Segment Optical Coherence Tomography Research Articles

Methodological Challenges of Deep Learning in Optical Coherence Tomography for Retinal Diseases: A Review.

Artificial intelligence (AI)-based automated classification and segmentation of optical coherence tomography (OCT) features have become increasingly popular. However, its 3-dimensional volumetric nature has made developing an algorithm that generalizes across all patient populations and OCT devices challenging. Several recent studies have reported high diagnostic performances of AI models; however, significant methodological challenges still exist in applying these models in real-world clinical practice. Lack of large-image datasets from multiple OCT devices, nonstandardized imaging or post-processing protocols between devices, limited graphics processing unit capabilities for exploiting 3-dimensional features, and inconsistency in the reporting metrics are major hurdles in enabling AI for OCT analyses. We discuss these issues and present possible solutions.

Anterior segment optical coherence tomographic characterisation of keratic precipitates

Background/objectivesAnterior segment optical coherence tomography (AS-OCT) can be used to visualise keratic precipitates (KPs) on the corneal endothelium. However, there has been no correlation between characteristic clinical appearances of KPs and AS-OCT morphology. We wished to assess the potential diagnostic role of AS-OCT in patients presenting with inflammatory eye disease and KPs. Subjects/methodsSix patients with inflammatory KPs were compared to one patient with infective interface keratitis following Descemet Membrane Endothelial Keratoplasty (DMEK) and one patient with endothelial pigment. AS-OCT was performed in each case and morphological features of the KPs were compared. Reflectivity of KPs was also compared numerically by measuring their relative lightness. ResultsAS-OCT images in acute and active inflammation generally demonstrated hyperreflective KP variants in comparison to conditions with moderate or longstanding inflammation. In the patient with infective interface keratitis, KPs were evident on the endothelial surface but no changes could be identified at the graft-host interface. There were no significant differences between infective and inflammatory KPs to help distinguish between the two. Endothelial pigment deposits were clearly differentiated from keratic precipitates with smaller, poorly defined deposits on the endothelium surface which were isoreflective to the cornea. ConclusionHyperreflective KPs could be suggestive of newly deposited KPs and active inflammation; they may also be increased in KPs of herpetic origin. AS-OCT should not be used to differentiate infective infiltrate from inflammatory KPs if a patient were to present with post-operative inflammation and interface infection should still be suspected even if only endothelial deposits are identified on AS-OCT. AS-OCT may be used as a diagnostic and monitoring tool to assess response to treatment in cases where anterior segment inflammation of uncertain aetiology is present.

Corticosteroid-Induced Central Serous Chorioretinopathy

Central Serous Chorioretinopathy (CSC) is a condition where there is an accumulation of serous fluid in the retinal pigment epithelium layer. The abnormality in the retinal pigment layer of the eye causes vision loss and serous detachment. CSC has a variety of causes, one of which is corticosteroid therapy. This article aims to report a case of a 27-year-old male patient who was diagnosed with CSC. The risk factor indicating CSC, in this case, was long-term oral and the use of a nasal spray to treat patient’s allergic rhinitis. Patients have allergic rhinitis and sneezing. Thus, they are administered to consume tablets of 16 mg methylprednisolone three times a day. The patient has a history of using a nasal spray containing 0.05% mometasone furoate monohydrate for ten years in a row. The patient’s visual acuity is 6/6 on his right eye and 6/15 on his left eye. Posterior segment examination and optical coherence tomography (OCT) were considered effective in identifying the features of patients with CSC, and thus both were administered. It was further found that steroid therapy replacement and healthier lifestyle adjustments could sustain the symptoms and improve the patient’s well-being.

