Detection Of Choroidal Neovascularization Research Articles

The role of multimodal imaging in characterization and monitoring of choroidal neovascularization secondary to angioid streaks.

To characterize and monitor choroidal neovascularisation (CNV) secondary to angioid streaks (AS) using multimodal imaging and to compare the results with conventional fluorescein angiography (FA). A total of 11 eyes with CNV secondary to AS were included in this retrospective study. Multimodal morphological and functional assessment, including spectral-domain optical coherence tomography (SD-OCT), spectral-domain optical coherence tomography angiography (SD-OCTA), and fundus autofluorescence (FAF), were used to assess for evidence of CNV activity and compared with conventional FA. Morphological features of CNV were analyzed and treatment was continuously monitored using SD-OCT and SD-OCTA. Our results showed that SD-OCTA provided reliable results for the detection of secondary CNV in AS that were comparable to conventional FA. With SD-OCTA, a total of 13 CNVs were detected in 11 eyes and analyzed by means of outer retinal choriocapillaris depth (ORCC) segmentation and the corresponding B-scans. Twelve of the 13 CNVs were classified as active and therefore required treatment. For treatment monitoring during intravitreal therapy (IVT), SD-OCTA was found to be a valuable diagnostic tool over a mean follow-up of 76 weeks. Our study demonstrates that SD-OCTA can be routinely used to identify ill-defined CNV without dye-based angiography, especially in cases of CNV secondary to AS, where Bruch's membrane (BM) defects limit the diagnostic value of FA. Our results showed that non-invasive multimodal imaging facilitates sufficient CNV monitoring and treatment guidance. Further studies are warranted to provide more evidence in this rare retinal disease.

CHOROIDAL NEOVASCULARIZATION IN A CHILD WITH DOWN SYNDROME

Purpose: To report a case of Down syndrome with myopic choroidal neovascularization (CNV) and the treatment outcome. Methods: Case report. Main outcome measures include refractive error, fundus examination, optical coherence tomography (OCT), OCT angiography (OCTA), fluorescein angiography (FA), anti-vascular endothelial growth factor (VEGF) injections. Results: A 12-year-old boy with Down syndrome presented at a regular check-up with decreased visual acuity (VA) with macular degeneration in the left eye. The best-corrected VA was 0.6 in the right eye and 0.1 in the left eye, which decreased from 0.3 1 year ago. The refractive error (spherical equivalent) was -5.25 diopters (D) in the right eye and -8.00 D in the left eye. Detailed examinations were performed under general anesthesia. The fundus examination showed macular degeneration with retinal pigment epithelium (RPE) atrophy, pigmentary changes, and fibrous tissue in the left eye. OCT showed CNV at the macula with edema, and OCTA showed spreading CNV above the RPE at the macula in the left eye. FA showed hyperfluorescence in the early phase and late dye leakage from the CNV. Intravitreal ranibizumab injections were administered twice within 2 months, and he maintained a VA of 0.1 in the left eye. Conclusion: CNV and associated macular degeneration may occur in Down syndrome with high myopia possibly because of the abnormal choroidal structure. In children with Down syndrome, regular fundus examinations with OCT are important for early detection and treatment of CNV.

Three-Year Follow-Up Detecting Choroidal Neovascularization with Swept Source Optical Coherence Tomography Angiography (SS-OCTA) after Successful Half-Fluence Photodynamic Therapy for Chronic Central Serous Chorioretinopathy.

