Optical Coherence Tomography Angiography Data Research Articles

CMFNet: a cross-dimensional modal fusion network for accurate vessel segmentation based on OCTA data.

Optical coherence tomography angiography (OCTA) is a novel non-invasive retinal vessel imaging technique that can display high-resolution 3D vessel structures. The quantitative analysis of retinal vessel morphology plays an important role in the automatic screening and diagnosis of fundus diseases. The existing segmentation methods struggle to effectively use the 3D volume data and 2D projection maps of OCTA images simultaneously, which leads to problems such as discontinuous microvessel segmentation results and deviation of morphological estimation. To enhance diagnostic support for fundus diseases, we propose a cross-dimensional modal fusion network (CMFNet) using both 3D volume data and 2D projection maps for accurate OCTA vessel segmentation. Firstly, we use different encoders to generate 2D projection features and 3D volume data features from projection maps and volume data, respectively. Secondly, we design an attentional cross-feature projection learning module to purify 3D volume data features and learn its projection features along the depth direction. Then, we develop a cross-dimensional hierarchical fusion module to effectively fuse coded features learned from the volume data and projection maps. In addition, we extract high-level semantic weight information and map it to the cross-dimensional hierarchical fusion process to enhance fusion performance. To validate the efficacy of our proposed method, we conducted experimental evaluations using the publicly available dataset: OCTA-500. The experimental results show that our method achieves state-of-the-art performance.

A Fast-scanning Protocol of Optical Coherence Tomography Angiography Based on Structure-Aware Attention.

Oral diseases have imposed a heavy social and financial burden on many countries and regions. If left untreated, severe cases can lead to malignant tumours. Common devices can no longer meet the high-resolution and non-invasive requirement, while Optical Coherence Tomography Angiography (OCTA) provides an ideal perspective for detecting vascular microcirculation. However, acquiring high-quality OCTA images takes time and can result in unpredictable motion artefacts. Therefore, we propose a systematic workflow for rapid OCTA data acquisition. Initially, we implement a fourfold reduction in sampling points to enhance the scanning speed. Then, we apply a deep neural network for rapid image reconstruction, elevating the resolution to the level achieved through full scanning. Specifically, it is a hybrid attention model with a structure-aware loss to extract local and global information on angiography, which improves the visualisation performance and quantitative metrics of numerous classical and recent-presented models by 3.536%-9.943% in SSIM and 0.930%-2.946% in MS-SSIM. Through this approach, the time of constructing one OCTA volume can be reduced from nearly 30 s to about 3 s. The rapid-scanning protocol of high-quality imaging also presents feasibility for future real-time detection applications.

OCTA evaluates changes in retinal microvasculature in renal hypertension patients