Hipermetropik Anizometropik Ambliyopide Retina Tabakalarının Optik Koherens Tomografi Segmentasyon Analizi ile Değerlendirilmesi

Amaç: Hipermetropik anizometropik ambliyopisi olan olgularda spektral domain optik koherens tomografi (OKT) kullanarak retina tabakalarını analiz etmek ve ambliyopik gözlerle normal gözleri kıyaslamak. Gereç ve Yöntemler: Detaylı oftalmolojik muayeneyi takiben hipermetropik anizometropik ambliyopisi olan olguların her iki gözü OKT ile değerlendirildi. Merkezi makula kalınlığı (MMK) analizi sonrasında, ganglion hücre tabakası, iç pleksiform tabaka, iç nükleer tabaka, dış pleksiform tabaka, dış nükleer tabaka ve retina pigment epiteli tabakasına ait ortalama kalınlıklar kaydedildi. Retinal katmanlar ayrıca iç ve dış retina katmanlar olmak üzere 2 katmana ayrılarak analiz edildi. Bulgular: Yirmi (%33,3)'si kadın, 40 (%66,7)'ı erkek hipermetropik anizometropik ambliyopiden oluşan olguların ortalama yaşı 17,3±9,0 olarak hesaplandı. Ortalama MMK ambliyopik gözlerde 27030±1815 µm, normal gözlerde ise 265,13±19,25 µm olarak hesaplandı. Ambliyopik gözlerde MMK'nin normal gözlere kıyasla istatistiksel olarak anlamlı düzeyde kalın olduğu saptandı (p0,05, her biri için). Sonuç: Hipermetropik anizometropik ambliyopisi olan olgularda ambliyopik gözlerde normal gözlere kıyasla merkezi makulanın anlamlı düzeyde daha kalın olduğu saptanırken, retina tabakaları kalınlıkları arasında istatistiksel olarak anlamlı bir fark bulunmamıştır.

Evaluation of Peripapillary Choroidal Microvasculature to Detect Glaucomatous Damage in Eyes With High Myopia.

Parapapillary choroidal microvasculature dropout (MvD), as observed by optical coherence tomography (OCT) angiography, was useful to detect glaucomatous damage in highly myopic eyes with unreliable OCT results due to segmentation errors. The purpose of this study was to evaluate the usefulness of optical coherence tomography angiography (OCTA) imaging of the peripapillary choroidal microvasculature in detecting glaucomatous damage in highly myopic eyes, in cases where evaluating the thickness of the retinal nerve fiber layer (RNFL) is unreliable due to OCT segmentation errors. Forty-five highly myopic eyes with primary open-angle glaucoma (POAG) with an axial length >26.5 mm, and 15 age-matched and axial length-matched 15 control eyes were included in this cross-sectional observational study. All participants had a segmentation error in OCT circumpapillary RNFL scanning. The peripapillary choroidal microvasculature was evaluated on en-face images obtained using swept-source OCTA. MvD was defined as a focal sectoral capillary dropout with no visible microvascular network identified in the choroidal layer. The topographic correlation between the MvD and a hemifield visual field (VF) defect was assessed using κ statistics. The MvD size was assessed by measuring both its area and circumferential extent. Choroidal MvD was observed in 44 of the 45 (97.8%) POAG eyes with high myopia, while none of the control eyes showed a choroidal MvD. There was an excellent topographic relationship between the choroidal MvD and the hemifield VF defect (κ=0.863, P<0.001). The area (R=0.2619, P=0.0006) and circumferential extent (R=0.3088, P=0.0002) of the MvD have significantly associated with the VF mean deviation. Choroidal MvDs were observed in most of the highly myopic POAG eyes and were topographically correlated with the location of glaucomatous VF defects despite unreliable OCT RNFL thickness measurements. Using OCTA to investigate the choroidal microvasculature may facilitate diagnoses of glaucoma in highly myopic eyes.

Correlation between Argus II array-retina distance and electrical thresholds of stimulation is improved by measuring the entire array.