Purpose: To assess the clinical course, structural changes, and choroidal neovascularization detection by SS-OCTA in long-standing and resolved patients with chronic central serous chorioretinopathy (cCSC) after successful half-fluence photodynamic therapy (hf-PDT) treatment. Methods: Twenty-four eyes presenting with cCSC were examined with SS-OCTA and were classified as choroidal neovascular (CNV) or non-choroidal neovascular (non-CNV) cCSC depending on the vascular pattern detected by SS-OCTA after one, two, and three years after hf-PDT. Two groups were compared based on the following clinical findings: demographic characteristics, time of clinical signs, best corrected visual acuity (BCVA), central retinal thickness (CRT), central choroidal thickness (CFT), subretinal fluid (SRF), flat, irregular pigment epithelial detachment (FIPED), and features of fluorescein angiography (FA) and vascular pattern by SS-OCTA. Results: All patients showed resolved cCSC during follow-up after hf-PDT. A total of 5 of 24 (20.8%) eyes showed a neovascular pattern by SS-OCTA. No differences between BCVA, CRT, SRF, FIPED, or FA features were found between both groups (p > 0.05). However, CFT and older age were associated with a neovascular pattern by SS-OCTA (p < 0.05) in follow-up. No signs of neovascular activity were detected by SS-OCT during follow-up in CNV cCSC patients, and no antiVEGF treatment was required for three-year follow-ups. Conclusions: Despite patients with cCSC showing a favorable clinical response after hf-PDT, lower foveal thickness and older age were associated with CNV patterns by SS-OCTA during follow-up.

Deep Learning Classification of Drusen, Choroidal Neovascularization, and Diabetic Macular Edema in Optical Coherence Tomography (OCT) Images.

Background Age-related macular degeneration (AMD), diabetic retinopathy (DR), drusen, choroidal neovascularization (CNV), and diabetic macular edema (DME) are significant causes of visual impairment globally. Optical coherence tomography (OCT) imaging has emerged as a valuable diagnostic tool for these ocular conditions. However, subjective interpretation and inter-observer variability highlight the need for standardized diagnostic approaches. Methods This study aimed to develop a robust deep learning model using artificial intelligence (AI) techniques for the automated detection of drusen, CNV, and DME in OCT images. A diverse dataset of 1,528 OCT images from Kaggle.com was used for model training. The performance metrics, including precision, recall, sensitivity, specificity, F1 score, and overall accuracy, were assessed to evaluate the model's effectiveness. Results The developed model achieved high precision (0.99), recall (0.962), sensitivity (0.985), specificity (0.987), F1 score (0.971), and overall accuracy (0.987) in classifying diseased and healthy OCT images. These results demonstrate the efficacy and efficiency of the model in distinguishing between retinal pathologies. Conclusion The study concludes that the developed deep learning model using AI techniques is highly effective in the automated detection of drusen, CNV, and DME in OCT images. Further validation studies and research efforts are necessary to evaluate the generalizability and integration of the model into clinical practice. Collaboration between clinicians, policymakers, and researchers is essential for advancing diagnostic tools and management strategies for AMD and DR. Integrating this technology into clinical workflows can positively impact patient care, particularly in settings with limited access to ophthalmologists. Future research should focus on collecting independent datasets, addressing potential biases, and assessing real-world effectiveness. Overall, the use of machine learning algorithms in conjunction with OCT imaging holds great potential for improving the detection and management of drusen, CNV, and DME, leading to enhanced patient outcomes and vision preservation.

Detection of Choroidal Neovascularization Using Optical Tissue Transparency.

Optical tissue transparency (OTT) provides a tool for visualizing the entire tissue block. This study provides insights into the potential value of OTT with light-sheet fluorescence microscopy (LSFM) in detecting choroidal neovascularization (CNV) lesions. OTT with LSFM, hematoxylin and eosin (H&E) staining of paraffin sections, choroidal flatmount immunofluorescence, and optical coherence tomography angiography (OCTA) were used to obtain images of CNV. We determined the rate of change as (Data of week 1 - Data of week 2)/Data of week 1 × 100%. Finally, we compared the rate of change acquired from OTT with LSFM and the other methodologies. We found that OTT with LSFM can realize three-dimensional (3D) visualizations of the entire CNV. The results showed that the decline in the rate of change from week 1 to week 2 after laser photocoagulation was 33.05% with OTT, 53.01% with H&E staining, 48.11% with choroidal flatmount, 24.06% with OCTA (B-scan), 18.08% with OCTA (en face), 10.98% with OCTA (3D reconstruction), and 7.74% with OCTA (vessel diameter index). OTT with LSFM will continue to be an invaluable resource for investigators to detect more visualized and quantified information regarding CNV. OTT with LSFM now serves as a tool for detecting CNV in mice, and it may undergo human clinical trials in the future.

