Segment Optical Coherence Tomography Research Articles

Partial Image Active Annotation (PIAA): An Efficient Active Learning Technique Using Edge Information in Limited Data Scenarios

AbstractActive learning (AL) algorithms are increasingly being used to train models with limited data for annotation tasks. However, the selection of data for AL is a complex issue due to the restricted information on unseen data. To tackle this problem, a technique we refer to as Partial Image Active Annotation (PIAA) employs the edge information of unseen images as prior knowledge to gauge uncertainty. This uncertainty is determined by examining the divergence and entropy in model predictions across edges. The resulting measure is then applied to choose superpixels from input images for active annotation. We demonstrate the effectiveness of PIAA in multi-class Optical Coherence Tomography (OCT) segmentation tasks, attaining a Dice score comparable to state-of-the-art OCT segmentation algorithms trained with extensive annotated data. Concurrently, we successfully reduce annotation label costs to 12%, 2.3%, and 3%, respectively, across three publicly accessible datasets (Duke, AROI, and UMN).

Segmentation and quantitative analysis of optical coherence tomography (OCT) images of laser burned skin based on deep learning

Evaluation of skin recovery is an important step in the treatment of burns. However, conventional methods only observe the surface of the skin and cannot quantify the injury volume. Optical coherence tomography (OCT) is a non-invasive, non-contact, real-time technique. Swept source OCT uses near infrared light and analyzes the intensity of light echo at different depths to generate images from optical interference signals. To quantify the dynamic recovery of skin burns over time, laser induced skin burns in mice were evaluated using deep learning of Swept source OCT images. A laser-induced mouse skin thermal injury model was established in thirty Kunming mice, and OCT images of normal and burned areas of mouse skin were acquired at day 0, day 1, day 3, day 7, and day 14 after laser irradiation. This resulted in 7000 normal and 1400 burn B-scan images which were divided into training, validation, and test sets at 8:1.5:0.5 ratio for the normal data and 8:1:1 for the burn data. Normal images were manually annotated, and the deep learning U-Net model (verified with PSPNe and HRNet models) was used to segment the skin into three layers: the dermal epidermal layer, subcutaneous fat layer, and muscle layer. For the burn images, the models were trained to segment just the damaged area. Three-dimensional reconstruction technology was then used to reconstruct the damaged tissue and calculate the damaged tissue volume. The average IoU value and f-score of the normal tissue layer U-Net segmentation model were 0.876 and 0.934 respectively. The IoU value of the burn area segmentation model reached 0.907 and f-score value reached 0.951. Compared with manual labeling, the U-Net model was faster with higher accuracy for skin stratification. OCT and U-Net segmentation can provide rapid and accurate analysis of tissue changes and clinical guidance in the treatment of burns.

Deep-Learning-Based Group Pointwise Spatial Mapping of Structure to Function in Glaucoma

PurposeTo establish generalizable point-wise spatial relationship between structure and function through occlusion analysis of a deep-learning (DL) model for predicting the visual field (VF) sensitivities from three-dimensional (3D) optical coherence tomography (OCT) scan. DesignRetrospective cross-sectional study. Participants2151 eyes from 1129 patients. MethodsA DL model was trained to predict 52 VF sensitivities of 24-2 standard automated perimetry from 3D spectral-domain OCT images of the optic nerve head (ONH) with 12915 OCT-VF pairs. Using occlusion analysis, the contribution of each individual cube covering a 240 x 240 x 31.25 μm region of the ONH to the model's prediction was systematically evaluated for each OCT-VF pair in a separate test set that consisted of 996 OCT-VF pairs. After simple translation (shifting in x and y-axes to match the ONH center), group t-statistic maps were derived to visualize statistically significant ONH regions for each VF test point within a group. This analysis allowed for understanding the importance of each super voxel (240 x 240 x 31.25 μm covering the entire 4.32 x 4.32 x 1.125 mm ONH cube) in predicting VF test points for specific patient groups. Main Outcome MeasuresThe region at the ONH corresponding to each VF test point and the effect of the former on the latter. ResultsThe test set was divided to two groups, the healthy-to-early-glaucoma group (792 OCT-VF pairs, VF mean deviation (MD): -1.32 ± 1.90 dB) and the moderate-to-advanced-glaucoma group (204 OCT-VF pairs, VF MD: -17.93 ± 7.68 dB). Two-dimensional group t-statistic maps (x, y projection) were generated for both groups, assigning related ONH regions to visual field test points. The identified influential structural locations for VF sensitivity prediction at each test point aligned well with existing knowledge and understanding of structure-function spatial relationships. ConclusionsThis study successfully visualized the global trend of point-by-point spatial relationships between OCT-based structure and VF-based function without the need for prior knowledge or segmentation of OCTs. The revealed spatial correlations were consistent with previously published mappings. This presents possibilities of learning from trained machine learning models without applying any prior knowledge, potentially robust and free from bias.

