Retinal Optical Coherence Tomography Scans Research Articles

Optical Coherence Tomography in Schizophrenia Spectrum Disorders: A Systematic Review and Meta-analysis

BackgroundInner retinal atrophy has been demonstrated in schizophrenia spectrum disorder (SSD) using optical coherence tomography (OCT). This systematic review and meta-analysis investigated the role of contemporary Fourier domain OCT devices in SSD. MethodsMEDLINE, PubMed, Scopus, Embase, PsycInfo, PYSNDEX, World Health Organization, and Cochrane databases were searched from inception until May 2022. All peer-reviewed adult SSD case-control studies using Fourier domain OCT were included. Ocular pathologies known to affect retinal OCT scans were excluded. Search, data appraisal, and summary data extraction were independently performed by 2 authors. ResultsThe review criteria was met by k = 36 studies, with k = 24 studies (1074 cases, 854 controls) suitable for meta-analysis. The SSD group exhibited a thinner global peripapillary retinal nerve fiber layer (−3.26 μm, 95% CI, −5.07 to −1.45, I2 = 64%, k = 21), thinner average macular layer (−7.88 μm, 95% CI, −12.73 to −3.04, I2 = 65%, k = 11), and thinner macular ganglion cell-inner plexiform sublayer (−2.44 μm, 95% CI, −4.13 to −0.76, I2 = 30%, k = 8) compared with the control group. Retinal nerve fiber layer findings remained significant after exclusion of metabolic disease, low quality, outlier, and influential studies. Studies involving eye examinations to exclude eye disease were associated with greater atrophy in SSD. Except for cardiometabolic disease, most studies did not report clinically significant covariate data known to influence retinal thickness. ConclusionsIndividuals with SSD generally exhibited retinal atrophy, possibly paralleling reduced brain volumes documented in clinical imaging. Prospective longitudinal studies that collect clinical data, including various illness phases, and control for confounders will be necessary to evaluate retinal atrophy as a biomarker in SSD.

RetiFluidNet: A Self-Adaptive and Multi-Attention Deep Convolutional Network for Retinal OCT Fluid Segmentation.

Optical coherence tomography (OCT) helps ophthalmologists assess macular edema, accumulation of fluids, and lesions at microscopic resolution. Quantification of retinal fluids is necessary for OCT-guided treatment management, which relies on a precise image segmentation step. As manual analysis of retinal fluids is a time-consuming, subjective, and error-prone task, there is increasing demand for fast and robust automatic solutions. In this study, a new convolutional neural architecture named RetiFluidNet is proposed for multi-class retinal fluid segmentation. The model benefits from hierarchical representation learning of textural, contextual, and edge features using a new self-adaptive dual-attention (SDA) module, multiple self-adaptive attention-based skip connections (SASC), and a novel multi-scale deep self-supervision learning (DSL) scheme. The attention mechanism in the proposed SDA module enables the model to automatically extract deformation-aware representations at different levels, and the introduced SASC paths further consider spatial-channel interdependencies for concatenation of counterpart encoder and decoder units, which improve representational capability. RetiFluidNet is also optimized using a joint loss function comprising a weighted version of dice overlap and edge-preserved connectivity-based losses, where several hierarchical stages of multi-scale local losses are integrated into the optimization process. The model is validated based on three publicly available datasets: RETOUCH, OPTIMA, and DUKE, with comparisons against several baselines. Experimental results on the datasets prove the effectiveness of the proposed model in retinal OCT fluid segmentation and reveal that the suggested method is more effective than existing state-of-the-art fluid segmentation algorithms in adapting to retinal OCT scans recorded by various image scanning instruments.

Optical Coherence Tomography Biomarkers in Predicting Treatment Outcomes of Diabetic Macular Edema after Ranibizumab Injections