The objective of this study is to utilize optical coherence tomography angiography (OCTA) techniques for the purpose of identifying abnormalities in retinal and conjunctival vascular density among patients afflicted with renal hypertension. From October 2022 to October 2023, a cohort of sixteen patients diagnosed with renal hypertension (RH), comprising a total of 32 eyes, was selected from the Department of Nephrology at the First Affiliated Hospital of Nanchang University. Concurrently, a group of sixteen healthy individuals, carefully matched in characteristics, was recruited from volunteers at the Ophthalmology Research Center and designated as the healthy controls (HCs) group. Optical coherence tomography angiography was employed to assess and examine the superficial vascular plexus (SVP) and deep vascular plexus (DVP) of the macular retina in both eyes. Subsequently, a comparative analysis was conducted between the two groups, focusing on the superficial and deep retinal microvessels (MIR), macrovascular (MAR), and total microvascular (TMI). The present study employed the central annuli segmentation method (C1–C6), the hemispheric segmentation method (SL, IL, SR, IR), and the Early Treatment Diabetic Retinopathy Study (S, I, L, R) to evaluate deviations in retinal blood vessel density. The investigation aimed to examine the association between blood vessel density and TMI in conjunctival capillaries. A statistically significant difference (p < 0.05) in macular retinal vascular density was observed between the two groups based on the OCTA data. Specifically, in SVP, the density of TMI, MIR, and MAR in the RH group was significantly lower compared to the HCs group (p < 0.05). Additionally, the deep density of TMI and MIR in DVP of the RH group was significantly lower than that of the HCs group (p < 0.05). Furthermore, using the hemispheric segmentation method, both the superficial and deep retina showed a significant reduction in the density of SL, SR and IL regions (p < 0.05). In the ETDRS method, there was a significant decrease in superficial and deep retinal S, I, and L in the RH group (p < 0.05). When applying the central annuli segmentation methods, the RH group exhibited a significant decrease in the superficial retinal C1–3 region (p < 0.05) and a noticeable reduction in the deep retina in the C1–4 region (p < 0.05). Furthermore, a higher positive likelihood ratio was observed in the deep SL and superficial C2 region. There was a positive correlation between conjunctival capillary density and the region of TMI in depth. The results of the OCTA investigation revealed a significant disparity in the density of superficial and deep retinal blood vessels between RH group and the HCs group. Additionally, a notable correlation was observed between the depth of TMI and the density of conjunctival capillaries. These findings highlight the potential of retinal OCTA as a valuable tool for early detection and image-assisted diagnosis of retinopathy progression in patients with RH.

Diagnostic model of microvasculature and neurologic alterations in the retina and optic disc for lupus nephritis

BackgroundMachine learning (ML) analysis of retinal nerve fiber layer (RNFL) thickness and vessel density (VD) alterations in the macular region and optic disc may provide a new diagnostic method for lupus nephritis (LN). This study aimed to assess these alterations in LN patients using optical coherence tomography angiography (OCTA). MethodsA retrospective analysis was conducted on 81 systemic lupus erythematosus (SLE) patients without retinopathy, divided into two groups: LN (41 patients) and non-LN (39 patients). OCTA imaging was performed on all participants. Independent risk factors were identified through univariate and multivariate analyses, followed by the development of a random forest (RF) diagnostic model. ResultsA total of 37 RNFL and VD variables from the macular region and 23 from the optic disc were analyzed. Through elastic net regression, 16 significant factors were identified. Further multivariate logistic regression selected 8 critical factors, which were used to construct the RF model. The RF model achieved an area under the curve (AUC) of 0.950 (95 % CI: 0.882 to 1.000), accuracy of 0.903 (95 % CI: 0.743 to 0.980), sensitivity of 0.867, specificity of 0.938, a positive predictive value (PPV) of 0.929, and a negative predictive value (NPV) of 0.882. ConclusionThis study highlights the potential of ML-based OCTA data in diagnosing LN. Key diagnostic factors included perimeter (PERIM), superficial capillary plexus vessel density (SVD) - parafoveal (para)-temporal (T), SVD-perifoveal (peri)-inferior (I), RNFL-Fovea, RNFL-Peri, RNFL-Peri-T, capillary-whole-image, and peripapillary RNFL (PRNFL)- inferonasal (IN).

Are optic nerve head and choroidal circulation affected by eye movements?

Although it has been reported that the optic nerve can be mechanically affected by the eye's horizontal movements, studies examining horizontal movements with optical coherence tomography angiography (OCTA) have only recently begun to emerge. This study aimed to investigate whether there are changes in the OCTA data of healthy individuals in the primary gaze, abduction, and adduction. Thirty volunteers (15-73 years old) were included in this prospectively designed study. Radial peripapillary capillary density parameters (RPCD) taken with OCTA in cases of primary gaze, abduction, and adduction were examined. With the OCTA device Angio Disc QuickVue that was used in the study, 3 main vessel structures could be examined. In the patients' primary, abduction, and adduction positions, a difference was observed only in the superior hemifield area of the left eye (P = 0.032). The superior hemifield all vessels vessel densities (AV VD) were 60.1 ± 2.7 in the central gaze, 59.9 ± 2.6 in the adduction, and 60.8 ± 2.6 in the abduction positions, with a relative decrease observed in adduction. This was also related to age. No difference was detected in terms of the other RPCD parameters. In healthy individuals, short-term horizontal eye movements may not result in significant changes except for superior hemifield in OCTA data.