Two-stage adversarial learning based unsupervised domain adaptation for retinal OCT segmentation.

Deep learning based optical coherence tomography (OCT) segmentation methods have achieved excellent results, allowing quantitative analysis of large-scale data. However, OCT images are often acquired by different devices or under different imaging protocols, which leads to serious domain shift problem. This in turn results in performance degradation of segmentation models. Aiming at the domain shift problem, we propose a two-stage adversarial learning based network (TSANet) that accomplishes unsupervised cross-domain OCT segmentation. In the first stage, a Fourier transform based approach is adopted to reduce image style differences from the image level. Then, adversarial learning networks, including a segmenter and a discriminator, are designed to achieve inter-domain consistency in the segmentation output. In the second stage, pseudo labels of selected unlabeled target domain training data are used to fine-tune the segmenter, which further improves its generalization capability. The proposed method was tested on cross-domain datasets for choroid or retinoschisis segmentation tasks. For choroid segmentation, the model was trained on 400 images and validated on 100 images from the source domain, and then trained on 1320 unlabeled images and tested on 330 images from target domain I, and also trained on 400 unlabeled images and tested on 200 images from target domain II. For retinoschisis segmentation, the model was trained on 1284 images and validated on 312 images from the source domain, and then trained on 1024 unlabeled images and tested on 200 images from the target domain. The proposed method achieved significantly improved results over that without domain adaptation, with improvement of 8.34%, 55.82% and 3.53% in intersection over union (IoU) respectively for the three test sets. The performance is better than some state-of-the-art domain adaptation methods. The proposed TSANet, with image level adaptation, feature level adaptation and pseudo-label based fine-tuning, achieved excellent cross-domain generalization. This alleviates the burden of obtaining additional manual labels when adapting the deep learning model to new OCT data.

Deep Learning-Based Retinal Layer Segmentation in Optical Coherence Tomography Scans of Patients with Inherited Retinal Diseases.

In optical coherence tomography (OCT) scans of patients with inherited retinal diseases (IRDs), the measurement of the thickness of the outer nuclear layer (ONL) has been well established as a surrogate marker for photoreceptor preservation. Current automatic segmentation tools fail in OCT segmentation in IRDs, and manual segmentation is time-consuming. Patients with IRD and an available OCT scan were screened for the present study. Additionally, OCT scans of patients without retinal disease were included to provide training data for artificial intelligence (AI). We trained a U-net-based model on healthy patients and applied a domain adaption technique to the IRD patients' scans. We established an AI-based image segmentation algorithm that reliably segments the ONL in OCT scans of IRD patients. In a test dataset, the dice score of the algorithm was 98.7%. Furthermore, we generated thickness maps of the full retinal thickness and the ONL layer for each patient. Accurate segmentation of anatomical layers on OCT scans plays a crucial role for predictive models linking retinal structure to visual function. Our algorithm for segmentation of OCT images could provide the basis for further studies on IRDs.