CNV-Net: Segmentation, Classification and Activity Score Measurement of Choroidal Neovascularization (CNV) Using Optical Coherence Tomography Angiography (OCTA)

This paper aims to present an artificial intelligence-based algorithm for the automated segmentation of Choroidal Neovascularization (CNV) areas and to identify the presence or absence of CNV activity criteria (branching, peripheral arcade, dark halo, shape, loop and anastomoses) in OCTA images. Methods: This retrospective and cross-sectional study includes 130 OCTA images from 101 patients with treatment-naïve CNV. At baseline, OCTA volumes of 6 × 6 mm2 were obtained to develop an AI-based algorithm to evaluate the CNV activity based on five activity criteria, including tiny branching vessels, anastomoses and loops, peripheral arcades, and perilesional hypointense halos. The proposed algorithm comprises two steps. The first block includes the pre-processing and segmentation of CNVs in OCTA images using a modified U-Net network. The second block consists of five binary classification networks, each implemented with various models from scratch, and using transfer learning from pre-trained networks. Results: The proposed segmentation network yielded an averaged Dice coefficient of 0.86. The individual classifiers corresponding to the five activity criteria (branch, peripheral arcade, dark halo, shape, loop, and anastomoses) showed accuracies of 0.84, 0.81, 0.86, 0.85, and 0.82, respectively. The AI-based algorithm potentially allows the reliable detection and segmentation of CNV from OCTA alone, without the need for imaging with contrast agents. The evaluation of the activity criteria in CNV lesions obtains acceptable results, and this algorithm could enable the objective, repeatable assessment of CNV features.

Individual vs. combined imaging modalities for diagnosing neovascular central serous chorioretinopathy.

To assess the diagnostic accuracy of individual and combined imaging modalities compared with multimodal imaging for the detection of choroidal neovascularization (CNV) in central serous chorioretinopathy (CSC). We analyzed patients with CSC with and without CNV who had indocyanine green angiography (ICGA), structural optical coherence tomography (OCT), and OCT angiography (OCTA) obtained on the same day. The presence of CNV was determined using multimodal imaging by a senior retina specialist (i.e., diagnostic reference). Individual and combined (i.e., ICGA + structural OCT) imaging modalities were then graded by two expert readers for the presence of CNV. Sensitivity, specificity, positive (PPV), and negative (NPV) predictive values were computed for individual and combined imaging modalities relative to the diagnostic reference. CNV was detected in 17 eyes in 17 out of 33 CSC patients according to the reference standard. Using ICGA, the identification of CNV had a sensitivity of 66.7%, specificity of 66.7%, PPV of 70.6%, and NPV of 62.5%. Structural OCT had the following diagnostic accuracy values: 83.3% of sensitivity, 53.3% of specificity, 68.1% of PPV, and 72.7% of NPV. Using OCTA, CNV was graded to be present with a sensitivity of 77.8%, specificity of 86.7%, PPV of 87.5%, and NPV of 76.5%. The combination of ICGA and structural OCT granted the identification of CNV with a sensitivity of 83.3%, specificity of 86.7%, PPV of 88.2%, and NPV of 81.3%. OCTA has an elevated diagnostic accuracy in identifying CSC-associated CNV, though a combination of ICGA and structural OCT has a comparable diagnostic efficiency.

Central serous chorioretinopathy: Treatment.