Combined evaluation of visual field and optical coherence tomography angiography data in multiple sclerosis patients

Aims: To evaluate Humphrey visual field analyzer (HVFA) data and optical coherence tomography angiography (OCT-A) parameters in multiple sclerosis (MS) patients with optic neuritis (ON) attacks. Methods: 34 eyes of 34 patients with MS diagnosis who had ON attacks were included in the study. After detailed ophthalmoscopic examination, OCT-A and HVFA images were taken. Spearman correlation analysis was used in statistical analysis. Results: The mean age of the participants was 31.52±10.09 years. In the correlation analysis, a moderate correlation was found between mean deviation (MD) and foveal deep blood flow (DF) (rho=0.52), and a weak correlation was found between MD and foveal superficial blood flow (SF) (rho=0.40) and optic disc head blood flow (ODF) (rho=0.38). A weak negative correlation was found between pattern standard deviation (PSD) and DF (rho=-0.37) and ODF (rho=-0.40). Conclusion: This study showed that OCTA data were affected in a manner consistent with HVFA data. More practical and quickly applicable OCTA scans may facilitate the estimation of visual field findings in MS patients.

Microvascular alterations of the ocular surface and retina in connective tissue disease-related interstitial lung disease.

To examine the disparities in macular retinal vascular density between individuals with connective tissue disease-related interstitial lung disease (CTD-ILD) and healthy controls (HCs) by optical coherence tomography angiography (OCTA) and to investigate the changes in microvascular density in abnormal eyes. For a retrospective case-control study, a total of 16 patients (32 eyes) diagnosed with CTD-ILD were selected as the ILD group. The 16 healthy volunteers with 32 eyes, matched in terms of age and sex with the patients, were recruited as control group. The macular retina's superficial retinal layer (SRL) and deep retinal layer (DRL) were examined and scanned using OCTA in each individual eye. The densities of retinal microvascular (MIR), macrovascular (MAR), and total microvascular (TMI) were calculated and compared. Changes in retinal vascular density in the macular region were analyzed using three different segmentation methods: central annuli segmentation method (C1-C6), hemispheric segmentation method [uperior right (SR), superior left (SL), inferior left (IL), and inferior right (IR)], and Early Treatment Diabetic Retinopathy Study (ETDRS) methods [superior (S), inferior (I), left (L), and right (R)]. The data were analyzed using Version 9.0 of GraphPad prism and Pearson analysis. The OCTA data demonstrated a statistically significant difference (P<0.05) in macular retinal microvessel density between the two groups. Specifically, in the SRL and DRL analyses, the ILD group exhibited significantly lower surface density of MIR and TMI compared to the HCs group (P<0.05). Furthermore, using the hemispheric segmentation method, the ILD group showed notable reductions in SL, SR, and IL in the superficial retina (P<0.05), as well as marked decreases in SL and IR in the deep retina (P<0.05). Similarly, when employing the ETDRS method, the ILD group displayed substantial drops in superficial retinal S and I (P<0.05), along with notable reductions in deep retinal L, I, and R (P<0.05). In the central annuli segmentation method, the ILD group exhibited a significant decrease in the superficial retinal C2-4 region (P<0.05), whereas the deep retina showed a notable reduction in the C3-5 region (P<0.05). Additionally, there was an observed higher positive likelihood ratio in the superficial SR region and deep MIR. Furthermore, there was a negative correlation between conjunctival vascular density and both deep and superficial retinal TMI (P<0.001). Patients with CTD-ILD exhibits a significantly higher conjunctival vascular density compared to the HCs group. Conversely, their fundus retinal microvascular density is significantly lower. Furthermore, CTD-ILD patients display notably lower superficial and deep retinal vascular density in comparison to the HCs group. The inverse correlation between conjunctival vascular density and both superficial and deep retinal TMI suggests that detecting subtle changes in ocular microcirculation could potentially serve as an early diagnostic indicator for connective tissue diseases, thereby enhancing disease management.