Rapid measurement of epidermal thickness in OCT images of skin

Epidermal thickness (ET) changes are associated with several skin diseases. To measure ET, segmentation of optical coherence tomography (OCT) images is essential; manual segmentation is very time-consuming and requires training and some understanding of how to interpret OCT images. Fast results are important in order to analyze ET over different regions of skin in rapid succession to complete a clinical examination and enable the physician to discuss results with the patient in real time. The well-known CNN-graph search (CNN-GS) methodology delivers highly accurate results, but at a high computational cost. Our objective was to build a computational core, based on CNN-GS, able to accurately segment OCT skin images in real time. We accomplished this by fine-tuning the hyperparameters, testing a range of speed-up algorithms including pruning and quantization, designing a novel pixel-skipping process, and implementing the final product with efficient use of core and threads on a multicore central processing unit (CPU). We name this product CNN-GS-skin. The method identifies two defined boundaries on OCT skin images in order to measure ET. We applied CNN-GS-skin to OCT skin images, taken from various body sites of 63 healthy individuals. Compared with CNN-GS, our described method reduced computation time by 130 ×\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\ imes$$\\end{document} with minimal reduction in ET determination accuracy (from 96.38 to 94.67%).

OCT Segmentation Errors with Bruch's Membrane Opening-Minimum Rim Width as Compared with Retinal Nerve Fiber Layer Thickness

To compare the magnitude and location of automated segmentation errors of the Bruch's membrane opening-minimum rim width (BMO-MRW) and retinal nerve fiber layer thickness (RNFLT). Cross-sectional study. We included 162 glaucoma suspect or open-angle glaucoma eyes from 162 participants. We used spectral-domain optic coherence tomography (Spectralis 870 nm, Heidelberg Engineering) to image the optic nerve with 24 radial optic nerve head B-scans and a 12-degree peripapillary circle scan, and exported the native "automated segmentation only" results for BMO-MRW and RNFLT. We also exported the results after "manual refinement" of the measurements. We calculated the absolute and proportional error globally and within the 12 30-degree sectors of the optic disc. We determined whether the glaucoma classifications were different between BMO-MRW and RNFLT as a result of manual and automatic segmentation. The absolute error mean was larger for BMO-MRW than for RNFLT (10.8 μm vs. 3.58 μm, P < 0.001). However, the proportional errors were similar (4.3% vs. 4.4%, P= 0.47). In a multivariable regression model, errors in BMO-MRW were not significantly associated with age, location, magnitude, or severity of glaucoma loss (all P ≥ 0.05). However, larger RNFLT errors were associated with the superior and inferior sector location, thicker nerve fiber layer, and worse visual field (all P < 0.05). Errors in BMO-MRW and RNFLT were not likely to occur in the same sector location (R2= 0.001; P= 0.15). With manual refinement, the glaucoma classification changed in 7.8% and 6.2% of eyes with BMO-MRW and RNFLT, respectively. Both BMO-MRW and RNFLT measurements included segmentation errors, which did not seem to have a common location, and may result in differences in glaucoma classification. Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

Deep learning network (DL-Net) based classification and segmentation of multi-class retinal diseases using OCT scans

The most frequent cause of blindness in industrialized nations is age-related macular degeneration (AMD), particularly in persons over 60. In recent years in this field, three key factors have led to an increase in the workload of experts and the healthcare system: 1) population aging worldwide prevalence, 2) AMD's chronic nature, and 3) more widespread usage of the retinal optical coherence tomography (OCT) imaging technology. The establishment of fully automated diagnosis systems has recently been made possible by recent developments in the deep learning field. The main objective of the research is to develop a new deep learning-based model using OCT images. The performance for classification and segmentation of retinal diseases is improved by the proposed model through effectively capturing inter-scale features and combining these features using convolutional blocks. Then, we classify volumetric OCT images via a new deep learning-based model. For multi-class classification and segmentation of ocular diseases, the OCT scans of the human eye are used in this research to demonstrate a Deep Learning Network (DL-Net) model by automatically recognizing normal, diabetic macular edema (DME), choroidal neovascularization (CNV), AMD, and drusen images. This research introduces the Modified ResNet-50 approach and Image Processing for multiple OCT image classification. This research presents an efficient diagnostic technique for image segmentation based on a Bi-LSTM-based deep recurrent convolutional neural network (DRCNN). The modified SqueezeNet model analyzes the volumetric segmentation of OCT images. The volumetric publicly available datasets are used to analyze the proposed model. The proposed multi-scale structure model outperforms several well-known OCT classification and segmentation frameworks. 99.76% accuracy is achieved by the proposed model respectively. In healthcare settings, the proposed methodology can be used as a diagnostic instrument to help medical experts make better-diagnosing decisions, as shown by the encouraging proposed architecture's qualitative evaluations and quantitative results by generating a confusion matrix.

