Optical Coherence Tomography Images Research Articles

CircWaveDL: Modeling of optical coherence tomography images based on a new supervised tensor-based dictionary learning for classification of macular abnormalities.

Modeling Optical Coherence Tomography (OCT) images is crucial for numerous image processing applications and aids ophthalmologists in the early detection of macular abnormalities. Sparse representation-based models, particularly dictionary learning (DL), play a pivotal role in image modeling. Traditional DL methods often transform higher-order tensors into vectors and then aggregate them into a matrix, which overlooks the inherent multi-dimensional structure of the data. To address this limitation, tensor-based DL approaches have been introduced. In this study, we present a novel tensor-based DL algorithm, CircWaveDL, for OCT classification, where both the training data and the dictionary are modeled as higher-order tensors. We named our approach CircWaveDL to reflect the use of CircWave atoms for dictionary initialization, rather than random initialization. CircWave has previously shown effectiveness in OCT classification, making it a fitting basis function for our DL method. The algorithm employs CANDECOMP/PARAFAC (CP) decomposition to factorize each tensor into lower dimensions. We then learn a sub-dictionary for each class using its respective training tensor. For testing, a test tensor is reconstructed with each sub-dictionary, and each test B-scan is assigned to the class that yields the minimal residual error. To evaluate the model's generalizability, we tested it across three distinct databases. Additionally, we introduce a new heatmap generation technique based on averaging the most significant atoms of the learned sub-dictionaries. This approach highlights that selecting an appropriate sub-dictionary for reconstructing test B-scans improves reconstructions, emphasizing the distinctive features of different classes. CircWaveDL demonstrated strong generalizability across external validation datasets, outperforming previous classification methods. It achieved accuracies of 92.5%, 86.1%, and 89.3% on datasets 1, 2, and 3, respectively, showcasing its efficacy in OCT image classification.

Near-infrared imaging retinal diagnostic applications-a review.

Near-infrared reflectance (NIR) is a commonly performed noncontact and rapid imaging technique. This paper reviews the clinical applications of NIR for diagnosing and monitoring retinal diseases. A comprehensive search was conducted across the Pubmed database. A total of 105 articles were finally included in this article. Images were acquired from the authors own clinical experience. The article describes the imaging utility of NIR for diagnosing and deomonstrating findings in various conditions. These include retinal vascular diseases, age-related macular degeneration (AMD), vitreoretinal interface pathologies, retinal dystrophies, inflammatory chorioretinopathies, phakomatoses, retinal toxicities, photic injury, choroidal cavitary lesions, choroidal neoplasms, and choroidal Vascular Lesions. NIR is widely acquired during OCT imaging, and is advantageous at imaging with low illumination levels and through narrow pupils or opaque media. NIR offers valuable information for the diagnosis and follow-up of retinal disease, and is highly recommended to utilize for clinical decision-making in ophthalmology.

Enhancing Ophthalmological Diagnoses: An Adaptive Ensemble Learning Approach Using Fundus and OCT Imaging

This study presents an innovative Ensemble Disease Learning Algorithm (EDL) for the detection and classification of retinal diseases using fundus images. We enhance our method by incorporating deep learning techniques and multi-modal imaging data, including optical coherence tomography (OCT) images alongside fundus photographs, to provide a more comprehensive understanding of retinal pathology. The advanced EDL integrates Convolutional Neural Networks (CNNs) and attention mechanisms with Capsule Networks (CapsNet) and Support Vector Machine (SVM) classifiers for more nuanced feature extraction and classification. We introduce a novel ensemble adaptive weighting approach that dynamically adjusts classifier weights based on performance across disease types and severity levels, significantly improving the algorithm's handling of complex and rare cases. To enhance model interpretability, we implement an explainable AI component that provides visual heatmaps of the most significant regions for each diagnosis to clinicians. We evaluate the enhanced EDL on a large, diverse dataset encompassing multiple retinal diseases, including diabetic retinopathy, age-related macular degeneration, and glaucoma, across various ethnicities and age groups. Our results demonstrate superior accuracy, sensitivity, and specificity compared to our previous model and other state-of-the-art approaches. A prospective clinical validation study assesses the algorithm's real-world performance. This research advances automated retinal disease diagnosis by making it more robust, accurate, and clinically relevant, potentially improving patient outcomes and global eye care through early disease detection and treatment planning.