Central serous chorioretinopathy (CSC) is a pachychoroid spectrum disease characterized by serous detachment of the neurosensory retina with subretinal fluid in young and middle-aged adults. The pathogenesis of CSC is not yet fully understood. However, it is considered a multifactorial disease that is strongly associated with choroidal dysfunction or vascular engorgement. Although there is no consensus on the treatment of CSC, photodynamic therapy has been effectively used to manage serous retinal detachment (SRD) in CSC. Moreover, micropulse diode laser photocoagulation and focal laser treatment have also been used. Recently, oral medications, including mineralocorticoid receptor antagonists, have been proposed for the management of CSC. Multimodal imaging plays a significant role in the diagnosis and treatment of CSC. Optical coherence tomography angiography (OCTA) has the advantage of detecting vascular flow in the retina and choroid layer, allowing for a better understanding of the pathology, severity, prognosis, and chronicity of CSC. In addition, early detection of choroidal neovascularization in CSC is possible using OCTA. This review article aims to provide a comprehensive and updated understanding of CSC, focusing on treatment.

Nonhomogenous Hyperreflectivity in the Choriocapillaris Layer on Optical Coherence Tomography Angiography Implies Early Treatment with Anti-VEGF for Central Serous Chorioretinopathy

Introduction: Optical coherence tomography angiography (OCTA) facilitates the detection of choroidal neovascularization (CNV). This study explored the role of nonhomogenous hyperreflectivity implying putative CNV in the choriocapillaris layer on OCTA in central serous chorioretinopathy (CSCR). Methods: Thirteen eyes out of 12 patients with CSCR were examined with OCTA. The nonhomogenous hyperreflectivity was compared with the histological morphology of experimental CNV. The effect of intravitreal anti-vascular endothelial growth factor (VEGF) was evaluated by analyzing the changes in central macular thickness (CMT) and the height of subretinal fluid (SRF). Results: Comparison of the nonhomogenous hyperreflectivity on OCTA with the established CNV in two animal models strongly indicated these signals are putative CNV. During following-up, these nonhomogenous hyperreflectivity in CSCR developed into visible CNV on OCTA. Moreover, anti-VEGF treatment was effective to reduce both the SRF and CMT in CSCR with nonhomogenous hyperreflectivity or secondary CNV within 2 months. Conclusion: This study suggested that the nonhomogenous hyperreflectivity on OCTA could be served as a diagnostic biomarker for putative CNV in CSCR, implying early treatment with anti-VEGF.

Detection of Choroidal Neovascularization (CNV) in Retina OCT Images Using VGG16 and DenseNet CNN

In this study, we intend to diagnose Choroidal Neovascularization in retinal Optical Coherence Tomography (OCT) images using Deep Learning Architectures. OCT images can be used to differentiate between a healthy eye and an eye with CNV disease. In CNV the Retinal Pigment Epithelial layer experiences changes in various properties which can be related to the assistance of OCT Images. This paper proposes a technique for finding CNV in OCTA pictures. Among the few attributes of CNV, the bigger turning point of veins is a moderately clear element, so we will utilize this property to see if there is CNV in an OCTA picture. DenseNet and Vgg16 Architectures of Deep Learning were used in the study and the hyper parameters of both of the architectures were changed to diagnose the disease properly. After the detection of the disease, the diseased OCT images are segmented from the background for the Region of Interest detection using Python OpenCV library that is used for the processing of images. The results of implementation of the Architectures showed that Vgg16 showed better results in detecting the images rather than Dense Net Architecture with an accuracy percentage of 97.53% approximately a percent greater than Dense Net.

Clinical course after the onset of choroidal neovascularization in eyes with central serous chorioretinopathy.