Background and Objectives: The identification of possible biomarkers that can predict treatment response among DME eyes is important for the individualization of treatment plans. We investigated optical coherence tomography (OCT)-based biomarkers that may predict the one-year real-life outcomes among diabetic macular edema (DME) eyes following treatment by intravitreal ranibizumab (IVR) injections. Materials and Methods: A total of 65 eyes from 35 treatment-naïve patients with DME treated with ranibizumab injection were recruited. Best-corrected visual acuity (BCVA), central retinal thickness (CRT), intraocular pressure (IOP), and OCT scans were retrospectively recorded at baseline before treatment and at 3 months, 6 months, and 12 months after treatment. The OCT scans were evaluated for biomarkers of interest, which included central retinal thickness (CRT), amount and locations of hyperreflective foci (HRF), subretinal fluid (SRF), intraretinal cysts (IRC), large outer nuclear layer cyst (LONLC), ellipsoid zone disruption (EZD), disorganization of retinal inner layers (DRIL), hard exudates (HE), epiretinal membrane (ERM), and vitreomacular interface (VMI). Correlations between these OCT biomarkers and outcome measures (visual and structural) were statistically analyzed. Results: A total of 65 eyes from 35 patients with DME were enrolled. The mean age was 64.2 ± 10.9 years old. Significant improvement in terms of mean BCVA (p < 0.005) and mean CRT was seen at final follow-up compared to baseline. The biomarkers of DRIL, LONLC, and SRF were found to be predictive for at least 50 μm CRT reduction after treatment (with odds ratio of 8.69, 8.5, and 17.58, respectively). The biomarkers of IRC, LONLC, and SRF were predictive for significant improvement in terms of BCVA and CRT after treatment. Finally, the number of HRF was predictive for both BCVA improvement and a CRT reduction of less than 100 μm after treatment. No serious complications were reported during the study. Conclusion: Our study demonstrated the utility of OCT biomarkers as therapeutic predictors of ranibizumab treatment among DME eyes.

Serum neurofilament light chain concentration predicts disease worsening in multiple sclerosis

Background: Serum neurofilament light (sNfL) chain is a promising biomarker reflecting neuro-axonal injury in multiple sclerosis (MS). However, the ability of sNfL to predict outcomes in real-world MS cohorts requires further validation. Objective: The aim of the study is to investigate the associations of sNfL concentration, magnetic resonance imaging (MRI) and retinal optical coherence tomography (OCT) markers with disease worsening in a longitudinal European multicentre MS cohort. Methods: MS patients (n = 309) were prospectively enrolled at four centres and re-examined after 2 years (n = 226). NfL concentration was measured by single molecule array assay in serum. The patients’ phenotypes were thoroughly characterized with clinical examination, retinal OCT and MRI brain scans. The primary outcome was disease worsening at median 2-year follow-up. Results: Patients with high sNfL concentrations (⩾8 pg/mL) at baseline had increased risk of disease worsening at median 2-year follow-up (odds ratio (95% confidence interval) = 2.8 (1.5–5.3), p = 0.001). We found no significant associations of MRI or OCT measures at baseline with risk of disease worsening. Conclusion: Serum NfL concentration was the only factor associated with disease worsening, indicating that sNfL is a useful biomarker in MS that might be relevant in a clinical setting.

Modular deep neural networks for automatic quality control of retinal optical coherence tomography scans

Retinal optical coherence tomography (OCT) with intraretinal layer segmentation is increasingly used not only in ophthalmology but also for neurological diseases such as multiple sclerosis (MS). Signal quality influences segmentation results, and high-quality OCT images are needed for accurate segmentation and quantification of subtle intraretinal layer changes. Among others, OCT image quality depends on the ability to focus, patient compliance and operator skills. Current criteria for OCT quality define acceptable image quality, but depend on manual rating by experienced graders and are time consuming and subjective. In this paper, we propose and validate a standardized, grader-independent, real-time feedback system for automatic quality assessment of retinal OCT images. We defined image quality criteria for scan centering, signal quality and image completeness based on published quality criteria and typical artifacts identified by experienced graders when inspecting OCT images. We then trained modular neural networks on OCT data with manual quality grading to analyze image quality features. Quality analysis by a combination of these trained networks generates a comprehensive quality report containing quantitative results. We validated the approach against quality assessment according to the OSCAR-IB criteria by an experienced grader. Here, 100 OCT files with volume, circular and radial scans, centered on optic nerve head and macula, were analyzed and classified. A specificity of 0.96, a sensitivity of 0.97 and an accuracy of 0.97 as well as a Matthews correlation coefficient of 0.93 indicate a high rate of correct classification. Our method shows promising results in comparison to manual OCT grading and may be useful for real-time image quality analysis or analysis of large data sets, supporting standardized application of image quality criteria.