Testosterone promotes photoreceptor degeneration in the sodium iodate model.

Previously, we found that retinas of young male mice were more damaged than those of young female mice in the sodium iodate (NaIO3) model. The purpose of this study was to test whether reducing testosterone levels would be retina-protective. Male C57Bl/6J mice underwent surgical castration or sham surgery, then were given an intraperitoneal injection of NaIO3 at 25 mg/kg. The mice were imaged a week later using optical coherence tomography (OCT). ImageJ with a custom macro was utilized to measure retinal thicknesses in OCT images. Electroretinography (ERG) was used to measure retinal function one week post-injection. After euthanasia, quantitative real-time PCR (qRT-PCR) was performed. Surgical castration partially protected photoreceptors, which was indicated by less photoreceptor layer thinning exhibited in OCT images compared to the sham surgery group. Consistent with this, qRT-PCR of castration group neural retinas revealed less reduction of rhodopsin mRNAs, and less upregulation of antioxidant as well as glucose transporter 1 mRNAs. ERG results also demonstrated partial preservation of both cone and rod function. These results indicate that surgical castration provided structural and functional protection to photoreceptors against NaIO3. These neuroprotective effects suggest that testosterone may be harmful to the stressed retina. Further investigation of this pathway could lead to a better understanding of the mechanisms involved in retinal degeneration.

Randomised, multicentre, placebo-controlled trial of fenofibrate for treatment of diabetic macular oedema with economic evaluation (FORTE study): study protocol for a randomised control trial

IntroductionDiabetic macular oedema (DMO), a serious ocular complication of diabetic retinopathy (DR), is a leading cause of vision impairment worldwide. If left untreated or inadequately treated, DMO can lead to...

Automated feature selection for early keratoconus screening optimization

In this paper, an automated feature selection (FS) method is presented to optimize machine learning (ML) models' performances, enhancing early keratoconus screening. A total of 448 parameters were analyzed from a dataset comprising 3162 observations sourced from the swept source optical coherence tomography imaging system developed by the Chinese Academy of Sciences Institute of Automation (SS-1000 CASIA OCT) and electronic health records (EHR). To identify the most relevant features, the analysis of variance (ANOVA) method was used in this study. The performance of three classifiers namely K-Nearest Neighbors (KNN), Support Vector Machine (SVM), and Artificial Neural Networks (ANN) was evaluated, yielding classification accuracies of 96.79% and 96.68% for KNN, 98.95% and 97.08% for SVM, and 95.64% and 95.62% for ANN when distinguishing between 2 and 4 keratoconus classes, respectively. The results show that selecting 50 features can significantly improve the performance of the model while reducing the computation time. The automated feature selection method can also assist ophthalmologists in better understanding the links between various ocular characteristics and keratoconus, potentially leading to advances in early diagnosis, risk prediction, and clinical management of this condition.

Long-term Follow-up Optical Coherence Tomography Assessment of Primary Percutaneous Coronary Intervention for Unprotected Left Main

