reflectivity maps (low optical reflectivity [LOR] ratios). Optical reflectivity LOR maps (OCT-Leakage maps) were collected for the full retina A-scan and layer by layer after segmentation. Low optical reflectivity ratios from patients with the different conditions of retinal edema and controls were compared. Fluorescein angiography (FA) and OCT angiography (OCTA) were performed in all eyes.

MAIN OUTCOME MEASURES

Identification of areas of abnormal retinal fluid accumulation.

RESULTS

The OCT-Leakage maps based on sites of LOR (LOR ratios) delineated the location of intraretinal and subretinal fluid, always integrating the location of the sites on FA and the vascular abnormalities observed on OCTA. The areas of fluid outline in the OCT-Leakage maps were coincident and generally larger than those seen on FA. In all cases, the OCT-Leakage maps were able to identify the location of the fluid in the different segmented retinal layers.

CONCLUSIONS

Mapping of lower reflectivity sites within the retina demonstrates the amount and location of retinal and subretinal fluid in different retinal diseases, showing potential to contribute to their management. Furthermore, the possibility of complementarity between OCT-Leakage and OCTA is highly promising.

Evaluating Efficacy of Aflibercept in Refractory Exudative Age-Related Macular Degeneration With OCT Segmentation Volumetric Analysis

BACKGROUND AND OBJECTIVE

To use automated segmentation software to analyze spectral-domain optical coherence tomography (SD-OCT) scans and evaluate the effectiveness of aflibercept (Eylea; Regeneron, Tarrytown, NY) in the treatment of patients with exudative age-related macular degeneration (AMD) refractory to other treatments.

PATIENTS AND METHODS

Retrospective chart review of 16 patients refractory to bevacizumab (Avastin; Genentech, South San Francisco, CA)/ranibizumab (Lucentis; Genentech, San Francisco, CA) treatment was conducted. Visual acuity, central foveal thickness (CFT), maximum fluid height, pigment epithelial detachment (PED) volume, sub-retinal fluid (SRF) volume, fluid-free time interval, and adverse effects were evaluated. Automated segmentation analysis was used to quantify improvement.

RESULTS

With aflibercept treatment, there was a statistically significant improvement in visual acuity by 1 line (P = .020), in CFT by 74.02 µm (P = .001), and in maximum fluid height by 31.9 µm (P= .011). Total PED and SRF volume also decreased significantly by 1.50 µm(3) × 10(8) µm(3) (P = .013). Anatomic improvement was confirmed by automated segmentation analysis.

CONCLUSION

This study demonstrates utility of automated segmentation software in quantifying anatomic improvement with aflibercept treatment in exudative AMD refractory to other anti-vascular endothelial growth factor treatments.

Machine learning based detection of age-related macular degeneration (AMD) and diabetic macular edema (DME) from optical coherence tomography (OCT) images

Non-lethal macular diseases greatly impact patients' life quality, and will cause vision loss at the late stages. Visual inspection of the optical coherence tomography (OCT) images by the experienced clinicians is the main diagnosis technique. We proposed a computer-aided diagnosis (CAD) model to discriminate age-related macular degeneration (AMD), diabetic macular edema (DME) and healthy macula. The linear configuration pattern (LCP) based features of the OCT images were screened by the Correlation-based Feature Subset (CFS) selection algorithm. And the best model based on the sequential minimal optimization (SMO) algorithm achieved 99.3% in the overall accuracy for the three classes of samples.

GANGLION CELL LAYER THICKNESS AND VISUAL IMPROVEMENT AFTER EPIRETINAL MEMBRANE SURGERY

PURPOSE

To evaluate the possible prognostic value of preoperative individual retinal layer thicknesses measured by an automated algorithm from spectral domain optical coherence tomography and visual acuity or improvement after epiretinal membrane surgery.

METHODS

Data from 76 eyes with idiopathic epiretinal membrane that underwent pars plana vitrectomy for idiopathic epiretinal membrane removal were analyzed. The preoperative thicknesses of the ganglion cell layer, inner plexiform layer, and other layers were measured using the Iowa Reference Algorithm. Each retinal layer thickness and its ratio of the central foveal thickness were compared between eyes with (Group 1) or without (Group 2) 2 or more Snellen lines of visual improvement at 3, 6, and 12 months after surgery.

RESULTS

Higher mean central foveal thickness/ganglion cell layer ratio and symptom duration of ≤1 year were significantly more common in Group 1 (P = 0.03 and 0.04, respectively). After adjusting for age and symptom duration, lens status, and preoperative visual acuity, higher central foveal thickness/ganglion cell layer ratio was associated with ≥2 lines of visual improvement after surgery (odds ratio: 6.57, 95% confidence interval: 1.29-33.40).

CONCLUSION

The preoperative inner retinal layer changes may have a role independent of outer retinal layer parameters in the visual prognosis after epiretinal membrane peeling.

Atlas-based shape analysis and classification of retinal optical coherence tomography images using the functional shape (fshape) framework

We propose a novel approach for quantitative shape variability analysis in retinal optical coherence tomography images using the functional shape (fshape) framework. The fshape framework uses surface geometry together with functional measures, such as retinal layer thickness defined on the layer surface, for registration across anatomical shapes. This is used to generate a population mean template of the geometry-function measures from each individual. Shape variability across multiple retinas can be measured by the geometrical deformation and functional residual between the template and each of the observations. To demonstrate the clinical relevance and application of the framework, we generated atlases of the inner layer surface and layer thickness of the Retinal Nerve Fiber Layer (RNFL) of glaucomatous and normal subjects, visualizing detailed spatial pattern of RNFL loss in glaucoma. Additionally, a regularized linear discriminant analysis classifier was used to automatically classify glaucoma, glaucoma-suspect, and control cases based on RNFL fshape metrics.

Classification of SD-OCT volumes with multi pyramids, LBP and HOG descriptors: application to DME detections

This paper deals with the automated detection of Diabetic Macular Edema (DME) on Optical Coherence Tomography (OCT) volumes. Our method considers a generic classification pipeline with preprocessing for noise removal and flattening of each B-Scan. Features such as Histogram of Oriented Gradients (HOG) and Local Binary Patterns (LBP) are extracted and combined to create a set of different feature vectors which are fed to a linear-Support Vector Machines (SVM) Classifier. Experimental results show a promising sensitivity/specificity of 0.75/0.87 on a challenging dataset.

A Review of Adaptive Optics Optical Coherence Tomography: Technical Advances, Scientific Applications, and the Future

PURPOSE

Optical coherence tomography (OCT) has enabled "virtual biopsy" of the living human retina, revolutionizing both basic retina research and clinical practice over the past 25 years. For most of those years, in parallel, adaptive optics (AO) has been used to improve the transverse resolution of ophthalmoscopes to foster in vivo study of the retina at the microscopic level. Here, we review work done over the last 15 years to combine the microscopic transverse resolution of AO with the microscopic axial resolution of OCT, building AO-OCT systems with the highest three-dimensional resolution of any existing retinal imaging modality.

METHODS

We surveyed the literature to identify the most influential antecedent work, important milestones in the development of AO-OCT technology, its applications that have yielded new knowledge, research areas into which it may productively expand, and nascent applications that have the potential to grow.

RESULTS

Initial efforts focused on demonstrating three-dimensional resolution. Since then, many improvements have been made in resolution and speed, as well as other enhancements of acquisition and postprocessing techniques. Progress on these fronts has produced numerous discoveries about the anatomy, function, and optical properties of the retina.