AI-based 3D analysis of retinal vasculature associated with retinal diseases using OCT angiography.

Retinal vasculature is the only vascular system in the human body that can be observed in a non-invasive manner, with a phenotype associated with a wide range of ocular, cerebral, and cardiovascular diseases. OCT and OCT angiography (OCTA) provide powerful imaging methods to visualize the three-dimensional morphological and functional information of the retina. In this study, based on OCT and OCTA multimodal inputs, a multitask convolutional neural network model was built to realize 3D segmentation of retinal blood vessels and disease classification for different retinal diseases, overcoming the limitations of existing methods that can only perform 2D analysis of OCTA. Two hundred thirty sets of OCT and OCTA data from 109 patients, including 138,000 cross-sectional images in normal and diseased eyes (age-related macular degeneration, retinal vein occlusion, and central serous chorioretinopathy), were collected from four commercial OCT systems for model training, validation, and testing. Experimental results verified that the proposed method was able to achieve a DICE coefficient of 0.956 for 3D segmentation of blood vessels and an accuracy of 91.49% for disease classification, and further enabled us to evaluate the 3D reconstruction of retinal vessels, explore the interlayer connections of superficial and deep vasculatures, and reveal the 3D quantitative vessel characteristics in different retinal diseases.

Diameter-dependent classification of dermal vasculature using optical coherence tomography angiography.

Dermal blood vessels beneath the epidermis play critical roles in epidermal homeostasis and are functionally divided into several types, such as capillaries. Optical coherence tomography angiography (OCTA) is a powerful tool for the non-invasive assessment of dermal vasculature. However, the classification of vessel types has been limited. To address this issue, we proposed an algorithm for diameter-dependent classification that preserves three-dimensional (3D) information using OCTA. OCTA data were acquired by a prototype swept-source-type optical coherence tomography (OCT) system, which was processed through several imaging filters: an optical microangiography (OMAG) imaging filter, a vesselness imaging filter, and a diameter map filter. All vessels were visually classified into three types based on their diameters, as micro-vessels, intermediate vessels, and thick vessels. Aging-related alterations and their association with the epidermis were investigated for each vessel type. The measurements were conducted on the cheeks of 124 female subjects aged 20-79 years. The 3D vascular structure was visualized by applying our proposed post-processing filters. Based on visual assessment, the thresholds for the diameters of the micro, intermediate and thick vessels were set at 80 and 160 µm. It was found that micro-vessels were predominantly located in the upper layer of the dermis and thick vessels in the deeper layer. Analysis of vessel metrics revealed that the volume density of the micro-vessels decreased significantly with age (r=-0.36, P<0.001) and was positively correlated with epidermal thickness (r=0.50, P<0.001). In contrast, the volume density of thick vessels significantly increased with age (r=0.2, P<0.05) and was not significantly correlated with epidermal thickness (r=0.13, P≥0.05). In this study, we proposed a 3D quantification method using OCTA for dermal blood vessels and various vessel metrics, such as vessel volume density. This proposed classification will be beneficial for determining the function of the dermal vasculature and its diagnostic applications.