The effect of optical degradation from cataract using a new Deep Learning optical coherence tomography segmentation algorithm.

To assess the validity of the results of a freely available online Deep Learning segmentation tool and its sensitivity to noise introduced by cataract. The OCT images were collected with a Spectralis SD-OCT (Heidelberg Engineering, Heidelberg, Germany) as part of normal clinical practice. Data were segmented using a freely available online tool called Relayer ( https://www.relayer.online/ ), based on a cross-platform Deep Learning segmentation architecture specifically adapted for retinal OCT images. The segmentations were read into MATLAB (The MathWorks, Natick, MA, USA) and analyzed. There was an excellent agreement between the ETDRS measurements obtained from the two algorithms. Upon visual inspection, the segmentation based on Deep Learning obtained with Relayer appeared more accurate except in one case of apparent good quality image showing interrupted segmentations in some of the B-scans. A freely available online Deep Learning segmentation tool showed good and promising performance in healthy retinas before and after cataract surgery, proving robust to optical degradation of the image from media opacities.

Cynomolgus monkey’s retina volume reference database based on hybrid deep learning optical coherence tomography segmentation

Cynomolgus monkeys (Macaca fascicularis) are commonly used in pre-clinical ocular studies. However, studies that report the morphological features of the macaque retina are based only on minimal sample sizes; therefore, little is known about the normal distribution and background variation. This study was conducted using optical coherence tomography (OCT) imaging to investigate the variations in retinal volumes of healthy cynomolgus monkeys and the effects of sex, origin, and eye side on the retinal volumes to establish a comprehensive reference database. A machine-learning algorithm was employed to segment the retina within the OCT data (i.e., generated pixel-wise labels). Furthermore, a classical computer vision algorithm has identified the deepest point in a foveolar depression. The retinal volumes were determined and analyzed based on this reference point and segmented retinal compartments. Notably, the overall foveolar mean volume in zone 1, which is the region of the sharpest vision, was 0.205 mm3 (range 0.154–0.268 mm3), with a relatively low coefficient of variation of 7.9%. Generally, retinal volumes exhibit a relatively low degree of variation. However, significant differences in the retinal volumes due to the monkey’s origin were identified. Additionally, sex had a significant impact on the paracentral retinal volume. Therefore, the origin and sex of cynomolgus monkeys should be considered when evaluating the macaque retinal volumes based on this dataset.

Longitudinal deep network for consistent OCT layer segmentation.

Retinal layer thickness is an important bio-marker for people with multiple sclerosis (PwMS). In clinical practice, retinal layer thickness changes in optical coherence tomography (OCT) are widely used for monitoring multiple sclerosis (MS) progression. Recent developments in automated retinal layer segmentation algorithms allow cohort-level retina thinning to be observed in a large study of PwMS. However, variability in these results make it difficult to identify patient-level trends; this prevents patient specific disease monitoring and treatment planning using OCT. Deep learning based retinal layer segmentation algorithms have achieved state-of-the-art accuracy, but the segmentation is performed on each individual scan without utilizing longitudinal information, which can be important in reducing segmentation error and reveal subtle changes in retinal layers. In this paper, we propose a longitudinal OCT segmentation network which achieves more accurate and consistent layer thickness measurements for PwMS.