Background: Elective unprotected left main (ULM) percutaneous coronary intervention (PCI) has long-term mortality rates comparable to surgical revascularization, thanks to advances in drug-eluting stent (DES) design, improved PCI techniques, and frequent use of intravascular imaging. However, urgent PCI of ULM culprit lesions remains associated with high in-hospital mortality and unfavourable long-term outcomes, including DES restenosis and stent thrombosis (ST). This analysis aimed to examine the long-term outcomes and healing of DES implanted in ULM during primary PCI using high-resolution optical coherence tomography (OCT) imaging. Methods: A total of 15 consecutive patients undergoing long-term OCT follow-up of ULM primary PCI from a high-volume center were included in this analysis. During the index primary PCI all subjects underwent angio-guided DES implantation, and follow-up was uneventful in all but one subject who had a non-target PCI lesion. The primary endpoint was the percentage of covered, uncovered, and malappossed stent struts at long-term follow-up. Secondary endpoints included quantitative and qualitative OCT measurements. For the left main bifurcation, a separate analysis was performed for three different segments: left main (LM), polygon of confluence (POC) and distal main branch (dMB), in all cases. Results: The average follow-up interval until OCT was 1580 ± 1260 days. Despite aorto-ostial stent protrusions in 40% of patients, optimal image quality was achieved in 93.3% of cases. There were higher rates of malapposed (11.4 ± 16.6 vs. 13.1 ± 8.3 vs. 0.3 ± 0.5%; p < 0.001) and lower rates of covered struts (81.7 ± 16.8 vs. 83.7 ± 9.2 vs. 92.4 ± 6.8%; p = 0.041) observed for the LM and POC segment compared to the dMB. Significantly malapposed stent struts (>400 μm) were less likely to be covered at follow-up, than struts with a measured strut to vessel wall distance of <400 μm (15.4 ± 21.6 vs. 24.8 ± 23.9%; p = 0.011). Neoatherosclerosis was observed in 5 (33.3%) and restenotic neointimal hyperplasia (NIH) in 2 (13.3%) patients, requiring PCI in 33.3% of patients. Conclusions: Long-term OCT examination of DES implanted during primary PCI for culprit ULM lesions demonstrated high rates of incomplete strut coverage, late malapposition, and high subclinical DES failure rates. These negative OCT results highlight the need for image optimization strategies during primary PCI to improve DES-related long-term outcomes.

Neovascularization restructuring patterns in diabetic patients with coronary in stent restenosis: an in-vivo optical coherence tomography study.

Patients with diabetes mellitus (DM) have an increased risk of in stent restenosis (ISR). Neovascularization (NV) is considered as a unique pathophysiology factor of ISR in diabetic patients. However, the restructuring patterns of in vivo human coronary NV and their relationship with ISR, especially in diabetic patients remain unclear. In this study, we aimed to investigate the NV structure differentiations between patients with and without DM after coronary stent implantation using optical coherence tomography (OCT).We included 136 patients with ISR (70 patients in DM group and 66 patients in non-DM group) who underwent OCT during coronary angiography follow-up. NVs were manually segmented, after which three-dimensional (3D) rendering of OCT images was conducted. NVs greater than 1 mm in length were classified as longitudinal running or coral tree types based on their 3D structures. NV structures were compared between DM and non-DM patients.The prevalence of the coral tree pattern NV in the DM group was 2.14-fold higher than in the non-DM group(p = 0.012). 47.14% of patients in the DM group and 51.51% of patients in the non-DM group presented longitudinal running NV (p = 0.610). The number of coral tree pattern NV was relatively higher in DM patients than in the non-DM patients (p = 0.019). However, the number of longitudinal running NV showed no difference between the two groups (p = 0.872). The normalized NV volume was significantly larger in the DM group (p = 0.008). Patients with coral tree pattern NV have thinner minimum fibrous cap thickness (p = 0.030). DM was the risk factor for coral tree pattern NV formation in ISR lesions after adjustment for other factors.NV with specific restructuring patterns, such as longitudinal running and coral tree patterns, can be identified in ISR lesions. NV with a coral tree pattern, characterized by higher leakiness and immaturity, is more commonly found in patients with DM and is associated with tissue instability in ISR. Accurate and feasible imaging modalities for NV might offer promising opportunities to evaluate NV and prevent progression of ISR in diabetic patients.

Concomitant Traumatic Macular Hole and Orbital Fracture.