To describe two methods of measuring Argus II array-retina distance and to correlate array-retina distance to electrode stimulation thresholds. This was a case series of eight patients implanted with the Argus II. Spectral domain-optical coherence tomography array-retina distance was measured by two methods and correlated to corresponding electrode thresholds: (1) array-retina distance at each array corner and the largest array-retina distance and (2) using manual optical coherence tomography segmentation, the average array-retina distance was determined for each group of four electrodes. Patients 1-5 and 6-8 were analyzed separately due to a different threshold programming software. The Spearman's rank coefficient between array-retina distance and thresholds was -0.006 (p = 0.98) for patients 1-5, and 0.16 (p = 0.59) for patients 6-8 with the first method. The Spearman's rank coefficient was 0.25 (p < 0.001) for patients 1-5 and 0.36 (p < 0.001) for patients 6-8 with the second method. There is a positive correlation between array-retina distance and threshold measurements when measuring the entire array but not when using a faster measurement method of four corners and largest array-retina distance.

Accurate tissue interface segmentation via adversarial pre-segmentation of anterior segment OCT images.

Optical Coherence Tomography (OCT) is an imaging modality that has been widely adopted for visualizing corneal, retinal and limbal tissue structure with micron resolution. It can be used to diagnose pathological conditions of the eye, and for developing pre-operative surgical plans. In contrast to the posterior retina, imaging the anterior tissue structures, such as the limbus and cornea, results in B-scans that exhibit increased speckle noise patterns and imaging artifacts. These artifacts, such as shadowing and specularity, pose a challenge during the analysis of the acquired volumes as they substantially obfuscate the location of tissue interfaces. To deal with the artifacts and speckle noise patterns and accurately segment the shallowest tissue interface, we propose a cascaded neural network framework, which comprises of a conditional Generative Adversarial Network (cGAN) and a Tissue Interface Segmentation Network (TISN). The cGAN pre-segments OCT B-scans by removing undesired specular artifacts and speckle noise patterns just above the shallowest tissue interface, and the TISN combines the original OCT image with the pre-segmentation to segment the shallowest interface. We show the applicability of the cascaded framework to corneal datasets, demonstrate that it precisely segments the shallowest corneal interface, and also show its generalization capacity to limbal datasets. We also propose a hybrid framework, wherein the cGAN pre-segmentation is passed to a traditional image analysis-based segmentation algorithm, and describe the improved segmentation performance. To the best of our knowledge, this is the first approach to remove severe specular artifacts and speckle noise patterns (prior to the shallowest interface) that affects the interpretation of anterior segment OCT datasets, thereby resulting in the accurate segmentation of the shallowest tissue interface. To the best of our knowledge, this is the first work to show the potential of incorporating a cGAN into larger deep learning frameworks for improved corneal and limbal OCT image segmentation. Our cGAN design directly improves the visualization of corneal and limbal OCT images from OCT scanners, and improves the performance of current OCT segmentation algorithms.

Deep learning based retinal OCT segmentation

We look at the recent application of deep learning (DL) methods in automated fine-grained segmentation of spectral domain optical coherence tomography (OCT) images of the retina. We describe a new method combining fully convolutional networks (FCN) with Gaussian Processes for post processing. We report performance comparisons between the proposed approach, human clinicians, and other machine learning (ML) such as graph based approaches. The approach is demonstrated on an OCT dataset consisting of mild non-proliferative diabetic retinopathy from the University of Miami. The method is shown to have performance on par with humans, also compares favorably with the other ML methods, and appears to have as small or smaller mean unsigned error (equal to 1.06), versus errors ranging from 1.17 to 1.81 for other methods, and compared with human error of 1.10.

Automatic proximal airway volume segmentation using optical coherence tomography for assessment of inhalation injury.