Retinal Blood Vessel Analysis Using Optical Coherence Tomography (OCT) in Multiple Sclerosis

Background: Both greater retinal neurodegenerative pathology and greater cardiovascular burden are seen in people with multiple sclerosis (pwMS). Studies also describe multiple extracranial and intracranial vascular changes in pwMS. However, there have been few studies examining the neuroretinal vasculature in MS. Our aim is to determine differences in retinal vasculature between pwMS and healthy controls (HCs) and to determine the relationship between retinal nerve fiber layer (RNFL) thickness and retinal vasculature characteristics. Methods: A total of 167 pwMS and 48 HCs were scanned using optical coherence tomography (OCT). Earlier OCT scans were available for 101 pwMS and 35 HCs for an additional longitudinal analysis. Segmentation of retinal vasculature was performed in a blinded manner in MATLAB's optical coherence tomography segmentation and evaluation GUI (OCTSEG) software. Results: PwMS has fewer retinal blood vessels when compared to HCs (35.1 vs. 36.8, p = 0.017). Over the 5.4 year follow up, and when compared to HCs, pwMS has a significant decrease in number of retinal vessels (average loss of -3.7 p = 0.007). Moreover, the total vessel diameter in pwMS does not change when compared to the increase in vessel diameter in the HCs (0.06 vs. 0.3, p = 0.017). Only in pwMS is there an association between lower RNFL thickness and fewer retinal vessel number and smaller diameter (r = 0.191, p = 0.018 and r = 0.216, p = 0.007). Conclusions: Over 5 years, pwMS exhibit significant retinal vascular changes that are related to greater atrophy of the retinal layers.

Cone Structure and Function in RPGR- and USH2A-Associated Retinal Degeneration

To compare cone structure and function between RPGR- and USH2A-associated retinal degeneration. Retrospective, observational, cross-sectional study. This multicenter study included 13 eyes (9 participants) with RPGR-related X-linked retinitis pigmentosa (RPGR), 15 eyes (10 participants) with USH2A-related Usher syndrome type 2 (USH2), 16 eyes (9 participants) with USH2A-related autosomal recessive retinitis pigmentosa (ARRP), and 7 normal eyes (6 participants). Structural measures included cone spacing and density from adaptive optics scanning laser ophthalmoscopy and photoreceptor inner segment (IS), outer segment (OS), and outer nuclear layer (ONL) thickness from optical coherence tomography (OCT) images. OCT angiography images were used to study choriocapillaris flow deficit percent (CCFD). Cone function was assessed by fundus-guided microperimetry. Measures were compared at designated regions using analysis of variance with pairwise comparisons among disease groups, adjusted for disease duration and eccentricity. OCT segmentation revealed shorter OS and IS, with reduced ONL thickness in RPGR compared to normal (OS: P < .001, IS: P=.001, ONL: P=.005), USH2 (OS: P=.01, IS: P=.03, ONL: P=.03), or ARRP (OS: P=.001, ONL: P=.03). Increased cone spacing was observed in both RPGR (P=.03) and USH2 compared with normal (P=.048). The mean CCFD in RPGR was greater than in USH2 (P=.02). Microperimetry demonstrated below-normal regional sensitivity in RPGR (P=.004), USH2 (P=.02), and ARRP (P=.009), without significant intergroup differences. Outer retinal structure and choriocapillaris perfusion were more abnormal in RPGR- than USH2A-related retinal degenerations, whereas there were no significant differences in below-normal regional sensitivity between each rod-cone degeneration associated with variants in these 2 genes expressed at the photoreceptor-connecting cilium.

Brain-derived neurotrophic factor levels and macular ganglion cell-inner plexiform layer thickness in macular telangiectasia type 2.

To determine brain-derived neurotrophic factor (BDNF) levels in the serum and aqueous humor (AH) and assess the relationship between BDNF levels and the thickness of the macular ganglion cell-inner plexiform layer (GCIPL) in macular telangiectasia type 2 (MacTel). This study included 25 patients with MacTel (MacTel group) and 25 control subjects (control group). The levels of BDNF in the serum and AH were tested using an enzyme-binding immunosorbent assay. GCIPL thickness was measured by segmentation analysis using optical coherence tomography (OCT). There was no significant difference in the mean serum BDNF levels between the MacTel and control groups (p = 0.145). The average BDNF level in the AH was significantly lower than that in the control group (p = 0.026). OCT segmentation analyses revealed that the minimum GCIPL thickness was significantly lower in the MacTel group than in the control group (p = 0.039). In the correlation analysis of BDNF levels with GCIPL thickness, significant correlations existed between the BDNF level of the AH and minimum GCIPL thickness in the MacTel group. The concentration of BDNF in the AH was decreased in the MacTel group, and this reduction was related to the minimum GCIPL thickness. The low BDNF levels detected in the MacTel group may have resulted in thinning of the GCIPL due to the loss of retinal ganglion cells.