Chronic central serous chorioretinopathy (CSC) can be complicated with choroidal neovascularization (CNV); however, the timing of its occurrence and its clinical significance are not well understood. This study aimed to observe the time of choroidal neovascularization detection after CSC diagnosis and determine whether clinical features and prognosis differed in patients with chronic CSC or age-related retinal degeneration.In this retrospective study, medical records of CSC patients complicated with CNV who visited Seoul St. Mary's hospital of Korea between October 2009 and December 2020 were reviewed. The presence of CNV was determined using fluorescein, indocyanine green, or optical coherent tomography angiography (OCTA). Based on the patients’ medical records, we observed the change of clinical pattern, best-corrected visual acuity (BCVA) and central macular thickness (CMT) at CNV detection and at 6 months, 1 year, 3 years, and 5 years following CNV detection.Thirty eyes of 30 patients (male: female ratio of 13:17) were enrolled. Mean age at diagnosis of CSC was 54.0 ± 8.5 years (mean ± standard deviation). On average, CNV was detected 1.65 ± 2.30 years after the diagnosis of CSC. The mean CMT was significantly decreased at 6 months, 1 year, and 3 years after choroidal neovascularization detection (P < .001, P < .001, P = .001 respectively). BCVA tend to improve after CNV detection, but there was no statistical significance at 6 months, 1 year, 3 years, and 5 years (all with P > .05). There were no clinical findings suggesting age-related macular degeneration such as intraretinal, subretinal hemorrhage or drusen in any of the case during follow-up. None of the subjects had severe visual acuity loss of 1.0 logarithm of the minimum angle of resolution (logMAR) (20/200 Snellen equivalent) or greater. Among the subjects, 6 patients (20%) did not require any treatment during observation, while 24 other patients required anti-vascular endothelial growth factor (anti-VEGF) or photodynamic therapy. At the last visit, 22 patients (73.3%) remained stable for more than 6 months, without subretinal fluid recurrence.Choroidal neovascularization was detected earlier than previously reported. There was no rapid deterioration of visual acuity or clinical features even after CNV detection.

OCT-Angiography for Detection of Choroidal Neovascularization: A Retrospective Real-Life Study

Purpose: The purpose of the study was to assess OCT-angiography (OCT-A) contribution for choroidal neovascularization (CNV) detection, with respect to multimodal imaging (MMI) modality (including OCT, fluorescein angiography (FFA), and indocyanine green angiography [ICG]), in a real-life consultation practice. Methods: Data of all consecutive patients undergoing OCT-A examination for CNV suspicion were collected between September 2017 and September 2019 at Strasbourg University Hospital, France. Only eyes which had anti-VEGF injection in the last 3 months were excluded. All types of neovascularization were included. For all patients, data from OCT, OCT-A, FFA, and ICG were interpreted by residents and retinal specialists, independently. Final diagnosis of CNV was based on decision to treat. Sensibility, specificity, and predictive values were computed for OCT-A alone and for MMI (OCT combined to angiography). They were computed for each group. OCT-A was also assessed as “contributory” (i.e., assessing without doubt the presence or absence of CNV) or not, with respect to MMI. Results: In total, 161 eyes of 145 patients were included. MMI sensibility was better than OCT-A sensibility (93.8 vs. 65.6%). OCT-A specificity was better than MMI specificity (96.9 vs. 89.5%). OCT-A was essential for diagnosis in 16.9% of cases. Sensibility and specificity values for all exams were better when interpreted by retinal specialists than residents. OCT-A was judged “contributory” in 57.4% of eyes. OCT-A was significantly less contributory when artefacts were present (32.9% of eyes with artefacts vs. 63.5% without, p < 0.001). Conclusion: OCT-A showed to be essential in diagnosing CNV in >16% of cases. However, it often failed to conclude for the absence of CNV, which obliged to perform more exams such as angiography. OCT-A must be part of diagnostic procedure for CNV detection but does not discard angiography in everyday life practice.