Acute respiratory distress syndrome (ARDS) is a severe form of acute lung injury with a mortality rate of up to 40%. Early management of ARDS has been difficult due to the lack of sensitive imaging tools and robust analysis software. We previously designed an optical coherence tomography (OCT) system to evaluate mucosa thickness (MT) after smoke inhalation, but the analysis relied on manual segmentation. The aim of this study is to assess in vivo proximal airway volume (PAV) after inhalation injury using automated OCT segmentation and correlate the PAV to lung function for rapid indication of ARDS. Anesthetized female Yorkshire pigs (n = 14) received smoke inhalation injury (SII) and 40% total body surface area thermal burns. Measurements of PaO2-to-FiO2 ratio (PFR), peak inspiratory pressure (PIP), dynamic compliance, airway resistance, and OCT bronchoscopy were performed at baseline, postinjury, 24 hours, 48 hours, 72 hours after injury. A tissue segmentation algorithm based on graph theory was used to reconstruct a three-dimensional (3D) model of lower respiratory tract and estimate PAV. Proximal airway volume was correlated with PFR, PIP, compliance, resistance, and MT measurement using a linear regression model. Proximal airway volume decreased after the SII: the group mean of proximal airway volume at baseline, postinjury, 24 hours, 48 hours, 72 hours were 20.86 cm (±1.39 cm), 17.61 cm (±0.99 cm), 14.83 cm (±1.20 cm), 14.88 cm (±1.21 cm), and 13.11 cm (±1.59 cm), respectively. The decrease in the PAV was more prominent in the animals that developed ARDS after 24 hours after the injury. PAV was significantly correlated with PIP (r = 0.48, p < 0.001), compliance (r = 0.55, p < 0.001), resistance (r = 0.35, p < 0.01), MT (r = 0.60, p < 0.001), and PFR (r = 0.34, p < 0.01). Optical coherence tomography is a useful tool to quantify changes in MT and PAV after SII and burns, which can be used as predictors of developing ARDS at an early stage. Prognostic, level III.

Evaluation of Structural Alterations in Eyes Exposed to Blunt Trauma by Anterior Segment and Macula Optic Coherence Tomography

Evaluation of Structural Alterations in Eyes Exposed to Blunt Trauma by Anterior Segment and Macula Optic Coherence Tomography

A Machine Learning-Based Method for Intracoronary OCT Segmentation and Vulnerable Coronary Plaque Cap Thickness Quantification

Accurate cap thickness quantification is of fundamental importance for vulnerable plaque detection in cardiovascular research. A segmentation method for intracoronary optical coherence tomography (OCT) image based on least squares support vector machine (LS-SVM) was performed to characterize plaque component borders and quantify fibrous cap thickness. Manual segmentation of OCT images were performed by experts based on combination of virtual-histology intravascular ultrasound (VH-IVUS) and OCT images and used as gold standard. The segmentation methods based on LS-SVM provided accurate plaque cap thickness (an 8.6% error by LS-SVM vs. 71% error by IVUS50) serving as solid basis for plaque modeling and assessment.

The Analysis of Intra-retinal Layers with Automatic Optical Coherence Tomography Segmentation in Healthy Subjects

Aims: To give normative databases of each retinal layers on OCT images in the healthy Caucasian population in Turkey and investigate the relevance of the data with factors such as age, gender, axial length and refraction.&#x0D; Study Design: Prospective, cross sectional, descriptive study.&#x0D; Place and Duration of Study: Department of Ophthalmology, Faculty of Medicine, Kirsehir Ahi Evran University, Kirsehir/TURKEY. Between September 2017 and March 2018.&#x0D; Methodology: 133 participants underwent full ophthalmologic examination and spectral domain OCT imaging (Spectralis, Heidelberg Engineering, Germany). After the automatic segmentation, central 1 mm and 1-3 mm superior, inferior, nasal and temporal thicknesses of retinal nerve fiber layer (RNFL), ganglion cell layer (GCL), inner plexiform layer (IPL), inner nuclear layer (INL), outer plexiform layer (OPL), outer nuclear layer (ONL), retina pigment epithelium (RPE), inner retinal layers (IRL), outer retinal layers (ORL) and total retina thickness (TRT) analyzed with respect to age, gender, axial length and refraction (spherical equivalent).&#x0D; Results: Central 1 mm INL, ONL, ORL, IRL and TRT and four quadrants of pericentral 1-3 mm thicknesses of RPE had positive correlation with the age. All the sections of total retina, RNFL, GCL, IPL, INL, ONL and IRL thicknesses were significantly thicker in males compared to females. The thicknesses of all RNFL sections and central 1 mm circle thicknesses of TRT, IPL, INL, OPL, RPE and IRL had positive correlation with the axial length.&#x0D; Conclusion: A normative database for thicknesses of intra-retinal layers in Turkish population was presented in the study and significant impacts of the age, gender and axial length were presented.