Automated Hole and Non-hole Screening in Retinal OCT Images Using Local Binary Patterns with Support Vector Machine

Macular hole (MH) formation in between the retinal layers causes distorted vision and decrease in the person’s visual acuity. MH is also the chronic stage of retinal disorder, significantly treated only by surgeries. This work addresses to the automated screening of the hole and non-hole images in the cross-sectional depiction of retinal optical coherence tomography (OCT) images. Screening between hole and non-hole comprises various pathological traces observed in the retinal OCT scans, aiming to automatically differentiating the retinal hole present in the macula and other macular pathologies. Machine learning utilizes local binary pattern with reduced dimension, as local descriptors, in which the texture information from the retinal OCT images is encoded. For the identification of the MH, support vector machine classifier is used. Dataset was prepared for 51 unseen OCT scans from 14 patients having orientation variabilities and used for extensive experimentation. Method effectiveness was verified through results, and the statement supported with the evaluations was performed across the dataset. Systems’ overall performance was validated stochastically where the system sensitivity is 92.3% and the specificity is 92%.

Patterns of retrograde axonal degeneration in the visual system.

Conclusive evidence for existence of acquired retrograde axonal degeneration that is truly trans-synaptic (RTD) has not yet been provided for the human visual system. Convincing data rely on experimental data of lesions to the posterior visual pathways. This study aimed to overcome the limitations of previous human studies, namely pathology to the anterior visual pathways and neurodegenerative co-morbidity. In this prospective, longitudinal cohort retinal optical coherence tomography scans were acquired before and after elective partial temporal lobe resection in 25 patients for intractable epilepsy. Newly developed region of interest-specific, retinotopic areas substantially improved on conventional reported early treatment diabetic retinopathy study (ETDRS) grid-based optical coherence tomography data. Significant inner retinal layer atrophy separated patients with normal visual fields from those who developed a visual field defect. Acquired RTD affected the retinal nerve fibre layer, ganglion cell and inner plexiform layer and stopped at the level of the inner nuclear layer. There were significant correlations between the resected brain tissue volume and the ganglion cell layer region of interest (R = -0.78, P < 0.0001) and ganglion cell inner plexiform layer region of interest (R = -0.65, P = 0.0007). In one patient, damage to the anterior visual pathway resulted in occurrence of microcystic macular oedema as recognized from experimental data. In the remaining 24 patients with true RTD, atrophy rates in the first 3 months were strongly correlated with time from surgery for the ganglion cell layer region of interest (R = -0.74, P < 0.0001) and the ganglion cell inner plexiform layer region of interest (R = -0.51, P < 0.0001). The different time course of atrophy rates observed relate to brain tissue volume resection and suggest that three distinct patterns of retrograde axonal degeneration exist: (i) direct retrograde axonal degeneration; (ii) rapid and self-terminating RTD; and (iii) prolonged RTD representing a 'penumbra', which slowly succumbs to molecularly governed spatial cellular stoichiometric relationships. We speculate that the latter could be a promising target for neuroprotection.

Deep Ensemble Learning Based Objective Grading of Macular Edema by Extracting Clinically Significant Findings from Fused Retinal Imaging Modalities.

Macular edema (ME) is a retinal condition in which central vision of a patient is affected. ME leads to accumulation of fluid in the surrounding macular region resulting in a swollen macula. Optical coherence tomography (OCT) and the fundus photography are the two widely used retinal examination techniques that can effectively detect ME. Many researchers have utilized retinal fundus and OCT imaging for detecting ME. However, to the best of our knowledge, no work is found in the literature that fuses the findings from both retinal imaging modalities for the effective and more reliable diagnosis of ME. In this paper, we proposed an automated framework for the classification of ME and healthy eyes using retinal fundus and OCT scans. The proposed framework is based on deep ensemble learning where the input fundus and OCT scans are recognized through the deep convolutional neural network (CNN) and are processed accordingly. The processed scans are further passed to the second layer of the deep CNN model, which extracts the required feature descriptors from both images. The extracted descriptors are then concatenated together and are passed to the supervised hybrid classifier made through the ensemble of the artificial neural networks, support vector machines and naïve Bayes. The proposed framework has been trained on 73,791 retinal scans and is validated on 5100 scans of publicly available Zhang dataset and Rabbani dataset. The proposed framework achieved the accuracy of 94.33% for diagnosing ME and healthy subjects and achieved the mean dice coefficient of 0.9019 ± 0.04 for accurately extracting the retinal fluids, 0.7069 ± 0.11 for accurately extracting hard exudates and 0.8203 ± 0.03 for accurately extracting retinal blood vessels against the clinical markings.