CONCLUSIONS

Adaptive optics OCT continues to evolve technically and to contribute to our basic and clinical knowledge of the retina. Due to its capacity to reveal cellular and microscopic detail invisible to clinical OCT systems, it is an ideal companion to those instruments and has the demonstrable potential to produce images that can guide the interpretation of clinical findings.

Retinal Ganglion Cell Layer Thinning Within One Month of Presentation for Non-Arteritic Anterior Ischemic Optic Neuropathy

PURPOSE

Optical coherence tomography reveals retinal ganglion cell layer (GCL) and retinal nerve fiber layer (RNFL) thinning in chronic optic nerve injury. With acute optic nerve injury, as in acute nonarteritic anterior ischemic optic neuropathy (NAION), swelling obscures early demonstration of RNFL thinning, which might be used to evaluate therapies. We hypothesized that measurement of GCL plus inner plexiform layer (IPL) thickness and trajectory of thinning would show it is an earlier and more accurate biomarker of early permanent neuronal injury.

METHODS

We prospectively studied 29 acute NAION eyes with standard automated perimetry and spectral domain (SD) optical coherence tomography for 6 months. We used a three-dimensional layer segmentation (method 1) and a commercial proprietary (method 2), to compute the combined thickness of macular GCL+IPL and method 2 to compute peripapillary RNFL thickness.

RESULTS

At presentation, the mean GCL+IPL thickness (78.7 μm ± 8.9) for NAION eyes, did not differ from unaffected fellow eyes (83 μm ± 6.4), using method 1 while method 2 (66.8 μm ± 18.7) failed in 34% of NAION eyes. At 1 to 2 months, 12% had RNFL loss compared to baseline, while 68% of NAION eyes had GCL+IPL thinning. The ganglion cell layer plus inner plexiform layer reduction was greatest at 1 to 2 months (19.6 μm ± 12.6) and was minimally worse after month 3. Ganglion cell layer plus inner plexiform layer thinning showed moderate to strong significant correlation with the visual acuity and mean deviation at each exam time. The retinal nerve fiber layer was not thinned until month 3.

CONCLUSIONS

Ganglion cell layer plus inner plexiform layer is acutely unaffected and provides a reliable measure of retinal neuronal structure using three-dimensional segmentation. Thinning develops within 1 to 2 months of onset, which is prior to RNFL swelling resolution. This suggests GCL+IPL measurement is better than the RNFL thickness to use as biomarker of early structural loss in NAION.

Prevalence and Distribution of Segmentation Errors in Macular Ganglion Cell Analysis of Healthy Eyes Using Cirrus HD-OCT

Purpose

To determine the frequency of different types of spectral domain optical coherence tomography (SD-OCT) scan artifacts and errors in ganglion cell algorithm (GCA) in healthy eyes.

Methods

Infrared image, color-coded map and each of the 128 horizontal b-scans acquired in the macular ganglion cell-inner plexiform layer scans using the Cirrus HD-OCT (Carl Zeiss Meditec, Dublin, CA) macular cube 512 × 128 protocol in 30 healthy normal eyes were evaluated. The frequency and pattern of each artifact was determined. Deviation of the segmentation line was classified into mild (less than 10 microns), moderate (10–50 microns) and severe (more than 50 microns). Each deviation, if present, was noted as upward or downward deviation. Each artifact was further described as per location on the scan and zones in the total scan area.

Results

A total of 1029 (26.8%) out of total 3840 scans had scan errors. The most common scan error was segmentation error (100%), followed by degraded images (6.70%), blink artifacts (0.09%) and out of register artifacts (3.3%). Misidentification of the inner retinal layers was most frequent (62%). Upward Deviation of the segmentation line (47.91%) and severe deviation (40.3%) were more often noted. Artifacts were mostly located in the central scan area (16.8%). The average number of scans with artifacts per eye was 34.3% and was not related to signal strength on Spearman correlation (p = 0.36).

Conclusions

This study reveals that image artifacts and scan errors in SD-OCT GCA analysis are common and frequently involve segmentation errors. These errors may affect inner retinal thickness measurements in a clinically significant manner. Careful review of scans for artifacts is important when using this feature of SD-OCT device.

Automatic Three-dimensional Detection of Photoreceptor Ellipsoid Zone Disruption Caused by Trauma in the OCT

Detection and assessment of the integrity of the photoreceptor ellipsoid zone (EZ) are important because it is critical for visual acuity in retina trauma and other diseases. We have proposed and validated a framework that can automatically analyse the 3D integrity of the EZ in optical coherence tomography (OCT) images. The images are first filtered and automatically segmented into 10 layers, of which EZ is located in the 7^th layer. For each voxel of the EZ, 57 features are extracted and a principle component analysis is performed to optimize the features. An Adaboost classifier is trained to classify each voxel of the EZ as disrupted or non-disrupted. Finally, blood vessel silhouettes and isolated points are excluded. To demonstrate its effectiveness, the proposed framework was tested on 15 eyes with retinal trauma and 15 normal eyes. For the eyes with retinal trauma, the sensitivity (SEN) was 85.69% ± 9.59%, the specificity (SPE) was 85.91% ± 5.48%, and the balanced accuracy rate (BAR) was 85.80% ± 6.16%. For the normal eyes, the SPE was 99.03% ± 0.73%, and the SEN and BAR levels were not relevant. Our framework has the potential to become a useful tool for studying retina trauma and other conditions involving EZ integrity.

Enhanced volumetric visualization for real time 4D intraoperative ophthalmic swept-source OCT

Current-generation software for rendering volumetric OCT data sets based on ray casting results in volume visualizations with indistinct tissue features and sub-optimal depth perception. Recent developments in hand-held and microscope-integrated intrasurgical OCT designed for real-time volumetric imaging motivate development of rendering algorithms which are both visually appealing and fast enough to support real time rendering, potentially from multiple viewpoints for stereoscopic visualization. We report on an enhanced, real time, integrated volumetric rendering pipeline which incorporates high performance volumetric median and Gaussian filtering, boundary and feature enhancement, depth encoding, and lighting into a ray casting volume rendering model. We demonstrate this improved model implemented on graphics processing unit (GPU) hardware for real-time volumetric rendering of OCT data during tissue phantom and live human surgical imaging. We show that this rendering produces enhanced 3D visualizations of pathology and intraoperative maneuvers compared to standard ray casting.

Retinal ganglion cell layer thinning within one month of presentation for optic neuritis

BACKGROUND

Spectral domain optical coherence tomography (SD-OCT) reveals retinal ganglion cell layer plus inner plexiform layer (GCL+IPL) and peripapillary retinal nerve fiber layer (pRNFL) thinning in chronic optic nerve injury. At presentation, swelling of the pRNFL confounds evaluation of early axon loss.

OBJECTIVE

We studied whether the GCL+IPL thins before the pRNFL, the trajectory of GCL+IPL loss and relationship to vision.

METHODS

We prospectively evaluated 33 eyes (study) with new optic neuritis, using perimetry and SD-OCT with investigative three-dimensional layer segmentation and commercial two-dimensional segmentation to compute the GCL+IPL and pRNFL thickness.

RESULTS

At presentation, GCL+IPL thickness (82.4±8.8 µm) did not differ from unaffected fellow eyes (81.2±6.7 µm), via the three-dimensional method, while the two-dimensional method failed in 9% of study eyes. At 1-2 months, there was thinning of the pRNFL in 10% and of the GCL+IPL in 93% of study eyes. GCL+IPL reduction was greatest during the first 2 months. GCL+IPL thinning at 1-2 months correlated with GCL+IPL thinning at 6 months (r=0.84, P=0.01) and presentation visual acuity (r=0.48, P=0.006) and perimetric mean deviation (r=0.52, P=0.003).