Layer boundary evolution method for macular OCT layer segmentation.

Optical coherence tomography (OCT) is used to produce high resolution depth images of the retina and is now the standard of care for in-vivo ophthalmological assessment. It is also increasingly being used for evaluation of neurological disorders such as multiple sclerosis (MS). Automatic segmentation methods identify the retinal layers of the macular cube providing consistent results without intra- and inter-rater variation and is faster than manual segmentation. In this paper, we propose a fast multi-layer macular OCT segmentation method based on a fast level set method. Our framework uses contours in an optimized approach specifically for OCT layer segmentation over the whole macular cube. Our algorithm takes boundary probability maps from a trained random forest and iteratively refines the prediction to subvoxel precision. Evaluation on both healthy and multiple sclerosis subjects shows that our method is statistically better than a state-of-the-art graph-based method.

Structural and Functional Characterization of the Retinal Effects of Hydroxychloroquine Treatment in Healthy Eyes

Purpose: To evaluate the influence of hydroxychloroquine in visual field and retinal layer thickness. Methods: This is a retrospective cross-sectional study. Patients taking hydroxychloroquine without signs of hydroxychloroquine retinopathy were included. Optical coherence tomography segmentation was used to obtain the ETDRS map thickness of each retinal layer. Groups were divided into short-term (< 5 years) and long-term (≥5 years) drug use. Results: We included 93 eyes of 93 patients (short-term: 25 eyes; long-term: 68 eyes). The inner nuclear layer (INL) was thinner in the long-term group (32.86 ± 2.12 vs. 34.14 ± 2.37 μm; p = 0.014). Considering long-term cases, the parafoveal ganglion cell layer (GCL) showed an inverse correlation with cumulative dose (r = –0.37; p < 0.001). After adjusting for confounders, parafoveal ganglion cell complex thickness was associated with cumulative dose (β = –0.239; p = 0.011). The parafoveal outer retina and visual field indices were similar between groups and did not correlate with cumulative dose. Conclusion: Hydroxychloroquine leads to progressive thinning of the parafoveal inner retina, particularly the INL and GCL. Visual field indices do not reflect the long-term effects of the drug.

RETOUCH: The Retinal OCT Fluid Detection and Segmentation Benchmark and Challenge.

Retinal swelling due to the accumulation of fluid is associated with the most vision-threatening retinal diseases. Optical coherence tomography (OCT) is the current standard of care in assessing the presence and quantity of retinal fluid and image-guided treatment management. Deep learning methods have made their impact across medical imaging, and many retinal OCT analysis methods have been proposed. However, it is currently not clear how successful they are in interpreting the retinal fluid on OCT, which is due to the lack of standardized benchmarks. To address this, we organized a challenge RETOUCH in conjunction with MICCAI 2017, with eight teams participating. The challenge consisted of two tasks: fluid detection and fluid segmentation. It featured for the first time: all three retinal fluid types, with annotated images provided by two clinical centers, which were acquired with the three most common OCT device vendors from patients with two different retinal diseases. The analysis revealed that in the detection task, the performance on the automated fluid detection was within the inter-grader variability. However, in the segmentation task, fusing the automated methods produced segmentations that were superior to all individual methods, indicating the need for further improvements in the segmentation performance.

Automatic Segmentation Methods Based on Machine Learning for Intracoronary Optical Coherence Tomography Image