To report 5 cases of concomitant traumatic macular hole (TMH) and orbital fracture, and discuss its incidence. This was a retrospective, observational study including all patients with orbital fracture who were referred to us from May 2013 to December 2023. Axial and coronal orbital computed tomographic images with bone and soft tissue window algorithms and optical coherence tomographic images were obtained from all patients. Among 1171 sides from 1152 patients with pure orbital blowout fractures, we found 5 sides from 5 patients (0.4%) with concomitant TMH. All trauma was caused by baseball/softball injury. One patient had a medial orbital wall fracture with TMH stage 1b. Two had orbital floor fracture with TMH stages 2 and 3. The other two had both orbital floor and medial orbital wall fractures with TMH stages 3 and 4. Orbital fracture was reduced in 3 patients. Two had spontaneous closure of TMH with no improvement in visual acuity, while one improved with pars plans vitrectomy and internal limiting membrane peeling. The incidence of concomitant TMH and orbital fracture is only 0.4%. The rarity of this association supports the protective role of orbital fractures in blunt trauma. Specific mechanisms of trauma, such as impacts from baseballs and softballs, may increase risk of such injuries.

Photoreceptor-RPE loss ratio and fundus autofluorescence patterns as predictive factors for lesion progression in geographic atrophy.

To assess the impact of the ratio between photoreceptor (PR) loss and retinal pigment epithelium (RPE) loss on the progression of geographic atrophy (GA) and to explore correlations between abnormal fundus autofluorescence (FAF) patterns and the PR-RPE loss ratio. Single-centre, retrospective case series. Multimodal images from 87 treatment-naïve patients with GA and a follow-up of 6-24 months were included. Geographic atrophy areas on FAF images and areas of PR-RPE loss on optical coherence tomography images at baseline were manually annotated, and FAF patterns were classified. The impact of these biomarkers on GA progression through month 24 as measured on FAF was evaluated using random slope and intercept models and Spearman correlation coefficients (ρ). Mean square-root GA growth rate was 0.27 ± 0.28 mm per year. Mean PR-RPE loss ratio at baseline was 2.16 ± 1.75. Fundus autofluorescence patterns "diffuse" and "diffuse trickling" showed higher PR-RPE loss ratios at baseline and contributed statistically significantly to the slope of GA progression (p = 0.01 and p = 0.0019). Baseline GA lesion size was negatively correlated to PR-RPE loss ratios at baseline (ρ = -0.47, p < 0.0001). Overall, GA growth was higher in patients with higher PR-RPE loss ratios at baseline (ρ = 0.35, p = 0.0011), and the ratio's contribution to the slope of GA progression was statistically significant (p = 0.0001). Eyes with higher PR-RPE loss ratios were more likely to exhibit FAF patterns "diffuse" and "diffuse trickling" and showed higher GA progression rates. Baseline characteristics derived from FAF and OCT images may thus offer information on lesion progression.

Artificial intelligence applications in ophthalmic optical coherence tomography: a 12-year bibliometric analysis.

To explore the current application and research frontiers of global ophthalmic optical coherence tomography (OCT) imaging artificial intelligence (AI) research. The citation data were downloaded from the Web of Science Core Collection database (WoSCC) to evaluate the articles in application of AI in ophthalmic OCT published from January 1, 2012 to December 31, 2023. This information was analyzed using CiteSpace 6.2.R2 Advanced software, and high-impact articles were analyzed. In general, 877 articles from 65 countries were studied and analyzed, of which 261 were published by the United States and 252 by China. The centrality of the United States is 0.33, the H index is 38, and the H index of two institutions in England reaches 20. Ophthalmology, computer science, and AI are the main disciplines involved. Hot keywords after 2018 include deep learning (DL), AI, macular degeneration, and automatic segmentation. The annual number of articles on AI applications in ophthalmic OCT has grown rapidly. The United States holds a prominent position. Institutions like the University of California System and the University of London are spearheading advancements. Initial researches centered on the automatic recognition and diagnosis of ocular diseases leveraging traditional machine learning (ML) technology and OCT images. Nowadays, the imaging process algorithm selection has shifted its focus towards DL. Concurrently, optical coherence tomography angiography (OCTA) and computer-aided diagnosis (CAD) have emerged as key areas of contemporary research.