CONCLUSION

GGL+IPL is an early biomarker of structural injury in optic neuritis as thinning develops within 1-2 months of onset, prior to pRNFL thinning.

An automated framework for 3D serous pigment epithelium detachment segmentation in SD-OCT images

Pigment epithelium detachment (PED) is an important clinical manifestation of multiple chorioretinal diseases, which can cause loss of central vision. In this paper, an automated framework is proposed to segment serous PED in SD-OCT images. The proposed framework consists of four main steps: first, a multi-scale graph search method is applied to segment abnormal retinal layers; second, an effective AdaBoost method is applied to refine the initial segmented regions based on 62 extracted features; third, a shape-constrained graph cut method is applied to segment serous PED, in which the foreground and background seeds are obtained automatically; finally, an adaptive structure elements based morphology method is applied to remove false positive segmented regions. The proposed framework was tested on 25 SD-OCT volumes from 25 patients diagnosed with serous PED. The average true positive volume fraction (TPVF), false positive volume fraction (FPVF), dice similarity coefficient (DSC) and positive predictive value (PPV) are 90.08%, 0.22%, 91.20% and 92.62%, respectively. The proposed framework can provide clinicians with accurate quantitative information, including shape, size and position of the PED region, which can assist clinical diagnosis and treatment.

Choroidal thickness maps from spectral domain and swept source optical coherence tomography: algorithmic versus ground truth annotation

BACKGROUND/AIMS

The purpose of the study was to create a standardised protocol for choroidal thickness measurements and to determine whether choroidal thickness measurements made on images obtained by spectral domain optical coherence tomography (SD-OCT) and swept source (SS-) OCT from patients with healthy retina are interchangeable when performed manually or with an automatic algorithm.

METHODS

36 grid cell measurements for choroidal thickness for each volumetric scan were obtained, which were measured for SD-OCT and SS-OCT with two methods on 18 eyes of healthy volunteers. Manual segmentation by experienced retinal graders from the Vienna Reading Center and automated segmentation on >6300 images of the choroid from both devices were statistically compared.

RESULTS

Model-based comparison between SD-OCT/SS-OCT showed a systematic difference in choroidal thickness of 16.26±0.725 μm (p<0.001) for manual segmentation and 21.55±0.725 μm (p<0.001) for automated segmentation. Comparison of automated with manual segmentations revealed small differences in thickness of -0.68±0.513 μm (p=0.1833). The correlation coefficients for SD-OCT and SS-OCT measures within eyes were 0.975 for manual segmentation and 0.955 for automatic segmentation.

CONCLUSION

Choroidal thickness measurements of SD-OCT and SS-OCT indicate that these two devices are interchangeable with a trend of choroidal thickness measurements being slightly thicker on SD-OCT with limited clinical relevance. Use of an automated algorithm to segment choroidal thickness was validated in healthy volunteers.

Advanced image processing for optical coherence tomographic angiography of macular diseases

This article provides an overview of advanced image processing for three dimensional (3D) optical coherence tomographic (OCT) angiography of macular diseases, including age-related macular degeneration (AMD) and diabetic retinopathy (DR). A fast automated retinal layers segmentation algorithm using directional graph search was introduced to separates 3D flow data into different layers in the presence of pathologies. Intelligent manual correction methods are also systematically addressed which can be done rapidly on a single frame and then automatically propagated to full 3D volume with accuracy better than 1 pixel. Methods to visualize and analyze the abnormalities including retinal and choroidal neovascularization, retinal ischemia, and macular edema were presented to facilitate the clinical use of OCT angiography.

State-of-the-art in retinal optical coherence tomography image analysis

Optical coherence tomography (OCT) is an emerging imaging modality that has been widely used in the field of biomedical imaging. In the recent past, it has found uses as a diagnostic tool in dermatology, cardiology, and ophthalmology. In this paper we focus on its applications in the field of ophthalmology and retinal imaging. OCT is able to non-invasively produce cross-sectional volumetric images of the tissues which can be used for analysis of tissue structure and properties. Due to the underlying physics, OCT images suffer from a granular pattern, called speckle noise, which restricts the process of interpretation. This requires specialized noise reduction techniques to eliminate the noise while preserving image details. Another major step in OCT image analysis involves the use of segmentation techniques for distinguishing between different structures, especially in retinal OCT volumes. The outcome of this step is usually thickness maps of different retinal layers which are very useful in study of normal/diseased subjects. Lastly, movements of the tissue under imaging as well as the progression of disease in the tissue affect the quality and the proper interpretation of the acquired images which require the use of different image registration techniques. This paper reviews various techniques that are currently used to process raw image data into a form that can be clearly interpreted by clinicians.

Outer Segment Thickness Predicts Visual Field Response to QLT091001 in Patients with RPE65 or LRAT Mutations

PURPOSE

To determine whether the degree of change in Goldmann visual fields (GVFs) following oral administration of QLT091001 was related to baseline measures of retinal structure.

METHODS

Oral QLT091001 was administered once daily for 7 days in all study patients. Comprehensive ophthalmic testing, including spectral-domain optical coherence tomography (SD-OCT), was conducted in 14 patients with Leber congenital amaurosis (LCA) and 18 patients with retinitis pigmentosa (RP) at seven international sites. Average thickness of the outer segment (OS) layer was calculated over central 20°. Both eyes of each subject were evaluated separately.

RESULTS

Nineteen of 28 eyes (68%) with LCA and 13 of 36 eyes (36%) with RP responded to QLT091001. Among these responders, the average baseline thickness of the OS layer (central 20°) was 13.5 μm in the LCA cohort and 11.7 μm in the RP cohort. Nonresponders had average baseline OS thickness of less than 4.6 μm in both cohorts. The OS thickness in the central 20° was significantly shorter in nonresponders than responders in the LCA cohort (P = 0.01, t-test) and in the RP cohort (P = 0.02, Wilcoxon rank sum test). The OS thickness in the central 20° did not change significantly from baseline during the first 2 months (P = 0.09, t-test, paired).

CONCLUSIONS

The present findings suggest that there is a close parallel between the thickness of the photoreceptor layer and the potential for functional improvement in these patients.

TRANSLATIONAL RELEVANCE

SD-OCT thickness in the central retina may be useful for predicting the visual field response in the peripheral retina to QLT091001. (https://clinicaltrials.gov/ct2/show/NCT01014052 number, NCT01014052).

Details of Glaucomatous Damage Are Better Seen on OCT En Face Images Than on OCT Retinal Nerve Fiber Layer Thickness Maps

PURPOSE

High-resolution images of glaucomatous damage to the retinal nerve fiber layer (RNFL) were obtained with an adaptive optics-scanning light ophthalmoscope (AO-SLO) and used as a basis for comparisons between en face slab images and thickness maps derived from optical coherence tomography (OCT) scans.

METHODS

Wide-field (9 × 12 mm) cube scans were obtained with swept-source OCT (DRI-OCT) from six eyes of six patients. All eyes had a deep defect near fixation as seen on a 10-2 visual field test. Optical coherence tomography en face images, based on the average reflectance intensity, were generated (ATL 3D-Suite) from 52-μm slabs just below the vitreal border of the inner limiting membrane. The RNFL thickness maps were generated from the same OCT data. Both were compared with the AO-SLO peripapillary images that were previously obtained.

RESULTS

On AO-SLO images, three eyes showed small regions of preserved and/or missing RNFL bundles within the affected region. Details in these regions were seen on the OCT en face images but not on the RNFL thickness maps. In addition, in the healthier hemi-retinas of two eyes, there were darker, arcuate-shaped regions on en face images that corresponded to abnormalities seen on AO-SLO. These were not seen on RNFL thickness maps.