Cardiovascular diseases are closely associated with sudden rupture of atherosclerotic plaques. Previous image modalities such as magnetic resonance imaging (MRI) and intravascular ultrasound (IVUS) were unable to identify vulnerable plaques due to their limited resolution. Optical coherence tomography (OCT) is an advanced intravascular imaging technique developed in recent years which has high resolution approximately 10 microns and could provide more accurate morphology of coronary plaque. In particular, it is now possible to identify plaques with fibrous cap thickness < 65 µm, an accepted threshold value for vulnerable plaques. However, the current segmentation of OCT images are still performed manually by physicians and the process is time consuming. Automatic segmentation and recognition of vulnerable plaques through quantification of plaque components have great clinical significance for cardiovascular research. Two segmentation methods for intracoronary OCT image based on support vector machine (SVM) and convolutional neural network (CNN) were performed to detect the lumen borders and characterize the plaque component. In vivo IVUS and OCT coronary plaque data from 5 patients were acquired at Emory University with patient’s consent obtained. Seventy-seven matched IVUS and OCT slices with good image quality and medium to large lipid cores were selected for our segmentation study. Manual OCT segmentation was performed by experts and used as gold standard in the automatic segmentations. VH-IVUS was used as references and guide by the experts in the manual segmentation process. Three plaque component tissue classes were identified from OCT images in this work: lipid tissue (LT), fibrous tissue (FT) and background (BG). Procedures using two machine learning methods (CNN and SVM) were developed to segment OCT images, respectively. For CNN method, the U-Net architecture was selected due to its good performance in very different biomedical segmentation and very few annotated images. For SVM method, local binary patterns (LBPs), gray level co-occurrence matrices (GLCMs) which contains contrast, correlation, energy and homogeneity, entropy and mean value were calculated as features and assembled to feed SVM classifier. The accuracies of two segmentation methods were evaluated and compared using the OCT dataset. Segmentation accuracy is defined as the ratio of the number of pixels correctly classified over the total number of pixels. The overall classification accuracy based CNN method reached 95.8%, and the accuracies for LT, FT and BG were 86.8%, 83.4%, and 98.2%, respectively. The overall classification accuracy based SVM was 71.9%, and per-class accuracy for LT, FT and BG was 75.4%, 78.3%, and 67.0%, respectively. The two methods proposed can automatically detect the lumen borders and characterize the composition of the superficial plaque in OCT images and greatly reduce the time spent by doctors in segmenting and identifying plaques. CNN provided better segmentation accuracies compared to those achieved by SVM. Acknowledgement: This research was supported in part by NIH grant R01 EB004759, National Sciences Foundation of China grant 11672001 and a Jiangsu Province Science and Technology Agency grant BE2016785.

Fully Convolutional Boundary Regression for Retina OCT Segmentation.

A major goal of analyzing retinal optical coherence tomography (OCT) images is retinal layer segmentation. Accurate automated algorithms for segmenting smooth continuous layer surfaces, with correct hierarchy (topology) are desired for monitoring disease progression. State-of-the-art methods use a trained classifier to label each pixel into background, layer, or surface pixels. The final step of extracting the desired smooth surfaces with correct topology are mostly performed by graph methods (e.g. shortest path, graph cut). However, manually building a graph with varying constraints by retinal region and pathology and solving the minimization with specialized algorithms will degrade the flexibility and time efficiency of the whole framework. In this paper, we directly model the distribution of surface positions using a deep network with a fully differentiable soft argmax to obtain smooth, continuous surfaces in a single feed forward operation. A special topology module is used in the deep network both in the training and testing stages to guarantee the surface topology. An extra deep network output branch is also used for predicting lesion and layers in a pixel-wise labeling scheme. The proposed method was evaluated on two publicly available data sets of healthy controls, subjects with multiple sclerosis, and diabetic macular edema; it achieves state-of-the art sub-pixel results.

Association of Optical Coherence Tomography Angiography of Collaterals in Retinal Vein Occlusion With Major Venous Outflow Through the Deep Vascular Complex