In vivo evaluation of laser-induced choroidal neovascularization in rats simultaneously using optical coherence tomography and photoacoustic microscopy

Determination of the precise location and the degree of the Choroidal neovascularization (CNV) lesion is essential for diagnosation Neovascular age-related macular degeneration (AMD) and evaluation the efficacy of treatment. Noninvasive imaging techniques with specific contrast for CNV evaluation are demanded. In this paper, two noninvasive imaging techniques, namely Optical coherence tomography (OCT) and Photoacoustic microscopy (PAM), are combined to provide specific detection of CNV for their complimentary contrast mechanisms. In vivo time-serial evaluation of Laser-induced CNV in rats is present at days 1, 3, 5, 7, 14, 21 after laser photocoagulation is applied to the rat fundus. Both OCT and PAM show that the CNV increases to its maximum at day 7 and decreases at day 14. Quantification of CNV area and CNV thickness is given. The dual-modal information of CNV is consistent with the histologic evaluation by hematoxylin and eosin (H&amp;E) staining.

Current status of home monitoring technology for age-related macular degeneration.

Evidence suggests that patients present with exudative age-related macular degeneration (AMD) in a delayed fashion. Increased lesion size associated with this delay directly impacts visual acuity. Upon treatment initiation, patients are monitored largely with optical coherence tomography (OCT) technology to determine the need for treatment. Home-monitoring systems using preferential hyperacuity perimetry (PHP) and OCT may optimize management. Comparison of Age-related Macular Degeneration Treatment Trials study and American Academy of Ophthalmology's Intelligent Research in Sight registry data suggest smaller lesion size and better visual acuity upon choroidal neovascularization (CNV) capture are associated with better final visual acuity with therapy. The HOME study and recent PHP-based ForeseeHome data indicate that this modality leads to earlier detection of CNV. Results of a real-world data analysis demonstrate 82% retention of ≥20/40 vision with median visual acuity of 20/40 at time of CNV detection using PHP home-monitoring. Home OCT data suggests excellent patient useability, with >90% of patients obtaining analyzable images. The Notal OCT Analyzer demonstrates superiority over human interpreters regarding the ability to detect intraretinal and subretinal fluid (82% vs. 47% sensitivity). PHP may improve treatment outcomes for exudative AMD by allowing for earlier detection of lesions. Home OCT platforms could allow for more convenient monitoring of patients undergoing treatment for exudative AMD and better enable true PRN models.

Detection and clinical course of choroidal neovascularization in central serous chorioretinopathy

PurposeThe objective of this study was to observe the detection of choroidal neovascularization (CNV) after central serous chorioretinopathy (CSC) diagnosis and to determine whether clinical features and prognosis differ in CNV eyes from chronic CSC after CNV detection.MethodsThe medical records of 30 eyes of 30 patients with CSC were retrospectively analyzed in this study. The presence of CNV was diagnosed using fluorescein angiography (FA), indocyanine green angiography (ICGA), or optical coherent tomography angiography (OCTA). The time of initial symptom diagnosis and the period from the diagnosis of CSC to the detection of CNV were estimated based on the medical records. We observed the clinical change pattern by measuring the best‐corrected visual acuity (BCVA), central macular thickness (CMT), and subfoveal choroidal thickness (SFCT) for one year since the detection of CNV.ResultsThe average period until CNV detection was 24.18 ± 29.43 months (mean ± standard deviation) from the initial symptom initiation and 20.10 ± 28.49 months from the first diagnosis of CSC. The CMT significantly decreased in patients with CSC in the one‐year follow‐up after CNV detection (p = 0.01), but no statistically significant changes were found in BCVA and SFCT.ConclusionsIn CSC patients, CNV detection was observed earlier than previously reported, and after CNV detection, there was no rapid deterioration of visual acuity or clinical features.