CONCLUSIONS

Details of local glaucomatous damage, missing or easily overlooked on traditional OCT RNFL thickness analysis used in clinical OCT reports, were seen on OCT en face images based on the average reflectance intensity. While more work is needed, it is likely that en face slab imaging has a role in the clinical management of glaucoma.

Causes and Prognosis of Visual Acuity Loss at the Time of Initial Presentation in Idiopathic Intracranial Hypertension

PURPOSE

To determine the etiology and prognosis of visual acuity loss in idiopathic intracranial hypertension (IIH) at presentation and to provide objective measures to predict visual outcome.

METHODS

A retrospective review of 660 patients with IIH (2009-2013) identified 31 patients (4.7%) with 48 eyes having best-corrected visual acuity (BCVA) of 20/25 or worse on initial presentation. Fundus photography, optical coherence tomography (OCT) of the optic disc and macula, and perimetry were used to determine the causes and prognosis of vision loss. Segmentation of the macula OCT was performed using the Iowa Reference Algorithm to determine the retinal ganglion cell-inner plexiform layer complex (GCL-IPL) thickness.

RESULTS

Outer retinal changes alone caused decreased BCVA at initial presentation in 22 eyes (46%): subretinal fluid in 16, chorioretinal folds in 5, and peripapillary choroidal neovascularization in 1. The vision loss was reversible except for some eyes with chorioretinal folds. Optic neuropathy alone caused decreased BCVA in 10 eyes (21%) and coexisting outer retinal changes and optic neuropathy caused decreased BCVA in 16 eyes (33%). A GCL-IPL thickness less than or equal to 70 μm at initial presentation or progressive thinning of greater than or equal to 10 μm within 2 to 3 weeks compared with baseline correlated with poor visual outcome.

CONCLUSIONS

Visual acuity loss in IIH can be caused by both outer retinal changes and optic neuropathy. Vision loss from outer retinal changes is mostly reversible. The outcome of patients with coexisting outer retinal changes and optic neuropathy or optic neuropathy alone depends on the degree of optic neuropathy, which can be predicted by the GCL-IPL thickness.

Papilledema Outcomes from the Optical Coherence Tomography Substudy of the Idiopathic Intracranial Hypertension Treatment Trial

PURPOSE

To assess treatment efficacy using spectral-domain (SD) optical coherence tomography (OCT) measurements of papilledema in the Idiopathic Intracranial Hypertension Treatment Trial (IIHTT), which evaluated the effects of acetazolamide and weight management and of placebo and weight management in eyes with mild visual loss.

DESIGN

Randomized double-masked control clinical trial of acetazolamide plus weight management compared with placebo plus weight management in subjects with mild visual field loss and previously untreated idiopathic intracranial hypertension (IIH).

PARTICIPANTS

Eighty-nine (43 acetazolamide treated, 46 placebo treated) of 165 subjects meeting IIHTT entry criteria.

METHODS

Subjects underwent perimetry, papilledema grading (Frisén method), high- and low-contrast visual acuity, and SD OCT imaging at study entry and 3 and 6 months. Study eye results (worse perimetric mean deviation [PMD]) were used for most analyses.

MAIN OUTCOME MEASURES

Retinal nerve fiber layer (RNFL) thickness, total retinal thickness (TRT), optic nerve (ONH) volume, and retinal ganglion cell layer (RGCL) measurements derived using 3-dimensional segmentation.

RESULTS

Study entry OCT values were similar in both treatment groups. At 6 months, the acetazolamide group had greater reduction than the placebo group for RNFL thickness (175 μm vs. 89 μm; P = 0.001), TRT (220 μm vs. 113 μm; P = 0.001), and ONH volume (4.9 mm(3) vs. 2.1 mm(3); P = 0.001). The RNFL thickness (P = 0.01), TRT (P = 0.003), and ONH volume (P = 0.002) measurements also showed smaller increases in subjects who lost 6% or more of study entry weight. The acetazolamide (3.6 μm) and placebo (2.1 μm) groups showed minor RGCL thinning (P = 0.06). The RNFL thickness, TRT, and ONH volume measurements showed moderate correlations (r = 0.48-0.59; P ≤ 0.0001) with Frisén grade. The 14 eyes with RGCL thickness less than the fifth percentile of controls had worse PMD (P = 0.001) than study eyes with RGCL in the fifth percentile or more.

CONCLUSIONS

In IIH, acetazolamide and weight loss effectively improve RNFL thickness, TRT, and ONH volume swelling measurements resulting from papilledema. In contrast to the strong correlation at baseline, OCT measures at 6 months show only moderate correlations with papilledema grade.

The Generalized Log-Ratio Transformation: Learning Shape and Adjacency Priors for Simultaneous Thigh Muscle Segmentation

We present a novel probabilistic shape representation that implicitly includes prior anatomical volume and adjacency information, termed the generalized log-ratio (GLR) representation. We demonstrate the usefulness of this representation in the task of thigh muscle segmentation. Analysis of the shapes and sizes of thigh muscles can lead to a better understanding of the effects of chronic obstructive pulmonary disease (COPD), which often results in skeletal muscle weakness in lower limbs. However, segmenting these muscles from one another is difficult due to a lack of distinctive features and inter-muscular boundaries that are difficult to detect. We overcome these difficulties by building a shape model in the space of GLR representations. We remove pose variability from the model by employing a presegmentation-based alignment scheme. We also design a rotationally invariant random forest boundary detector that learns common appearances of the interface between muscles from training data. We combine the shape model and the boundary detector into a fully automatic globally optimal segmentation technique. Our segmentation technique produces a probabilistic segmentation that can be used to generate uncertainty information, which can be used to aid subsequent analysis. Our experiments on challenging 3D magnetic resonance imaging data sets show that the use of the GLR representation improves the segmentation accuracy, and yields an average Dice similarity coefficient of 0.808 ±0.074, comparable to other state-of-the-art thigh segmentation techniques.

Quantitative Analysis of Mouse Retinal Layers Using Automated Segmentation of Spectral Domain Optical Coherence Tomography Images

PURPOSE

Quantification of retinal layers using automated segmentation of optical coherence tomography (OCT) images allows for longitudinal studies of retinal and neurological disorders in mice. The purpose of this study was to compare the performance of automated retinal layer segmentation algorithms with data from manual segmentation in mice using the Spectralis OCT.

METHODS

Spectral domain OCT images from 55 mice from three different mouse strains were analyzed in total. The OCT scans from 22 C57Bl/6, 22 BALBc, and 11 C3A.Cg-Pde6b⁺Prph2^Rd2 /J mice were automatically segmented using three commercially available automated retinal segmentation algorithms and compared to manual segmentation.

RESULTS

Fully automated segmentation performed well in mice and showed coefficients of variation (CV) of below 5% for the total retinal volume. However, all three automated segmentation algorithms yielded much thicker total retinal thickness values compared to manual segmentation data (P < 0.0001) due to segmentation errors in the basement membrane.

CONCLUSIONS

Whereas the automated retinal segmentation algorithms performed well for the inner layers, the retinal pigmentation epithelium (RPE) was delineated within the sclera, leading to consistently thicker measurements of the photoreceptor layer and the total retina.

TRANSLATIONAL RELEVANCE

The introduction of spectral domain OCT allows for accurate imaging of the mouse retina. Exact quantification of retinal layer thicknesses in mice is important to study layers of interest under various pathological conditions.