Deep structure tensor graph search framework for automated extraction and characterization of retinal layers and fluid pathology in retinal SD-OCT scans

Maculopathy is a group of retinal disorders that affect macula and cause severe visual impairment if not treated in time. Many computer-aided diagnostic methods have been proposed over the past that automatically detect macular diseases. However, to our best knowledge, no literature is available that provides an end-to-end solution for analyzing healthy and diseased macular pathology. This paper proposes a vendor-independent deep convolutional neural network and structure tensor graph search-based segmentation framework (CNN-STGS) for the extraction and characterization of retinal layers and fluid pathology, along with 3-D retinal profiling. CNN-STGS works by first extracting nine layers from an optical coherence tomography (OCT) scan. Afterward, the extracted layers, combined with a deep CNN model, are used to automatically segment cyst and serous pathology, followed by the autonomous 3-D retinal profiling. CNN-STGS has been validated on publicly available Duke datasets (containing a cumulative of 42,281 scans from 439 subjects) and Armed Forces Institute of Ophthalmology dataset (containing 4260 OCT scans of 51 subjects), which are acquired through different OCT machinery. The performance of the CNN-STGS framework is validated through the marked annotations, and it significantly outperforms the existing solutions in various metrics. The proposed CNN-STGS framework achieved a mean Dice coefficient of 0.906 for segmenting retinal fluids, along with an accuracy of 98.75% for characterizing cyst and serous fluid from diseased retinal OCT scans.

Multilayered Deep Structure Tensor Delaunay Triangulation and Morphing Based Automated Diagnosis and 3D Presentation of Human Macula

Maculopathy is the group of diseases that affects central vision of a person and they are often associated with diabetes. Many researchers reported automated diagnosis of maculopathy from optical coherence tomography (OCT) images. However, to the best of our knowledge there is no literature that presents a complete 3D suite for the extraction as well as diagnosis of macula. Therefore, this paper presents a multilayered convolutional neural networks (CNN) structure tensor Delaunay triangulation and morphing based fully autonomous system that extracts up to nine retinal and choroidal layers along with the macular fluids. Furthermore, the proposed system utilizes the extracted retinal information for the automated diagnosis of maculopathy as well as for the robust reconstruction of 3D macula of retina. The proposed system has been validated on 41,921 retinal OCT scans acquired from different OCT machines and it significantly outperformed existing state of the art solutions by achieving the mean accuracy of 95.27% for extracting retinal and choroidal layers, mean dice coefficient of 0.90 for extracting fluid pathology and the overall accuracy of 96.07% for maculopathy diagnosis. To the best of our knowledge, the proposed framework is first of its kind that provides a fully automated and complete 3D integrated solution for the extraction of candidate macula along with its fully automated diagnosis against different macular syndromes.

Progressive inner nuclear layer dysfunction in non-optic neuritis eyes in MS.

Objective:To investigate primary retinal functional changes in non-optic neuritis (ON) eyes of patients with MS by full-field electroretinography (ERG).Methods:Seventy-seven patients with relapsing-remitting MS with no history of clinical ON in at least 1 eye and 30 healthy controls were recruited in the cohort study. Full-field ERGs were recorded, and retinal optical coherence tomography scans were performed to assess the thicknesses of peripapillary retinal nerve fiber layer (RNFL) and retinal ganglion cell layer–inner plexiform layer (GCL-IPL). Annual MRI scans were also carried out to evaluate the disease activity in the brain. Patients were followed up for 3 years.Results:At baseline, a delayed b-wave peak time was observed in the cone response (p < 0.001), which was associated with the thicknesses of RNFL and GCL-IPL. The peak time of the delayed b-wave also correlated with the Expanded Disability Status Scale, T2 lesion volume, and disease duration. During the 3-year follow-up, progressive ERG amplitude reduction was observed (both a- and b-waves, p < 0.05). There was a correlation between the b-wave amplitude reduction and longitudinal RNFL loss (p = 0.001). However, no correlation was found between longitudinal ERG changes and disease activity in the brain.Conclusions:This study demonstrated progressive inner nuclear layer dysfunction in MS. The borderline a-wave changes suggested some outer retinal dysfunction as well. The correlation between full-field ERG changes and retinal ganglion cell loss suggested that there might be subclinical retinal pathology in MS affecting both outer and inner retinal layers.

Ametropia, retinal anatomy, and OCT abnormality patterns in glaucoma. 1. Impacts of refractive error and interartery angle.