Estimation of foveal avascular zone area from a B-scan OCT image using machine learning algorithms.

The objective of this study is to estimate the area of the Foveal Avascular Zone (FAZ) from B-scan OCT images using machine learning algorithms. We developed machine learning models to predict the FAZ area from OCT B-scan images of eyes without retinal vascular diseases. The study involved three models: Model 1 predicted the FAZ length from B-scan images; Model 2 estimated the FAZ area from the predicted length using 1, 3, or 5 horizontal measurements; and Model 3 converted the FAZ area from pixels to mm2. The models' performance was evaluated using Mean Absolute Error (MAE), Mean Squared Error (MSE), and the Coefficient of Determination (R2). The FAZ area was subsequently estimated by sequentially applying Models 1→2→3 on a new dataset. Model 1 achieved a MAE of 2.86, MSE of 17.56, and R2 of 0.87. Model 2's performance improved with the number of horizontal measurements, with the best results obtained using 5 lines (MAE: 40.36, MSE: 3129.65, R2: 0.95). Model 3 achieved a MAE of 1.52e-3, MSE of 4.0e-6, and R2 of 1.0. The accuracy of FAZ area estimation increased with the number of B-scan images used, with the correlation coefficient rising from 0.475 (1 line) to 0.596 (5 lines). Bland-Altman analysis showed improved agreement between predicted and actual FAZ areas with increasing B-scan images, evidenced by decreasing biases and narrower limits of agreement. This study successfully developed machine learning models capable of predicting FAZ area from OCT B-scan images. These findings demonstrate the potential for using OCT images to predict OCTA data, particularly in populations where OCTA imaging is challenging, such as children and the elderly. Future studies could explore the developmental mechanisms of the FAZ and macula, providing new insights into retinal health across different age groups.

THERAPEUTIC REFRACTIVE VITRECTOMY (TRV) FOR THE MANAGEMENT OF VITREOUS FLOATERS AND OPACITIES (VFO) ASSESSED BY THE STANDARDIZED AND KINETIC ANATOMICAL AND FUNCTIONAL TESTING OF VITREOUS FLOATERS AND OPACITIES (SK VFO TEST).

Propose new terminology and evaluate the effectiveness of Therapeutic Refractive Vitrectomy (TRV) for selective removal of vitreous floaters and opacities (VFO) utilizing Standardized Kinetic Anatomical Functional Testing of VFO (SK VFO Test) and new ultra widefield (UWF) OCT imaging techniques. Retrospective analysis. Twenty eyes underwent TRV for symptomatic VFO. Pre-/post-TRV assessments: SK-VFO Test, including straylight measurements (HD Analyzer, Light Disturbance Analyzer, C-Quant) alongside non-contact imaging including a new UWF OCT to evaluate changes in vitreous anatomical and optical properties. Post-TRV evaluations indicated objective changes in vitreous optical properties and subjective measures. Reduced straylight measurements: HDA 22%, LDA 54.4% (p=0.013), and C-Quant 7.8% (p=0.034). Patient reported outcomes statistically significantly improved (p=0.022). Corrected distance visual acuity (CDVA) changes were marginal. New UWF 26 mm with a 12 mm imaging window OCT facilitated detailed vitreous imaging, confirming status of posterior vitreous detachment (PVD) (100%). Post-TRV UWF and OCT imaging demonstrated restoration of vitreous clarity, confirmed presence of residual cortical vitreous and absence of new PVDs. TRV is a significant contribution for therapeutic refractive surgery as a safe and effective approach to enhancing visual quality, correcting refractive and opaque vitreous anomalies. Improvement in CDVA was minimal representing limited effectiveness as a measure of comprehensive visual function. Improvements in objective straylight measures and imaging are in alignment with subjective symptom improvements post-TRV. This underscores the utility and value of new holistic evaluation methods beyond traditional metrics to assess the impact of TRV on visual function and quality of life.

Subclinical Detection of Hydroxychloroquine-Induced Retinopathy in Patients with Systemic Lupus Erythematous Using Multifocal Electroretinography and Optical Coherence Tomography.