Automatic detection of subretinal fluid and sub-retinal pigment epithelium fluid in optical coherence tomography images

Age-related macular degeneration (AMD) is the leading cause of blindness in developed countries. Subretinal fluid (SRF) and sub-retinal pigment epithelium (sub-RPE) fluid are signs of AMD and can be detected in optical coherence tomography images. However, manual detection and segmentation of SRFs and sub-RPE fluids are laborious and time consuming. In this paper, a novel pipeline is proposed for automatic detection of SRFs and sub-RPE fluids. First, top and bottom layers of retina are segmented using a graph cut method. Then, a Split Bregman-based segmentation method is used to segment dark regions between layers. These segmented regions are considered as potential fluid candidates, on which a set of features are generated. After that, a random forest classifier is trained to distinguish between the true fluid regions from the falsely detected fluid regions. This method shows reasonable performance in a leave-one-out evaluation using a dataset from 21 patients.

Optical imaging of the optic nerve: beyond demonstration of retinal nerve fiber layer loss

Although we are still early in the evolution of optical imaging of the optic nerve, the available techniques already play an important role in clinical decision making. I would summarize our findings to date as follows: For acute ON: Presentation: OCT shows RNFL swelling, normal GCL + IPL by OCT; 1 month: OCT and SLP show RNFL thinning and swelling, GCL + IPL thinning by OCT; 3 months or later: OCT and SLP show RNFL thinning, further mild GCL thinning by OCT; 6 months: RNFL and GCL + IPL thinning finished. For acute NAION: Presentation: OCT shows RNFL swelling and SLP shows loss of birefringence, normal GCL + IPL by OCT; 1 month: RNFL swelling and thinning by OCT and thinning by SLP, GCL + IPL thinning by OCT; 3 months or later: RNFL and further mild GCL + IPL thinning; 6 months: RNFL and GCL + IPL thinning finished. For IIH Papilledema with mild vision loss: Presentation: OCT shows swelling of RNFL, TRT, and ONH volume; Presentation: OCT shows normal GCL + IPL; Presentation: OCT shows neural canal border inward deflection; 6 months: OCT shows structural shape changes reflecting the effectiveness of treatment.

Three dimensional data-driven multi scale atomic representation of optical coherence tomography

In this paper, we discuss about applications of different methods for decomposing a signal over elementary waveforms chosen in a family called a dictionary (atomic representations) in optical coherence tomography (OCT). If the representation is learned from the data, a nonparametric dictionary is defined with three fundamental properties of being data-driven, applicability on 3D, and working in multi-scale, which make it appropriate for processing of OCT images. We discuss about application of such representations including complex wavelet based K-SVD, and diffusion wavelets on OCT data. We introduce complex wavelet based K-SVD to take advantage of adaptability in dictionary learning methods to improve the performance of simple dual tree complex wavelets in speckle reduction of OCT datasets in 2D and 3D. The algorithm is evaluated on 144 randomly selected slices from twelve 3D OCTs taken by Topcon 3D OCT-1000 and Cirrus Zeiss Meditec. Improvement of contrast to noise ratio (CNR) (from 0.9 to 11.91 and from 3.09 to 88.9, respectively) is achieved. Furthermore, two approaches are proposed for image segmentation using diffusion. The first method is designing a competition between extended basis functions at each level and the second approach is defining a new distance for each level and clustering based on such distances. A combined algorithm, based on these two methods is then proposed for segmentation of retinal OCTs, which is able to localize 12 boundaries with unsigned border positioning error of 9.22 ±3.05 μm, on a test set of 20 slices selected from 13 3D OCTs.

Automated 3-D retinal layer segmentation of macular optical coherence tomography images with serous pigment epithelial detachments

Automated retinal layer segmentation of optical coherence tomography (OCT) images has been successful for normal eyes but becomes challenging for eyes with retinal diseases if the retinal morphology experiences critical changes. We propose a method to automatically segment the retinal layers in 3-D OCT data with serous retinal pigment epithelial detachments (PED), which is a prominent feature of many chorioretinal disease processes. The proposed framework consists of the following steps: fast denoising and B-scan alignment, multi-resolution graph search based surface detection, PED region detection and surface correction above the PED region. The proposed technique was evaluated on a dataset with OCT images from 20 subjects diagnosed with PED. The experimental results showed the following. 1) The overall mean unsigned border positioning error for layer segmentation is 7.87±3.36 μm , and is comparable to the mean inter-observer variability ( 7.81±2.56 μm). 2) The true positive volume fraction (TPVF), false positive volume fraction (FPVF) and positive predicative value (PPV) for PED volume segmentation are 87.1%, 0.37%, and 81.2%, respectively. 3) The average running time is 220 s for OCT data of 512 × 64 × 480 voxels.

Fast retinal layer segmentation of spectral domain optical coherence tomography images

An approach to segment macular layer thicknesses from spectral domain optical coherence tomography has been proposed. The main contribution is to decrease computational costs while maintaining high accuracy via exploring Kalman filtering, customized active contour, and curve smoothing. Validation on 21 normal volumes shows that 8 layer boundaries could be segmented within 5.8 s with an average layer boundary error <2.35 μm. It has been compared with state-of-the-art methods for both normal and age-related macular degeneration cases to yield similar or significantly better accuracy and is 37 times faster. The proposed method could be a potential tool to clinically quantify the retinal layer boundaries.

Population-based evaluation of retinal nerve fiber layer, retinal ganglion cell layer, and inner plexiform layer as a diagnostic tool for glaucoma

PURPOSE

We determined the glaucoma screening performance of regional optical coherence tomography (OCT) layer thickness measurements in the peripapillary and macular region, in a population-based setting.

METHODS

Subjects (n = 1224) in the Rotterdam Study underwent visual field testing (Humphrey Field Analyzer) and OCT of the macula and optic nerve head (Topcon 3-D OCT-1000). We determined the mean thicknesses of the retinal nerve fiber layer (RNFL), retinal ganglion cell layer (RGCL), and inner plexiform layer for regions-of-interest; thus, defining a series of OCT parameters, using the Iowa Reference Algorithms. Reference standard was the presence of glaucomatous visual field loss (GVFL); controls were subjects without GVFL, an intraocular pressure (IOP) of 21 mm Hg or less, and no positive family history for glaucoma. We calculated the area under the receiver operating characteristics curve (AUCs) and the sensitivity at 97.5% specificity for each parameter.

RESULTS

After excluding 23 subjects with an IOP > 21 mm Hg and 73 subjects with a positive family history for glaucoma, there were 1087 controls and 41 glaucoma cases. Mean RGCL thickness in the inferior half of the macular region showed the highest AUC (0.85; 95% confidence interval [CI] 0.77-0.92) and sensitivity (53.7%; 95% CI, 38.7-68.0%). The mean thickness of the peripapillary RNFL had an AUC of 0.77 (95% CI, 0.69-0.85) and a sensitivity of 24.4% (95% CI, 13.7-39.5%).

CONCLUSIONS

Macular RGCL loss is at least as common as peripapillary RNFL abnormalities in population-based glaucoma cases. Screening for glaucoma using OCT-derived regional thickness identifies approximately half of those cases of glaucoma as diagnosed by perimetry.

Baseline OCT measurements in the idiopathic intracranial hypertension treatment trial, part I: quality control, comparisons, and variability

PURPOSE

Optical coherence tomography (OCT) has been used to investigate papilledema in single-site, mostly retrospective studies. We investigated whether spectral-domain OCT (SD-OCT), which provides thickness and volume measurements of the optic nerve head and retina, could reliably demonstrate structural changes due to papilledema in a prospective multisite clinical trial setting.