Retinal Vessel Plexus Differentiation Based on OCT Angiography Using Deep Learning

PurposeWhile structural optical coherence tomography (OCT) is traditionally used to differentiate the vascular plexus layers in OCT angiography (OCTA), the vascular plexuses do not always obey the retinal laminations. We sought to segment the superficial, deep and avascular plexuses from OCTA images using deep learning without structural OCT image input or segmentation boundaries. DesignCross-sectional study. SubjectsThe study included 235 OCTA cubes from 33 patients for training and testing of the model. MethodsFrom each OCTA cube, 3 weakly labeled images representing the superficial, deep and avascular plexuses were obtained for a total of 705 starting images. Images were augmented with standard intensity and geometric transforms, and regions from adjacent plexuses were programmatically combined to create synthetic 2-class images for each OCTA cube. Images were partitioned on a per patient basis into training, validation, and reserved test groups to train and evaluate a U-Net based machine learning model. To investigate the generalization of the model we applied the model to multi-class thin slabs from OCTA volumes and qualitatively observed the resulting b-scans. Main Outcome MeasuresPlexus segmentation performance was assessed quantitatively using Dice scores on a held-out test set. ResultsAfter training on single class plexus images, our model achieved good results (Dice scores > .82) and was further improved when using the synthetic 2-class images (Dice > .95). While not trained on more complex multi-class slabs, the model performed plexus labeling on slab data that indicates the use of only OCTA data shows promise for segmenting the superficial, deep and avascular plexuses without requiring OCT layer segmentations, and the use of synthetic 2-class images makes a significant performance improvement. ConclusionsThis study presents the use of OCTA data alone to segment the superficial, deep and avascular plexuses of the retina, confirming that use of structural OCT layer segmentations as boundaries is not required.

Quantitative Volumetric Analysis of Retinal Ischemia with an Oxygen Diffusion Model and OCT Angiography

PurposeRetinal ischemia is a major feature of diabetic retinopathy (DR). Traditional nonperfused areas measured by optical coherence tomography angiography (OCTA) measure blood supply but not ischemia. We propose a novel 3-dimensional (3D) quantitative method to derive ischemia measurements from OCTA data. DesignCross-sectional study. ParticipantsWe acquired 223 macular OCTA volumes from 33 healthy eyes, 33 diabetic eyes without retinopathy, 7 eyes with non-referable DR, 17 eyes with referable but non-vision-threatening DR, and 133 eyes with vision-threatening DR. MethodsEach eye was scanned using a spectral-domain OCTA system (Avanti RTVue-XR, Visionix/Optovue, Inc) with 1.6 mm scan depth in a 3 × 3-mm region (640 × 304 × 304 voxels) centered on the fovea. For each scanned OCTA volume, a custom algorithm removed flow projection artifacts. We then enhanced, binarized, and skeletonized the vasculature in each OCTA volume and generated a 3D oxygen tension map using a zero-order kinetics oxygen diffusion model. Each volume was scaled to the average retina thickness in healthy controls after foveal registration and flattening of the Bruch membrane. Finally, we extracted 3D ischemia maps by comparison with a reference map established from scans of healthy eyes using the same processing. To assess the ability of the ischemia maps to grade DR severity, we constructed receiver-operating characteristic (ROC) curves for diagnosing diabetes, referable DR, and vision-threatening DR. Main outcome measuresSpearman correlation coefficient and area under ROC curve (AUC) were used to quantify the ability of the ischemia maps to DR. ResultsThe ischemia maps showed that the ischemic tissues were at or near pathologically non-perfused areas, but not the normally non-vascular tissue, such as the foveal avascular zone. We found multiple novel metrics, including inferred 3D-oxygen tension, ischemia index, and ischemic volume ratio, were strongly correlated with DR severity. The AUCs of ischemia index measured were 0.95 for diabetes, 0.89 for DR, 0.88 for referable DR, and 0.85 for vision threatening DR. ConclusionsA quantitative method to infer 3D oxygen tension and ischemia using OCTA in diabetic eyes can identify ischemic tissue that are more specific to pathologic changes in DR.

Identification of diabetic retinopathy classification using machine learning algorithms on clinical data and optical coherence tomography angiography.