Analysis of collateral vessel formation following retinal vein occlusion may advance our understanding of the venous outflow anatomy in the macula. To determine the location of collateral vessels with optical coherence tomography (OCT) angiography imaging. Observational retrospective cohort study. Collateral vessel formation was studied with OCT angiography (OCTA) in patients with retinal vein occlusion (RVO). The study took place at 2 retinal practices (Vitreous Retina Macula Consultants of New York and Stein Eye Institute, University of California, Los Angeles), with patient records retrieved from March 2015 to August 2017. Data analysis was completed in November 2017. Collaterals identified with fundus photography and/or fluorescein angiography were analyzed with OCTA to determine their course through the superficial vascular plexus (SVP) and the deep vascular complex (DVC). Collateral vessel pathways through the SVP and DVC were analyzed with cross-sectional and en face OCT and OCTA segmentation and color-coded volume renderings prepared from raw OCTA voxel data. From 23 eyes (22 branch and 1 hemispheric retinal vein occlusion ) of 23 patients (mean [SD] age, 73 [11] years), 101 collateral vessels were identified and analyzed (mean [SD], 4.4 [2.0]; range, 2-9 collateral per eye). On OCTA, the collaterals appeared as curvilinear dilated flow signals that connected veins across the horizontal raphe or veins on opposite sides of an occluded venous segment within the same retinal hemisphere. Of the 101 collaterals analyzed, all showed greater flow signal in the DVC, and all had some portion of their course identified within the DVC. No collaterals were found exclusively in the SVP. Volume renderings for 3 cases confirmed qualitatively that retinal collateral vessels course through the retina predominantly at the level of the DVC. Based on a limited number of cases, all collateral vessels associated with retinal vein occlusion were found to course through the DVC. The absence of collaterals isolated to the SVP supports a serial arrangement of the SVP and DVC, with venous drainage predominantly coursing through the DVC.

QUANTITATIVE ANALYSIS OF THE INNER RETINAL LAYER THICKNESSES IN AGE-RELATED MACULAR DEGENERATION USING CORRECTED OPTICAL COHERENCE TOMOGRAPHY SEGMENTATION.

To characterize inner retinal damage in patients with dry age-related macular degeneration (AMD) using high-resolution spectral domain optical coherence tomography images. Sixty eyes of 60 patients with AMD were categorized using the Age-Related Eye Disease Study (AREDS) severity scale. Spectral domain optical coherence tomography images of these patients were quantified by manually correcting the segmentation of each retinal layer, including the retinal nerve fiber layer, ganglion cell layer, and inner plexiform layer to ensure accurate delineation of layers. The mean ganglion cell complex thickness values (ganglion cell layer + inner plexiform layer + retinal nerve fiber layer) were compared with 30 eyes of 30 healthy subjects. Ninety percent of eyes (81 eyes) required manual correction of segmentation. Compared with healthy subjects, mean ganglion cell complex thicknesses significantly decreased in more advanced dry AMD eyes, and this decrease was predominantly related to a change in inner plexiform layer thickness. There was no significant difference in thickness-related measurements between milder dry AMD (AREDS-2) eyes and healthy eyes (P > 0.05). In patients with dry AMD, automatic optical coherence tomography segmentation algorithms may be erroneous. As the severity of dry AMD increases, the inner plexiform layer layer becomes thinned, suggesting that transsynaptic degeneration may be occurring, as the photoreceptor layer is affected by AMD.

Predicting Surgical Success in Patients with Idiopathic Epiretinal Membrane Using the Spectral-Domain Optical Coherence Tomography Segmentation Module for Single Retinal Layer Analysis

ABSTRACTIntroduction: Idiopathic epiretinal membrane (ERM) is a proliferation of cells formed on the internal surface of the retina and may cause a slow decrease in visual acuity (VA). The aim of this study was to evaluate the individual layers of the retina by optical coherence tomography (OCT) before and after vitrectomy with ERM peeling in order to refine surgical decision-making.Methods: Forty-seven eyes of 45 patients (aged 55–87 years) with ERM were enrolled retrospectively from a tertiary referral center. OCT examination was performed preoperatively and at a mean of 3.2 months postoperatively in all cases. Nine retinal surfaces were subjected to automated all-layer segmentation using the manufacturer’s software and assessed for their correlation with VA.Results: There was a significant correlation between the initial retinal morphology and change in VA postoperatively. Patients who gained at least two lines of VA had a significantly higher total retinal perimacular volume and retinal nerve fiber layer (each p < 0.0001) preoperatively.Conclusion: Patients with high preoperative retinal volumes and therefore increased tractive components seemed to benefit more from surgery than those with low tractive components.