METHODS

At entry, 126 subjects in the Idiopathic Intracranial Hypertension Treatment Trial (IIHTT) with mild visual field loss had optic disc and macular scans, using the Cirrus SD-OCT. Images were analyzed by using the proprietary commercial and custom 3D-segmentation algorithms to calculate retinal nerve fiber layer (RNFL), total retinal thickness (TRT), optic nerve head volume (ONHV), and retinal ganglion cell layer (GCL) thickness. We evaluated variability, with interocular comparison and correlation between results for both methods.

RESULTS

The average RNFL thickness > 95% of normal controls in 90% of eyes and the RNFL, TRT, ONH height, and ONHV showed strong (r > 0.8) correlations for interocular comparisons. Variability for repeated testing of OCT parameters was low for both methods and intraclass correlations > 0.9 except for the proprietary GCL thickness. The proprietary algorithm-derived RNFL, TRT, and GCL thickness measurements had failure rates of 10%, 16%, and 20% for all eyes respectively, which were uncommon with 3D-segmentation-derived measurements. Only 7% of eyes had GCL thinning that was less than fifth percentile of normal age-matched control eyes by both methods.

CONCLUSIONS

Spectral-domain OCT provides reliable continuous variables and quantified assessment of structural alterations due to papilledema. (ClinicalTrials.gov number, NCT01003639.).

Three-dimensional automated choroidal volume assessment on standard spectral-domain optical coherence tomography and correlation with the level of diabetic macular edema

PURPOSE

To measure choroidal thickness on spectral-domain optical coherence tomography (SD OCT) images using automated algorithms and to correlate choroidal pathology with retinal changes attributable to diabetic macular edema (DME).

DESIGN

Post hoc analysis of multicenter clinical trial baseline data.

METHODS

SD OCT raster scans/fluorescein angiograms were obtained from 284 treatment-naïve eyes of 142 patients with clinically significant DME and from 20 controls. Three-dimensional (3D) SD OCT images were evaluated by a certified independent reading center analyzing retinal changes associated with diabetic retinopathy. Choroidal thicknesses were analyzed using a fully automated algorithm. Angiograms were assessed manually. Multiple endpoint correction according to Bonferroni-Holm was applied. Main outcome measures were average retinal/choroidal thickness on fovea-centered or peak of edema (thickest point of edema)-centered Early Treatment Diabetic Retinopathy Study grid, maximum area of leakage, and the correlation between retinal and choroidal thicknesses.

RESULTS

Total choroidal thickness is significantly reduced in DME (175 ± 23 μm; P = .0016) and nonedematous fellow eyes (177 ± 20 μm; P = .009) of patients compared with healthy control eyes (190 ± 23 μm). Retinal/choroidal thickness values showed no significant correlation (1-mm: P = .27, r(2) = 0.01; 3-mm: P = .96, r(2) < 0.0001; 6-mm: P = .42, r(2) = 0.006). No significant difference was found in the 1- or 3-mm circle of a retinal peak of edema-centered grid. All other measurements of choroidal/retinal thickness (DME vs healthy, DME vs peak of edema-centered, DME vs fellow, healthy vs fellow, peak of edema-centered vs healthy, peak of edema-centered vs fellow eyes) were compared but no statistically significant correlation was found. By tendency a thinner choroid correlates with larger retinal leakage areas.

CONCLUSIONS

Automated algorithms can be used to reliably assess choroidal thickness in eyes with DME. Choroidal thickness was generally reduced in patients with diabetes if DME is present in 1 eye; however, no correlation was found between choroidal/retinal pathologies, suggesting different pathogenetic pathways.

Subvoxel accurate graph search using non-Euclidean graph space

Graph search is attractive for the quantitative analysis of volumetric medical images, and especially for layered tissues, because it allows globally optimal solutions in low-order polynomial time. However, because nodes of graphs typically encode evenly distributed voxels of the volume with arcs connecting orthogonally sampled voxels in Euclidean space, segmentation cannot achieve greater precision than a single unit, i.e. the distance between two adjoining nodes, and partial volume effects are ignored. We generalize the graph to non-Euclidean space by allowing non-equidistant spacing between nodes, so that subvoxel accurate segmentation is achievable. Because the number of nodes and edges in the graph remains the same, running time and memory use are similar, while all the advantages of graph search, including global optimality and computational efficiency, are retained. A deformation field calculated from the volume data adaptively changes regional node density so that node density varies with the inverse of the expected cost. We validated our approach using optical coherence tomography (OCT) images of the retina and 3-D MR of the arterial wall, and achieved statistically significant increased accuracy. Our approach allows improved accuracy in volume data acquired with the same hardware, and also, preserved accuracy with lower resolution, more cost-effective, image acquisition equipment. The method is not limited to any specific imaging modality and readily extensible to higher dimensions.

Depth-encoded all-fiber swept source polarization sensitive OCT

Polarization sensitive optical coherence tomography (PS-OCT) is a functional extension of conventional OCT and can assess depth-resolved tissue birefringence in addition to intensity. Most existing PS-OCT systems are relatively complex and their clinical translation remains difficult. We present a simple and robust all-fiber PS-OCT system based on swept source technology and polarization depth-encoding. Polarization multiplexing was achieved using a polarization maintaining fiber. Polarization sensitive signals were detected using fiber based polarization beam splitters and polarization controllers were used to remove the polarization ambiguity. A simplified post-processing algorithm was proposed for speckle noise reduction relaxing the demand for phase stability. We demonstrated systems design for both ophthalmic and catheter-based PS-OCT. For ophthalmic imaging, we used an optical clock frequency doubling method to extend the imaging range of a commercially available short cavity light source to improve polarization depth-encoding. For catheter based imaging, we demonstrated 200 kHz PS-OCT imaging using a MEMS-tunable vertical cavity surface emitting laser (VCSEL) and a high speed micromotor imaging catheter. The system was demonstrated in human retina, finger and lip imaging, as well as ex vivo swine esophagus and cardiovascular imaging. The all-fiber PS-OCT is easier to implement and maintain compared to previous PS-OCT systems and can be more easily translated to clinical applications due to its robust design.

User-guided segmentation for volumetric retinal optical coherence tomography images

Despite the existence of automatic segmentation techniques, trained graders still rely on manual segmentation to provide retinal layers and features from clinical optical coherence tomography (OCT) images for accurate measurements. To bridge the gap between this time-consuming need of manual segmentation and currently available automatic segmentation techniques, this paper proposes a user-guided segmentation method to perform the segmentation of retinal layers and features in OCT images. With this method, by interactively navigating three-dimensional (3-D) OCT images, the user first manually defines user-defined (or sketched) lines at regions where the retinal layers appear very irregular for which the automatic segmentation method often fails to provide satisfactory results. The algorithm is then guided by these sketched lines to trace the entire 3-D retinal layer and anatomical features by the use of novel layer and edge detectors that are based on robust likelihood estimation. The layer and edge boundaries are finally obtained to achieve segmentation. Segmentation of retinal layers in mouse and human OCT images demonstrates the reliability and efficiency of the proposed user-guided segmentation method.

Comparison of a MEMS-Based Handheld OCT Scanner With a Commercial Desktop OCT System for Retinal Evaluation

PURPOSE

The goal of this study was to evaluate the ability of our handheld optical coherence tomography (OCT) scanner to image the posterior and anterior structures of the human eye, and especially the individual layers of the retina, and to compare its diagnostic performance with that of a fixed desktop commercial ophthalmic OCT system.

METHODS

We compared the clinical imaging results of our handheld OCT with a leading commercial desktop ophthalmic system (RTVue) used in specialist offices. Six patients exhibiting diabetes-related retinal pathology had both eyes imaged with each OCT system.

RESULTS

In both sets of images, the structural irregularities of the retinal layers could be identified such as retinal edema and vitreomacular traction.