Retinal blood vessel analysis using optical coherence tomography in multiple sclerosis

Background: Both greater retinal neurodegenerative pathology and greater cardiovascular burden have been seen in persons with multiple sclerosis (pwMS).1,2 Moreover, studies have described multiple extracranial and intracranial vasculature changes in pwMS.3 However, only a few studies have examined the retinal vasculature in multiple sclerosis (MS).&#x0D; Objectives: To determine if there are differences in retinal vasculature between pwMS and healthy controls (HCs) and their relationship to peripapillary retinal nerve fiber layer (pRNFL) thickness.&#x0D; Materials and methods: A total of 167 pwMS (113 relapsing-remitting MS (RRMS) and 54 progressive MS (PMS)) and 48 HCs were scanned using optical coherence tomography (OCT). Earlier OCT scans were available in a smaller sample size of 101 pwMS and 35 HCs for additional longitudinal 5-year follow-up analysis. The semiautomated segmentation of the retinal vasculature was performed in a blinded manner on peripapillary scans using the optical coherence tomography segmentation and evaluation GUI (OCTSEG) in MatLab. (Figure 1). Automated segmentation of the pRNFL was performed in the native Heidelberg OCT software. The sum of bilateral measures of total retinal vessel diameter, the total number of retinal vessels and average vessel diameter were calculated. Independent sample t-test and paired t-test were used for cross-sectional and longitudinal analyses, respectively and non-parametric Spearman’s test for determining correlations.&#x0D; Results: PwMS had a significantly smaller total vessel diameter (2.5 cm vs 2.7 cm, age-adjusted p=0.017) and numerically fewer number of retinal vessels when compared to HCs (35.1 vs 36.8, age-adjusted p=0.167). No significant differences between the pwRRMS and pwPMS were found. Over the follow-up, pwMS had significant decrease in number of retinal vessels (36.7 vs. 33.0, p&lt;0.001) and significant increase in the average vessel diameter (0.072cm vs. 0.081cm, p&lt;0.001). No longitudinal changes in the HCs were noted. Only in pwMS, lower pRNFL was associated with fewer retinal vessels and total vessel diameter (r=0.191, p=0.018 and r=0.216, p=0.007).&#x0D; Conclusions: PwMS have retinal vasculature that results in smaller and fewer retinal vessels when compared to HCs that were related to reduced pRNFL. Over time, a reduction of retinal vasculature occurred. Future investigations should determine the relevance of retinal vasculature in regards to MS disease outcomes, presence of cardiovascular abnormalities and cerebral/retinal perfusion.

Normative Data and Conversion Equation for Spectral-Domain Optical Coherence Tomography in an International Healthy Control Cohort.