The role of optical coherence tomography angiography in diagnosis of central serous chorioretinopathy

Purpose To detect the findings of optical coherence tomography angiography (OCTA) in eyes with central serous chorioretinopathy (CSCR), in comparison with conventional multimodal imaging. Patients and methods In the current case series, 80 eyes of 80 patients were diagnosed to have CSCR, and they underwent spectral domain optical coherence tomography (SD-OCT), fluorescein angiography (FA), and OCTA. OCTA images are performed at two main depth intervals: automatically segmented outer retina and automatically segmented choriocapillaris. Results In 40 of 80 eyes, OCTA images showed detached retina adjacent to the leakage point, compared with 40 of 80 eyes using FA, and 80 of 80 eyes using SD-OCT. In 44 of 80 eyes, irregular flow patterns were observed on OCTA images through the choriocapillaris. OCTA images could not identify leakage points in any of the included eyes, compared with 68 of 80 eyes on FA, and 56 of 80 eyes on SD-OCT. In 12 of 80 eyes, abnormal vessels (associated choroidal neovascularization) were observed on OCTA images, compared with eight of 80 eyes in SD-OCT and four of 80 eyes in FA. Conclusion OCTA images of the superficial and deep retinal plexus, outer retina, and choriocapillaris did not reveal altered flow patterns directly associated with the leakage point in acute CSCR. However, OCTA was able to visualize altered choroidal flow in some of the included eyes and was the best between all other modalities in detection of choroidal neovascularization in eyes with chronic CSCR.

Diagnostic Value of Optical Coherence Tomography Angiography for Choroidal Neovascularization in Age-Related Macular Degeneration: A Systematic Review and Meta-Analysis

Objective: This study aims to evaluate the diagnostic value of optical coherence tomography angiography (OCTA) in detecting the choroidal neovascularization (CNV) in age-related macular degeneration (AMD). Methods: A systematic review and meta-analysis was performed by searching Pubmed, Science Direct, Embase, and Web of Science. The pooled sensitivity and specificity with 95% confidence intervals (CIs), area under the summary receiver operator characteristic curve (sROC), and the total accurate classification rate were used to evaluate OCTA’s diagnostic value of CNV in AMD patients. Results: Seven studies involving 517 eyes were included in the analysis. The mean age of subjects in each study ranged from 58.5 years to 81.7 years. Fluorescein angiography was applied as the gold standard in 5 studies. There were 350 eyes diagnosed with CNV, OCTA detected 301 eyes correctly, while among the 167 eyes without CNV, OCTA identified 150 correctly. The total accurate classification rate was 87.23%. The Spearman’s rank correlation coefficient was 0.5, indicating that there was no significant threshold effect in the current study (S = 8, p = 0.103). The pooled sensitivity and pooled specificity were 0.89 (95% CI: 0.82, 0.94) and 0.96 (95% CI: 0.85, 1.00), respectively. The area under sROC was up to 0.911. Conclusion: The specificity of OCTA for the detection of CNV in AMD patients is extremely high; however, the sensitivity still needs to be improved. In general, the meta-analysis revealed that OCTA had a high diagnostic value for the detection of CNV in AMD patients.

Optical coherence tomography angiography for identifying choroidal neovascular membranes: a masked study in clinical practice.

Optical coherence tomography angiography (OCT-A) allows non-invasive imaging of chorio-retinal vasculature, and is a potential alternative to fluorescein angiography (FA). Sensitivity and specificity of OCT-A for detecting choroidal neovascularisation (CNV) in treatment-naïve neovascular age-related macular degeneration (nAMD) patients is examined, using the Heidelberg Spectralis in a 'real world' setting. Overall, 43 eyes from 26 patients were included in the study. Spectral domain OCT (SD-OCT), OCT-A and FA images were obtained at baseline. Each of the three retinal image modalities was systematically assessed by three masked clinicians. Decisions about the presence/absence of CNV were recorded using an automated segmentation for OCT-A, a manual method, and using both OCT-A and SD-OCT in conjunction. Additional information about the presence of sub-retinal hyper-reflective material (SHRM) and the 'double layer sign' (DLS) were recorded. The average sensitivity and specificity of the OCT-A for the detection of CNV in treatment naïve AMD was 89% and 87% for the combined SD-OCT and OCT-A, 76% and 91% for the automated segmentation and 84% and 85% for the manual segmentation, respectively. Inter-clinician agreement was 0.59-65 kappa. In patients without CNV, SHRM was present in only 6% while DLS was present in 28%. Sensitivity and specificity was >78% for both SHRM and DLS. OCT-A provides a reliable tool for detecting CNV in treatment naïve nAMD patients, with high sensitivity and specificity. Combined use of SD-OCT images and SHRM as an additional bio-marker, OCT-A could become an alternative to FA in routine clinical practice.