CONCLUSIONS

Our handheld OCT system can be used to identify relevant anatomical structures and pathologies in the eye, potentially enabling earlier screening, disease detection, and treatment. Images can be acquired quickly, with sufficient resolution and negligible motion artifacts that would normally limit its diagnostic use.

TRANSLATIONAL RELEVANCE

Following screening and early disease detection in primary care via our optimized handheld OCT system, patients can be referred to a specialist for treatment, preventing further disease progression. While many primary care physicians are adept at using the ophthalmoscope, they can definitely take advantage of more advanced technologies.

Quantifying disrupted outer retinal-subretinal layer in SD-OCT images in choroidal neovascularization

PURPOSE

We reported a fully automated method to identify and quantify the thickness of the outer retinal-subretinal (ORSR) layer from clinical spectral-domain optical coherence tomography (SD-OCT) scans of choroidal neovascularization (CNV) due to exudative age-related macular degeneration (eAMD).

METHODS

A total of 23 subjects with CNV met eligibility. Volumetric SD-OCT scans of 23 eyes were obtained (Zeiss Cirrus, 200 × 200 × 1024 voxels). In a subset of eyes, scans were repeated. The OCT volumes were analyzed using our standard parameters and using a 3-dimensional (3D) graph-search approach with an adaptive cost function. A retinal specialist graded the segmentation as generally accurate, local segmentation inaccuracies, or failure. Reproducibility on repeat scans was analyzed using root mean square coefficient of variation (RMS CV) of the average ORSR thickness.

RESULTS

Using a standard segmentation approach, 1/23 OCT segmentations was graded generally accurate and 22/23 were failure(s). With the adaptive method 21/23 segmentations were graded generally accurate; 2/23 were local segmentation inaccuracies and none was a failure. The intermethod quality of segmentation was significantly different (P << 0.001). The average ORSR thickness measured on CNV patients (78.0 μm; 95% confidence interval [CI], 72.5-83.4 μm) is significantly larger (P << 0.001) than normal average ORSR layer thickness (51.5 ± 3.3 μm). The RMS CV was 8.1%.

CONCLUSIONS

We have developed a fully automated 3D method for segmenting the ORSR layer in SD-OCT of patients with CNV from eAMD. Our method can quantify the ORSR layer thickness in the presence of fluid, which has the potential to augment management accuracy and efficiency of anti-VEGF treatment.

Multiple-object geometric deformable model for segmentation of macular OCT

Optical coherence tomography (OCT) is the de facto standard imaging modality for ophthalmological assessment of retinal eye disease, and is of increasing importance in the study of neurological disorders. Quantification of the thicknesses of various retinal layers within the macular cube provides unique diagnostic insights for many diseases, but the capability for automatic segmentation and quantification remains quite limited. While manual segmentation has been used for many scientific studies, it is extremely time consuming and is subject to intra- and inter-rater variation. This paper presents a new computational domain, referred to as flat space, and a segmentation method for specific retinal layers in the macular cube using a recently developed deformable model approach for multiple objects. The framework maintains object relationships and topology while preventing overlaps and gaps. The algorithm segments eight retinal layers over the whole macular cube, where each boundary is defined with subvoxel precision. Evaluation of the method on single-eye OCT scans from 37 subjects, each with manual ground truth, shows improvement over a state-of-the-art method.

An adaptive grid for graph-based segmentation in retinal OCT

Graph-based methods for retinal layer segmentation have proven to be popular due to their efficiency and accuracy. These methods build a graph with nodes at each voxel location and use edges connecting nodes to encode the hard constraints of each layer's thickness and smoothness. In this work, we explore deforming the regular voxel grid to allow adjacent vertices in the graph to more closely follow the natural curvature of the retina. This deformed grid is constructed by fixing node locations based on a regression model of each layer's thickness relative to the overall retina thickness, thus we generate a subject specific grid. Graph vertices are not at voxel locations, which allows for control over the resolution that the graph represents. By incorporating soft constraints between adjacent nodes, segmentation on this grid will favor smoothly varying surfaces consistent with the shape of the retina. Our final segmentation method then follows our previous work. Boundary probabilities are estimated using a random forest classifier followed by an optimal graph search algorithm on the new adaptive grid to produce a final segmentation. Our method is shown to produce a more consistent segmentation with an overall accuracy of 3.38 μm across all boundaries.

Optical Coherence Tomography (OCT) Device Independent Intraretinal Layer Segmentation

PURPOSE

To develop and test an algorithm to segment intraretinal layers irrespectively of the actual Optical Coherence Tomography (OCT) device used.

METHODS

The developed algorithm is based on the graph theory optimization. The algorithm's performance was evaluated against that of three expert graders for unsigned boundary position difference and thickness measurement of a retinal layer group in 50 and 41 B-scans, respectively. Reproducibility of the algorithm was tested in 30 C-scans of 10 healthy subjects each with the Spectralis and the Stratus OCT. Comparability between different devices was evaluated in 84 C-scans (volume or radial scans) obtained from 21 healthy subjects, two scans per subject with the Spectralis OCT, and one scan per subject each with the Stratus OCT and the RTVue-100 OCT. Each C-scan was segmented and the mean thickness for each retinal layer in sections of the early treatment of diabetic retinopathy study (ETDRS) grid was measured.

RESULTS

The algorithm was able to segment up to 11 intraretinal layers. Measurements with the algorithm were within the 95% confidence interval of a single grader and the difference was smaller than the interindividual difference between the expert graders themselves. The cross-device examination of ETDRS-grid related layer thicknesses highly agreed between the three OCT devices. The algorithm correctly segmented a C-scan of a patient with X-linked retinitis pigmentosa.

CONCLUSIONS

The segmentation software provides device-independent, reliable, and reproducible analysis of intraretinal layers, similar to what is obtained from expert graders.

TRANSLATIONAL RELEVANCE

Potential application of the software includes routine clinical practice and multicenter clinical trials.

Segmentation of choroidal boundary in enhanced depth imaging OCTs using a multiresolution texture based modeling in graph cuts

The introduction of enhanced depth imaging optical coherence tomography (EDI-OCT) has provided the advantage of in vivo cross-sectional imaging of the choroid, similar to the retina, with standard commercially available spectral domain (SD) OCT machines. A texture-based algorithm is introduced in this paper for fully automatic segmentation of choroidal images obtained from an EDI system of Heidelberg 3D OCT Spectralis. Dynamic programming is utilized to determine the location of the retinal pigment epithelium (RPE). Bruch's membrane (BM) (the blood-retina barrier which separates the RPE cells of the retina from the choroid) can be segmented by searching for the pixels with the biggest gradient value below the RPE. Furthermore, a novel method is proposed to segment the choroid-sclera interface (CSI), which employs the wavelet based features to construct a Gaussian mixture model (GMM). The model is then used in a graph cut for segmentation of the choroidal boundary. The proposed algorithm is tested on 100 EDI OCTs and is compared with manual segmentation. The results showed an unsigned error of 2.48 ± 0.32 pixels for BM extraction and 9.79 ± 3.29 pixels for choroid detection. It implies significant improvement of the proposed method over other approaches like k-means and graph cut methods.