Spectral-domain (SD-) optical coherence tomography (OCT) can reliably measure axonal (peripapillary retinal nerve fiber layer [pRNFL]) and neuronal (macular ganglion cell + inner plexiform layer [GCIPL]) thinning in the retina. Measurements from 2 commonly used SD-OCT devices are often pooled together in multiple sclerosis (MS) studies and clinical trials despite software and segmentation algorithm differences; however, individual pRNFL and GCIPL thickness measurements are not interchangeable between devices. In some circumstances, such as in the absence of a consistent OCT segmentation algorithm across platforms, a conversion equation to transform measurements between devices may be useful to facilitate pooling of data. The availability of normative data for SD-OCT measurements is limited by the lack of a large representative world-wide sample across various ages and ethnicities. Larger international studies that evaluate the effects of age, sex, and race/ethnicity on SD-OCT measurements in healthy control participants are needed to provide normative values that reflect these demographic subgroups to provide comparisons to MS retinal degeneration. Participants were part of an 11-site collaboration within the International Multiple Sclerosis Visual System (IMSVISUAL) consortium. SD-OCT was performed by a trained technician for healthy control subjects using Spectralis or Cirrus SD-OCT devices. Peripapillary pRNFL and GCIPL thicknesses were measured on one or both devices. Automated segmentation protocols, in conjunction with manual inspection and correction of lines delineating retinal layers, were used. A conversion equation was developed using structural equation modeling, accounting for clustering, with healthy control data from one site where participants were scanned on both devices on the same day. Normative values were evaluated, with the entire cohort, for pRNFL and GCIPL thicknesses for each decade of age, by sex, and across racial groups using generalized estimating equation (GEE) models, accounting for clustering and adjusting for within-patient, intereye correlations. Change-point analyses were performed to determine at what age pRNFL and GCIPL thicknesses exhibit accelerated rates of decline. The healthy control cohort (n = 546) was 54% male and had a wide distribution of ages, ranging from 18 to 87 years, with a mean (SD) age of 39.3 (14.6) years. Based on 346 control participants at a single site, the conversion equation for pRNFL was Cirrus = -5.0 + (1.0 × Spectralis global value). Based on 228 controls, the equation for GCIPL was Cirrus = -4.5 + (0.9 × Spectralis global value). Standard error was 0.02 for both equations. After the age of 40 years, there was a decline of -2.4 μm per decade in pRNFL thickness ( P < 0.001, GEE models adjusting for sex, race, and country) and -1.4 μm per decade in GCIPL thickness ( P < 0.001). There was a small difference in pRNFL thickness based on sex, with female participants having slightly higher thickness (2.6 μm, P = 0.003). There was no association between GCIPL thickness and sex. Likewise, there was no association between race/ethnicity and pRNFL or GCIPL thicknesses. A conversion factor may be required when using data that are derived between different SD-OCT platforms in clinical trials and observational studies; this is particularly true for smaller cross-sectional studies or when a consistent segmentation algorithm is not available. The above conversion equations can be used when pooling data from Spectralis and Cirrus SD-OCT devices for pRNFL and GCIPL thicknesses. A faster decline in retinal thickness may occur after the age of 40 years, even in the absence of significant differences across racial groups.

LOCTseg: A lightweight fully convolutional network for end-to-end optical coherence tomography segmentation

This article presents a novel end-to-end automatic solution for semantic segmentation of optical coherence tomography (OCT) images. OCT is a non-invasive imaging technology widely used in clinical practice due to its ability to acquire high-resolution cross-sectional images of the ocular fundus. Due to the large variability of the retinal structures, OCT segmentation is usually carried out manually and requires expert knowledge. This study introduces a novel fully convolutional network (FCN) architecture designated by LOCTSeg, for end-to-end automatic segmentation of diagnostic markers in OCT b-scans. LOCTSeg is a lightweight deep FCN optimized for balancing performance and efficiency. Unlike state-of-the-art FCNs used in image segmentation, LOCTSeg achieves competitive inference speed without sacrificing segmentation accuracy. The proposed LOCTSeg is evaluated on two publicly available benchmarking datasets: (1) annotated retinal OCT image database (AROI) comprising 1136 images, and (2) healthy controls and multiple sclerosis lesions (HCMS) consisting of 1715 images. Moreover, we evaluated the proposed LOCTSeg with a private dataset of 250 OCT b-scans acquired from epiretinal membrane (ERM) and healthy patients. Results of the evaluation demonstrate empirically the effectiveness of the proposed algorithm, which improves the state-of-the-art Dice score from 69% to 73% and from 91% to 92% on AROI and HCMS datasets, respectively. Furthermore, LOCTSeg outperforms comparable lightweight FCNs’ Dice score by margins between 4% and 15% on ERM segmentation.

Volumetric subfield analysis of cynomolgus monkey's choroid derived from hybrid machine learning optical coherence tomography segmentation.