Background/Objectives: Although hydroxychloroquine (HCQ) is used to treat systemic lupus erythematosus (SLE), it is associated with retinal toxicity. Early diagnosis can prevent the further progression of HCQ-associated retinopathy by discontinuing HCQ treatments. This study aimed to evaluate the early diagnostic parameters in patients with SLE treated with HCQ and identify the best approach using multifocal electroretinography (mfERG) and swept-source optical coherence tomography (SS-OCT) to reflect subclinical retinal toxicity. Methods: Thirty-eight patients with SLE (76 eyes) and 18 healthy controls (36 eyes) were enrolled. They were referred for HCQ retinopathy screening without visual field defects. The patients were tested using a standard 61-hexagon mfERG stimulus and SS-OCT. Ten groups of the mfERG responses from the sectors were averaged to compare the quadrants, hemiretinal areas, consecutive ring amplitudes, and ring ratios (R1/R2-R5) from the center to the periphery. Additionally, the ganglion cell complex (GCC) analyses were performed using SS-OCT. Results: No difference was observed in GCC thickness on the OCT images, in the P1 amplitudes, and in the implicit time of mfERG. However, the R1/Rx ring ratios, except the R1/R2 ratio, showed significant differences among the three groups (p = 0.759, 0.018, 0.029, and 0.029, respectively). The R1/R3, R1/R4, and R1/R5 ring ratios demonstrated a correlation with the duration of HCQ therapy (r = -0.303, -0.279, and -0.266; p = 0.003, 0.006, and 0.009). The areas under the receiver operating characteristic curve of the ring ratios R1/R3-R5 were 0.730, 0.702, and 0.724, respectively (p = 0.004, 0.012, and 0.006), indicating the likelihood of being categorized as a high-risk group for subclinical HCQ retinopathy. Conclusions: The ring ratio of mfERG reflects the subclinical electrophysiological alterations induced by HCQ and can become more clinically useful by simplifying screening examinations.

Novel Application of Non-Invasive Methodological Approaches in Biomedical Sciences Towards Better Understanding of Marine Teleost Ocular Health and Disease.

Seafood is an important resource for global nutrition and food security, with both land and marine aquaculture playing pivotal roles. High visual acuity is key for health and survival of farmed, cultured, and wild fish. Cleaner fish technology to control parasite infestation has become important in marine aquaculture and highlights the importance of visual acuity in the efficacy of cleaner fish species. New clinical diagnostic approaches towards understanding and optimising fish visual health could benefit both aquacultured and wild fish populations. Opportunities for developing and using advanced non-invasive clinical assessment and diagnosis of ocular health in wild, cultured, and experimental fish are key to more rapidly realising how threats to eye health in these animals might be better understood and mitigated. Ophthalmoscopy can rapidly and non-invasively image anatomical aspects of retinal and anterior ocular tissues and has been used in mammalian biomedicine since the turn of the 20th century. More now than ever, labour-intensive post-mortem approaches for ocular analysis such as histology are increasingly being replaced or supplemented by application of various forms of optical coherence tomography (OCT) imaging of ocular tissues in mammalian biomedicine. Advances and availability of other methodological approaches such as three-dimensional printing and computer science make instrument customisation affordable and adaptable. This review article will outline how ophthalmoscopy, OCT, and other methodologies are being applied towards understanding ocular health in teleost fish species and will describe some of the future opportunities that technological advances might afford in advancing ocular imaging in fish health and disease in general.

Clinical Course and Prognostic Factors in Non-Neovascular Age-Related Macular Degeneration with Subretinal Fluid.