Intra-retinal layer segmentation of 3D optical coherence tomography using coarse grained diffusion map

Optical coherence tomography (OCT) is a powerful and noninvasive method for retinal imaging. In this paper, we introduce a fast segmentation method based on a new variant of spectral graph theory named diffusion maps. The research is performed on spectral domain (SD) OCT images depicting macular and optic nerve head appearance. The presented approach does not require edge-based image information in localizing most of boundaries and relies on regional image texture. Consequently, the proposed method demonstrates robustness in situations of low image contrast or poor layer-to-layer image gradients. Diffusion mapping applied to 2D and 3D OCT datasets is composed of two steps, one for partitioning the data into important and less important sections, and another one for localization of internal layers. In the first step, the pixels/voxels are grouped in rectangular/cubic sets to form a graph node. The weights of the graph are calculated based on geometric distances between pixels/voxels and differences of their mean intensity. The first diffusion map clusters the data into three parts, the second of which is the area of interest. The other two sections are eliminated from the remaining calculations. In the second step, the remaining area is subjected to another diffusion map assessment and the internal layers are localized based on their textural similarities. The proposed method was tested on 23 datasets from two patient groups (glaucoma and normals). The mean unsigned border positioning errors (mean ± SD) was 8.52 ± 3.13 and 7.56 ± 2.95 μm for the 2D and 3D methods, respectively.

Motion-compensated mega-voltage cone beam CT using the deformation derived directly from 2D projection images

This paper presents a novel method for respiratory motion compensated reconstruction for cone beam computed tomography (CBCT). The reconstruction is based on a time sequence of motion vector fields, which is generated by a dynamic geometrical object shape model. The dynamic model is extracted from the 2D projection images of the CBCT. The process of the motion extraction is converted into an optimal 3D multiple interrelated surface detection problem, which can be solved by computing a maximum flow in a 4D directed graph. The method was tested on 12 mega-voltage (MV) CBCT scans from three patients. Two sets of motion-artifact-free 3D volumes, full exhale (FE) and full inhale (FI) phases, were reconstructed for each daily scan. The reconstruction was compared with three other motion-compensated approaches based on quantification accuracy of motion and size. Contrast-to-noise ratio (CNR) was also quantified for image quality. The proposed approach has the best overall performance, with a relative tumor volume quantification error of 3.39 ± 3.64% and 8.57 ± 8.31% for FE and FI phases, respectively. The CNR near the tumor area is 3.85 ± 0.42 (FE) and 3.58 ± 3.33 (FI). These results show the clinical feasibility to use the proposed method to reconstruct motion-artifact-free MVCBCT volumes.

Effect of age on individual retinal layer thickness in normal eyes as measured with spectral-domain optical coherence tomography

PURPOSE

To determine the effect of age on the thickness of individual retinal layers, measured with spectral-domain optical coherence tomography (SD-OCT), in a population of healthy Caucasians.

METHODS

One hundred and twenty subjects with an age ranging between 18 and 81 years were examined with SD-OCT. Mean layer thickness was calculated for seven retinal layers, in the fovea (region 1 of the 9 Early Treatment Diabetic Retinopathy Study [ETDRS] regions); in the pericentral ring (ETDRS regions 2 to 5); and the peripheral ring (ETDRS regions 6 to 9) following automated segmentation using the Iowa Reference Algorithm. In addition, mean peripapillary retinal nerve fiber layer (RNFL) thickness was measured. The partial correlation test was performed on each layer to determine the effect of age on layer thickness, while correcting for spherical equivalent, sex, and Topcon image quality factor as confounders, followed by Bonferroni corrections to adjust for multiple testing.

RESULTS

The thickness of the peripapillary RNFL (R = -0.332; P < 0.001); pericentral ganglion cell layer (R = -0.354, P < 0.001); peripheral inner plexiform layer (R = -0.328, P < 0.001); and foveal outer segment layer (R = -0.381, P < 0.001) decreased significantly with increasing age. Foveal RPE thickness (R = 0.467, P < 0.001) increased significantly with increasing age; other layers showed no significant differences with age.

CONCLUSIONS

Several macular layers and the peripapillary RNFL thickness showed significant changes correlated with age. This should be taken into consideration when analyzing macular layers and the peripapillary RNFL in SD-OCT studies of retinal diseases and glaucoma.

Retinal layer segmentation of macular OCT images using boundary classification

Optical coherence tomography (OCT) has proven to be an essential imaging modality for ophthalmology and is proving to be very important in neurology. OCT enables high resolution imaging of the retina, both at the optic nerve head and the macula. Macular retinal layer thicknesses provide useful diagnostic information and have been shown to correlate well with measures of disease severity in several diseases. Since manual segmentation of these layers is time consuming and prone to bias, automatic segmentation methods are critical for full utilization of this technology. In this work, we build a random forest classifier to segment eight retinal layers in macular cube images acquired by OCT. The random forest classifier learns the boundary pixels between layers, producing an accurate probability map for each boundary, which is then processed to finalize the boundaries. Using this algorithm, we can accurately segment the entire retina contained in the macular cube to an accuracy of at least 4.3 microns for any of the nine boundaries. Experiments were carried out on both healthy and multiple sclerosis subjects, with no difference in the accuracy of our algorithm found between the groups.

Reproducibility of diabetic macular edema estimates from SD-OCT is affected by the choice of image analysis algorithm

PURPOSE

To evaluate the intersession repeatability of retinal thickness measurements in patients with diabetic macular edema (DME) using the Heidelberg Spectralis optical coherence tomography (OCT) algorithm and a publicly available, three-dimensional graph search-based multilayer OCT segmentation algorithm, the Iowa Reference Algorithm.

METHODS

Thirty eyes from 21 patients diagnosed with clinically significant DME were included and underwent consecutive, registered macula-centered spectral-domain optical coherence scans (Heidelberg Spectralis). The OCT scans were segmented into separate surfaces, and the average thickness between internal limiting membrane and outer retinal pigment epithelium complex surfaces was determined using the Iowa Reference Algorithm. Variability between paired scans was analyzed and compared with the retinal thickness obtained from the manufacturer-supplied Spectralis software.

RESULTS

The coefficient of repeatability (variation) for central macular thickness using the Iowa Reference Algorithm was 5.26 μm (0.62% [95% confidence interval (CI), 0.43-0.71]), while for the Spectralis algorithm this was 6.84 μm (0.81% [95% CI, 0.55-0.92]). When the central 3 mm was analyzed, the coefficient of repeatability (variation) was 2.46 μm (0.31% [95% CI, 0.23-0.38]) for the Iowa Reference Algorithm and 4.23 μm (0.53% [95% CI, 0.39-0.65]) for the Spectralis software.

CONCLUSIONS

The Iowa Reference Algorithm and the Spectralis software provide excellent reproducibility between serial scans in patients with clinically significant DME. The publicly available Iowa Reference Algorithm may have lower between-measurement variation than the manufacturer-supplied Spectralis software for the central 3 mm subfield. These findings have significant implications for the management of patients with DME.

Curvature correction of retinal OCTs using graph-based geometry detection

In this paper, we present a new algorithm as an enhancement and preprocessing step for acquired optical coherence tomography (OCT) images of the retina. The proposed method is composed of two steps, first of which is a denoising algorithm with wavelet diffusion based on a circular symmetric Laplacian model, and the second part can be described in terms of graph-based geometry detection and curvature correction according to the hyper-reflective complex layer in the retina. The proposed denoising algorithm showed an improvement of contrast-to-noise ratio from 0.89 to 1.49 and an increase of signal-to-noise ratio (OCT image SNR) from 18.27 to 30.43 dB. By applying the proposed method for estimation of the interpolated curve using a full automatic method, the mean ± SD unsigned border positioning error was calculated for normal and abnormal cases. The error values of 2.19 ± 1.25 and 8.53 ± 3.76 µm were detected for 200 randomly selected slices without pathological curvature and 50 randomly selected slices with pathological curvature, respectively. The important aspect of this algorithm is its ability in detection of curvature in strongly pathological images that surpasses previously introduced methods; the method is also fast, compared to the relatively low speed of similar methods.