Classification of retinal fundus image using MS-DRLBP features and CNN-RBF classifier

The most common retinal diseases that are to be diagnosed are Diabetic Retinopathy (DR), Age-related Macular Degeneration (AMD) and Choroidal Neovascularization (CNV). For the people above 60 years of age, detection of these retinal diseases is an important task for treatment that reduces the risk of vision loss. Retinal fundus images play a significant role in the detection of DR, AMD and CNV disease diagnosis and treatment. The existing techniques for the detection of DR, AMD and CNV have not fulfilled with the classification accuracy of the retinal diseases effectively. This research work proposes an efficient classification framework for retinal fundus image recognition to overcome these drawbacks. Initially, the input image from the publicly available STARE database is preprocessed with the following three steps (a) Specular reflection removal and smoothing, (b) contrast enhancement and (c) retinal region expansion. With the preprocessed image, the features are extracted using Multi-Scale Discriminative Robust Local Binary Pattern (MS-DRLBP), based on RGB component selection, Gradient operation, and LBP descriptor. Finally, classification was done using hybrid Convolution Neural Network (CNN) and Radial Basis Function (RBF) model (CNN-RBF) which classifies the retinal fundus images into four classes such as DR, AMD, CNV and Normal (NR). Experimental results of the proposed method gives an accuracy of 97.22% compared with the existing other methodologies.

Multimodal Imaging in the Management of Choroidal Neovascularization Secondary to Central Serous Chorioretinopathy.

The diagnosis and treatment of choroidal neovascularization (CNV) in eyes with chronic central serous chorioretinopathy (CSCR) can be challenging. The purpose of this study was to classify eyes with suspected CNV using multimodal imaging. The effect of intravitreal anti-vascular endothelial growth factor (VEGF) was assessed and compared to controls. This retrospective study included chronic CSCR patients with suspected secondary CNV who received intravitreal bevacizumab. Eyes were divided into “definite CNV” and “no CNV” based on optical coherence tomography angiography (OCTA). Eyes that did not undergo OCTA imaging were considered as “presumed CNV”. One-year outcome in visual acuity (VA) and central foveal thickness (CFT) were investigated and compared to non-treated control patients to assess the response to anti-VEGF. Logistic regression analysis was used to explore predictive biomarkers of CNV detection and improvement after anti-VEGF. Ninety-two eyes with chronic CSCR from 88 participants were included in this study. Sixty-one eyes received bevacizumab and 31 eyes were non-treated control subjects. The presence of subretinal hyperreflective material (SHRM) and shallow irregular retinal pigment epithelium (RPE) elevation (SIRE) with sub-RPE hyperreflectivity on OCT was associated with a significantly increased risk of detecting CNV on OCTA. Intravitreal anti-VEGF caused significant functional and anatomical improvement in patients with neovascular CSCR as compared to non-treated eyes. In contrast, VA and CFT changes were not significantly different between treated and non-treated CSCR with no evidence of CNV on OCTA. No clinical or anatomical biomarkers were found to be associated with response to treatment. In conclusion, OCTA should be used to confirm the presence CNV in suspected chronic CSCR patients. Intravitreal anti-VEGF treatment resulted in a significantly better one-year outcome in patients with definitive OCTA evidence of CNV.