To apply machine learning (ML) algorithms to perform multiclass diabetic retinopathy (DR) classification using both clinical data and optical coherence tomography angiography (OCTA). In this cross-sectional observational study, clinical data and OCTA parameters from 203 diabetic patients (203 eye) were used to establish the ML models, and those from 169 diabetic patients (169 eye) were used for independent external validation. The random forest, gradient boosting machine (GBM), deep learning and logistic regression algorithms were used to identify the presence of DR, referable DR (RDR) and vision-threatening DR (VTDR). Four different variable patterns based on clinical data and OCTA variables were examined. The algorithms' performance were evaluated using receiver operating characteristic curves and the area under the curve (AUC) was used to assess predictive accuracy. The random forest algorithm on OCTA+clinical data-based variables and OCTA+non-laboratory factor-based variables provided the higher AUC values for DR, RDR and VTDR. The GBM algorithm produced similar results, albeit with slightly lower AUC values. Leading predictors of DR status included vessel density, retinal thickness and GCC thickness, as well as the body mass index, waist-to-hip ratio and glucose-lowering treatment. ML-based multiclass DR classification using OCTA and clinical data can provide reliable assistance for screening, referral, and management DR populations.

Microvascular Density Analysis of Patients with Inactive Systemic Lupus Erythematosus-A Two-Year Follow-Up Optical Coherence Tomography Angiography Study.

Background/Objectives: This study aims to investigate the long-term effect of inactive systemic lupus erythematosus (SLE) on the retinal microcirculation measured via optical coherence tomography angiography (OCT-A). Methods: Twenty-four eyes of 24 patients with inactive SLE under hydroxychloroquine (HCQ) therapy were included. The OCT-A data (mainly vessel density (VD) and foveal avascular zone (FAZ) data of the superficial and of the deep capillary plexus (SCP, DCP) and the choriocapillaris (CC)) were analyzed and compared between the baseline examination (t0) and 2 years later (t1). Results: At t1, VD in the whole en face SCP and in the CC was notably reduced compared to t0 (SCP: p = 0.001, CC: p = 0.013). VD in the DCP, CRT and FAZ area showed no difference at t1 compared to t0 (DCP: p = 0.128, FAZ: p = 0.332, CRT fovea: p = 0.296). Correlation analysis between the increase in cumulative doses of HCQ between t0 and t1 and the VD of the whole en face SCP did not show any correlation (Spearman r = 0.062 (95% CI -0.367; 0.477). Conclusions: SLE patients demonstrated a decrease in the retinal VD of the SCP and CC over a 2-year period. There was no correlation with the change in cumulative doses of HCQ. These results suggest an ongoing effect of the disease on the retinal and choriocapillary microcirculation.

Imaging of human corneoscleral junction (Limbus) vasculature with 100 KHz A-scan rate swept-source optical coherence tomography/angiography (OCT/A) system

The study demonstrates in-vivo three-dimensional depth-resolved Optical Coherence Tomography Angiography (OCTA) and Doppler OCT imaging performed on the anterior segment of the human eye. A high-speed swept-source OCT system was developed utilizing a swept-source laser having a 100 kHz A-scan sweep rate and centre wavelength at 1060 nm. The proposed system has an axial resolution of 4.5 µm and a transverse imaging resolution of 14 µm. The Doppler OCT provides information regarding the direction of blood flow in corneoscleral junction vessels, which employs the Joint Spectral and Time domain OCT (STdOCT) method. Parameters influencing the imaging of various vessels, like scanning density, A-scan rate, B-scan averaging, and number of BM scanning repeats, were also studied. Slit lamp images and OCT angiography en-face projections produced from PVOCTA (Phase-variance OCTA) and STdOCTA from the same regular patients were compared in order to demonstrate the additional potential of the system. The vascular systems at the Limbus consisting of circulatory, lymphatic, and aqueous outflow systems were imaged and presented. The output clinical parameters of the system will contribute to understanding the blood circulation with directionality at the limbus location, which can be further utilized to identify glaucoma. In the author's opinion, this article represents the first attempt to provide Doppler OCTA data for the anterior chamber of the human eye.