This study aimed to provide volumetric choroidal readings regarding sex, origin, and eye side from healthy cynomolgus monkey eyes as a reference database using optical coherence tomography (OCT) imaging. A machine learning (ML) algorithm was used to extract the choroid from the volumetric OCT data. Classical computer vision methods were then applied to automatically identify the deepest location in the foveolar depression. The choroidal thickness was determined from this reference point. A total of 374 eyes of 203 cynomolgus macaques from Asian and Mauritius origin were included in the analysis. The overall subfoveolar mean choroidal volume in zone 1, in the region of the central bouquet, was 0.156 mm3 (range, 0.131-0.193 mm3). For the central choroid volume, the coefficient of variation (CV) was found of 6.3%, indicating relatively little variation. Our results show, based on analyses of variance, that monkey origin (Asian or Mauritius) does not influence choroid volumes. Sex had a significant influence on choroidal volumes in the superior-inferior axis (p ≤ 0.01), but not in the fovea centralis. A homogeneous foveolar choroidal architecture was also observed.

Cynomolgus monkey’s choroid reference database derived from hybrid deep learning optical coherence tomography segmentation

Cynomolgus monkeys exhibit human-like features, such as a fovea, so they are often used in non-clinical research. Nevertheless, little is known about the natural variation of the choroidal thickness in relation to origin and sex. A combination of deep learning and a deterministic computer vision algorithm was applied for automatic segmentation of foveolar optical coherence tomography images in cynomolgus monkeys. The main evaluation parameters were choroidal thickness and surface area directed from the deepest point on OCT images within the fovea, marked as the nulla with regard to sex and origin. Reference choroid landmarks were set underneath the nulla and at 500 µm intervals laterally up to a distance of 2000 µm nasally and temporally, complemented by a sub-analysis of the central bouquet of cones. 203 animals contributed 374 eyes for a reference choroid database. The overall average central choroidal thickness was 193 µm with a coefficient of variation of 7.8%, and the overall mean surface area of the central bouquet temporally was 19,335 µm2 and nasally was 19,283 µm2. The choroidal thickness of the fovea appears relatively homogeneous between the sexes and the studied origins. However, considerable natural variation has been observed, which needs to be appreciated.

Retinal ganglion cell layer thickness and volume measured by OCT changes with age, sex, and axial length in a healthy population

BackgroundThe ganglion cell layer (GCL) measurements with Optical Coherence Tomography (OCT) are important for both ophthalmologists and neurologists because of their association with many ophthalmic and neurological diseases. Different factors can affect these measurements, such as brain pathologies, ocular axial length (AL) as well as age and sex. Studies conducted to measure the GCL have overlooked many of these factors. The purpose of this study is to examine the effect of age, sex, and AL on normal retinal GCL thickness and volume in a healthy population without any neurological diseases.MethodsA prospective cross-sectional study was designed to measure GCL thickness and total volume with OCT with automated segmentation and manual correction where needed. Visual acuity, AL, and autorefraction were also measured. A mixed linear model was used to determine the association of the effect of the various parameters on the GCL thickness and volume.ResultsOne hundred and sixteen eyes of 60 subjects (12–76 years of age, 55% female) were examined of which 77% had 0 ± 2 D of spherical equivalent, and mean axial length was 23.86 mm. About 25% of the OCT-automated GCL measurements required manual correction. GCL thickness did not differ in similar anatomic regions in right and left eyes (P > 0.05). GCL volume was greater in males relative to females after adjustment for age and axial length (1.13 ± 0.07 mm3 for males vs 1.09 ± 0.09 mm3 for females; P = 0.031). GCL thickness differed between males and females in the inner retinal ring (P = 0.025) but not in the outer ring (P = 0.66). GCL volume declined with age (P = 0.031) but not after adjustment for sex and axial length (P = 0.138). GCL volume declined with longer axial length after adjustment for age and sex (P = 0.048).ConclusionAge, sex and axial length should be taken into consideration when measuring the GCL thickness and volume with OCT. Automated OCT segmentation should be reviewed for manual adjustments.