Retinal nerve fiber layer thickness (RNFLT) measured by optical coherence tomography (OCT) is widely used in clinical practice to support glaucoma diagnosis. Clinicians frequently interpret peripapillary RNFLT areas marked as abnormal by OCT machines. However, presently, clinical OCT machines do not take individual retinal anatomy variation into account, and according diagnostic biases have been shown particularly for patients with ametropia. The angle between the two major temporal retinal arteries (interartery angle, IAA) is considered a fundamental retinal ametropia marker. Here, we analyze peripapillary spectral domain OCT RNFLT scans of 691 glaucoma patients and apply multivariate logistic regression to quantitatively compare the diagnostic bias of spherical equivalent (SE) of refractive error and IAA and to identify the precise retinal locations of false-positive/negative abnormality marks. Independent of glaucoma severity (visual field mean deviation), IAA/SE variations biased abnormality marks on OCT RNFLT printouts at 36.7%/22.9% of the peripapillary area, respectively. 17.2% of the biases due to SE are not explained by IAA variation, particularly in inferonasal areas. To conclude, the inclusion of SE and IAA in OCT RNFLT norms would help to increase diagnostic accuracy. Our detailed location maps may help clinicians to reduce diagnostic bias while interpreting retinal OCT scans.

OCT-based deep learning algorithm for the evaluation of treatment indication with anti-vascular endothelial growth factor medications.

Intravitreal injections with anti-vascular endothelial growth factor (anti-VEGF) medications have become the standard of care for their respective indications. Optical coherence tomography (OCT) scans of the central retina provide detailed anatomical data and are widely used by clinicians in the decision-making process of anti-VEGF indication. In recent years, significant progress has been made in artificial intelligence and computer vision research. We trained a deep convolutional artificial neural network to predict treatment indication based on central retinal OCT scans without human intervention. A total of 183,402 retinal OCT B-scans acquired between 2008 and 2016 were exported from the institutional image archive of a university hospital. OCT images were cross-referenced with the electronic institutional intravitreal injection records. OCT images with a following intravitreal injection during the first 21days after image acquisition were assigned into the 'injection' group, while the same amount of random OCT images without intravitreal injections was labeled as 'no injection'. After image preprocessing, OCT images were split in a 9:1 ratio to training and test datasets. We trained a GoogLeNet inception deep convolutional neural network and assessed its performance on the validation dataset. We calculated prediction accuracy, sensitivity, specificity, and receiver operating characteristics. The deep convolutional neural network was successfully trained on the extracted clinical data. The trained neural network classifier reached a prediction accuracy of 95.5% on the images in the validation dataset. For single retinal B-scans in the validation dataset, a sensitivity of 90.1% and a specificity of 96.2% were achieved. The area under the receiver operating characteristic curve was 0.968 on a per B-scan image basis, and 0.988 by averaging over six B-scans per examination on the validation dataset. Deep artificial neural networks show impressive performance on classification of retinal OCT scans. After training on historical clinical data, machine learning methods can offer the clinician support in the decision-making process. Care should be taken not to mistake neural network output as treatment recommendation and to ensure a final thorough evaluation by the treating physician.

Ocular toxicity after intracameral injection of very high doses of cefuroxime during cataract surgery

To report cases of intraocular inflammation after intracameral injection of a very high dose of cefuroxime at the end of uneventful cataract surgery. Department of Ophthalmology, Bordeaux University Hospital, Bordeaux, France. Case series. Patients were followed on an outpatient basis and were examined postoperatively at 1 and 5 days and 6 weeks. Central macular thickness, angiography, central corneal thickness (CCT), endothelial cell density (ECD), and electroretinography (ERG) were analyzed to evaluate ocular toxicity. One day postoperatively, the mean corrected distance visual acuity (CDVA) was 0.95 logMAR ± 0.40 (SD). All the cases had moderate anterior inflammation. Retinal optical coherence tomography scans systematically showed extensive macular edema (mean 843.2 ± 212.7 μm) associated with a large serous retinal detachment. Fluorescein angiograms showed diffuse leakage without abnormal retinal perfusion. At 5 days, the mean CDVA improved significantly to 0.52 ± 0.29 logMAR (P < .005), as did the macular edema and serous retinal detachment (mean 339.4 ± 138.3 μm) (P = .005). At 6 weeks, the mean CDVA reached 0.09 ± 0.06 logMAR. Modifications in CCT and ECD were similar to those observed after uneventful phacoemulsification. The macular thickness (mean 288.4 ± 22.6 μm) and profile returned to normal in all patients, although ERG recordings showed reduced rod photoreceptor cell function (P < .05). Intracameral injection of high doses of cefuroxime induced anterior and posterior inflammation. Without surgical intervention, the final visual outcome was satisfactory in all cases. Long-term retinal function, however, must be assessed through repeated ERG recordings.