Role of optical coherence tomography angiography in the evaluation of peripheral ischemia in retinal vein occlusion.

In the last decade, optical coherence tomography angiography (OCTA) has become part of the clinical management of retinal vein occlusion (RVO), proving in itself a useful technique for both the prediction of visual acuity (VA) outcomes and the risk of complications. In fact, OCTA has been proven a valid imaging technique in detailed assessment of foveal and parafoveal microvascular status in both acute and chronic RVO. Quantitative OCTA data have shown a significant correlation not only with final VA but also with the extension of peripheral ischemia, which represents a major risk factor for macular edema recurrence and neovascularization onset. Finally, wide-field OCTA represents a promising noninvasive technique for the assessment of peripheral ischemia. The aim of this review is to report the main literature findings about microvascular changes and clinical applications of OCTA in the context of RVO-induced peripheral ischemia.

Co-assessment of OCT-A and choroidal vascularity index data in multiple sclerosis patients

ObjectiveTo evaluate optical coherence tomography-angiography (OCT-A) findings and choroidal vascular index (CVI) in patients with multiple sclerosis (MS). Methods113 patients, including multiple sclerosis patients with optic neuritis attack (MSON+) and no optic neuritis attack (MSON−) and healthy control group (HCG), participated in this cross-sectional study. OCT-A images of all patients were taken and CVI was calculated. ResultsSuperior flow (SF), deep flow (DF), foveal, and parafoveal superior vascular density (sVD) were decreased in the MSON+ group compared to HCG (p < 0.05). Optic disk flow (ODF) and optic disk head density (ONHD) values decreased in the MS group (p < 0.05). CVI was decreased in the MSON+ group compared to HCG (p < 0.05). There is a correlation between CVI and foveal and parafoveal sVD. ConclusionNon-invasive diagnostic tools such as OCT-A and CVI can be used for early diagnosis and follow-up of microvascular pathologies in inflammatory diseases such as MS.

Robust AMD Stage Grading with Exclusively OCTA Modality Leveraging 3D Volume.

Age-related Macular Degeneration (AMD) is a degenerative eye disease that causes central vision loss. Optical Coherence Tomography Angiography (OCTA) is an emerging imaging modality that aids in the diagnosis of AMD by displaying the pathogenic vessels in the subretinal space. In this paper, we investigate the effectiveness of OCTA from the view of deep classifiers. To the best of our knowledge, this is the first study that solely uses OCTA for AMD stage grading. By developing a 2D classifier based on OCTA projections, we identify that segmentation errors in retinal layers significantly affect the accuracy of classification. To address this issue, we propose analyzing 3D OCTA volumes directly using a 2D convolutional neural network trained with additional projection supervision. Our experimental results show that we achieve over 80% accuracy on a four-stage grading task on both error-free and error-prone test sets, which is significantly higher than 60%, the accuracy of human experts. This demonstrates that OCTA provides sufficient information for AMD stage grading and the proposed 3D volume analyzer is more robust when dealing with OCTA data with segmentation errors.

Evaluation of retina and choroid perfusion with optical coherence tomography angiography in patients with retinitis pigmentosa

PurposeIn this study, we aimed to evaluate macular perfusion with optical coherence tomography angiography (OCTA) and to investigate the correlation between OCTA quantitative data and visual acuity (VA) in patients with retinitis pigmentosa (RP). MethodsThis retrospective single-center study was conducted on 60 eyes of 30 RP patients and 52 healthy eyes. The vessel density (VD) of the superficial capillary plexus (SCP) and deep capillary plexus (DCP) of the macula, the size of foveal avascular zone (FAZ), choriocapillary flow density (FD) were measured using OCTA. Quantitative data obtained with OCTA were compared between the two groups. In addition, the correlation between the OCTA measurements and VA was examined. ResultsIn patients with RP, the choriocapillary FD was decreased (p = 0.001), the FAZ area was enlarged (p = 0.010), and the VDs of the SCP and DCP were decreased in all areas (p = 0.001). Correlation was found between VA and SCP VD, whole image (p = 0.011, rho = -0.327) and parafoveal (p = 0.001, rho = -0.444) areas. ConclusionQuantitative data from OCTA showed reduced macular perfusion in patients with RP compared to healthy controls. There was also a correlation between the quantitative OCTA data and VA.

Factors affecting optical coherence tomography angiography signal strength index in patients receiving intravitreal injection treatment.

To investigate the clinical factors affecting optical coherence tomography angiography (OCTA) signal strength index (SSI) and its change after intravitreal injection treatment in patients with retinal disorders. OCTA data from 186 eyes of 166 patients with various retinal disorders including age-related macular degeneration, diabetic macular edema (DME), and retinal vein occlusions who received intravitreal injections were analyzed. The associations between SSI and clinical factors, including age, best-corrected visual acuity (BCVA), media opacity severity, and central macular thickness (CMT), were evaluated both before and after injection. After injection, BCVA improved and CMT decreased significantly, and SSI increased significantly (p = 0.030). BCVA showed a significant positive correlation with media opacity severity before and after injection and with CMT only before injection. In the multivariate analysis, age, presence of DME, BCVA, and media opacity severity were negatively associated with SSI both before and after injection, while CMT was negatively associated with SSI only before injection. After injection, a negative correlation was found between SSI change and both BCVA and CMT change. Our findings suggest that OCTA SSI is influenced by various clinical factors, including age, visual acuity, media opacity severity, and macular thickening, especially in cases of DME. The results also indicate that SSI may decrease in patients with macular disorders due to the presence of macular edema and the associated decrease in visual acuity. Therefore, it is crucial to consider these factors when interpreting OCTA data and ensure an adequate level of SSI.

Long-term real-world outcomes of retinal microvasculature changes in proliferative diabetic retinopathy treated with panretinal photocoagulation vs. intravitreal conbercept

PurposeTo compare long-term real-world outcomes of retinal microvasculature changes in proliferative diabetic retinopathy (PDR) treated with panretinal photocoagulation (PRP) vs. intravitreal conbercept (IVC) and to explore the potential factors affecting these changes. MethodsThis study retrospectively included 96 treatment-naïve PDR eyes of 96 type 2 diabetes mellitus patients [59 PRP and 37 IVC]. Baseline characteristics and treatment details were collected. Optical coherence tomography angiography (OCTA) data of macular vessel density (VD) and optic disc capillary density (CD) at baseline and at the last follow-up were compared between groups. The differences between the baseline and the last follow-up OCTA data in each group were also tested for significance. The correlation between the change in each OCTA parameter from baseline and each baseline characteristic/treatment parameter was investigated in each group. ResultsDuring a mean follow-up of two years, greater superficial (SCP) (p = 0.004) and deep capillary plexus (DCP) VD (p < 0.001) were observed in the foveal area in the PRP than in the IVC. Compared to the baseline, SCP VD in the foveal area increased in the PRP (p = 0.012), while an increased SCP VD in some sectors in the parafoveal and perifoveal areas (p < 0.05), rather than the foveal area (p = 0.908), was seen in the IVC. For both groups, eyes with a higher VD/CD at baseline tended to develop capillary dropout more intensively (all p < 0.05). In the IVC group, foveal avascular zone (FAZ) area change showed a negative correlation with baseline FAZ area (p = 0.020), and complementary PRP exerted a negative influence on FAZ area change (p = 0.002). In the PRP group, SCP VD change was positively correlated with follow-up frequency, and was negatively correlated with diastolic blood pressure (all p < 0.05); DCP VD change showed a positive correlation with PRP shot number (p = 0.019). ConclusionThe aforementioned microvasculature changes should be considered when PRP or IVC is adopted in PDR long-term management.