To investigate the clinical course and prognostic factors of age-related macular degeneration (AMD) without macular neovascularization (MNV) in patients presenting with pigment epithelial detachment (PED) and the associated subretinal fluid (SRF). Morphological characteristics of spectral-domain optical coherence tomography images were analyzed to determine anatomic outcomes. Factors associated with the progression to late AMD, defined as complete retinal pigment epithelium and outer retinal atrophy (cRORA) or MNV, were investigated. Fifty eyes of 41 patients were included in this study. The most common SRF location was the angle of the PED (56%), and there was a significant decrease in SRF thickness and PED height and width over the follow-up period. Eleven (22%) eyes developed cRORA, and seven (14%) eyes developed MNV during a mean period of 52.1 months. Multivariate analysis revealed that hyperreflective foci and MNV in the fellow eye were associated with the development of cRORA, and higher PED height was a significant factor associated with the development of MNV. In patients with AMD, SRF can be accompanied by PED in the absence of MNV. Notably, patients with this characteristic entity can progress to late AMD, including cRORA and MNV, in a significant proportion of cases.

Retinal fluid quantification using a novel deep learning algorithm in patients treated with faricimab in the TRUCKEE study.

Investigate retinal fluid changes via a novel deep-learning algorithm in real-world patients receiving faricimab for the treatment of neovascular age-related macular degeneration (nAMD). Multicenter, retrospective chart review and optical coherence tomography (OCT)image upload from participating sites was conducted on patients treated with faricimab for nAMD from February 2022 to January 2024. The Notal OCT Analyzer (NOA) algorithm provided intraretinal, subretinal and total retinal fluid for each scan. Results were segregated based on treatment history and fluid compartments, allowing for multiple cross-sections of evaluation. A total of 521 eyes were included at baseline. The previous treatments prior to faricimab were aflibercept, ranibizumab, bevacizumab, or treatment-naive for 52.3%, 21.0%, 13.3%, and 11.2% of the eyes, respectively. Of all 521 eyes, 49.9% demonstrated fluid reduction after one injection of faricimab. The mean fluid reduction after one injection was -60.7nL. The proportion of eyes that saw reduction in fluid compared to baseline after second, third, fourth and fifth faricimab injections were 54.4%, 51.9%, 51.4% and 52.2%, respectively. The mean (SD) retreatment interval after second, third, fourth and fifth faricimab injection were 53.4 (34.3), 56.6 (36.0), 57.1 (35.3) and 61.5 (40.2) days, respectively. Deep-learning algorithms provide a novel tool for evaluating precise quantification of retinal fluid after treatment of nAMD with faricimab. Faricimab demonstrates reduction of retinal fluid in multiple groups after just one injection and sustains this response after multiple treatments, along with providing increases in treatment intervals between subsequent injections.

Monte Carlo-based realistic simulation of optical coherence tomography angiography.

Optical coherence tomography angiography (OCTA) offers unparalleled capabilities for non-invasive detection of vessels. However, the lack of accurate models for light-tissue interaction in OCTA jeopardizes the development of the techniques to further extract quantitative information from the measurements. In this manuscript, we propose a Monte Carlo (MC)-based simulation method to precisely describe the signal formation of OCTA based on the fundamental theory of light-tissue interactions. A dynamic particle-fixed model is developed to depict the spatial-temporal behaviors of the tissue phantom: the particles are initialized and fixed in specific locations with wavelength-dependent scattering cross-sections and are allowed to travel over time. We then employ a full-spectrum MC engine to faithfully simulate the formation of OCT and OCTA images. A simulation on a vessel-mimicking phantom demonstrated that speckle characteristics in OCT as well as decorrelation maps in OCTA could be successfully reproduced. We further illustrate the usefulness of our method on the quantitative OCTA by extending it to simulate the gradual saturation of decorrelation in OCTA-based velocimetry. We believe our method will serve as a valuable tool for studying OCTA theory and inspire better solutions and metrics for non-invasive flow velocity measurement.

Autoencoder-based phenotyping of ophthalmic images highlights genetic loci influencing retinal morphology and provides informative biomarkers.

Genome-wide association studies (GWAS) have been remarkably successful in identifying associations between genetic variants and imaging-derived phenotypes. To date, the main focus of these analyses has been on established, clinically-used imaging features. We sought to investigate if deep learning approaches can detect more nuanced patterns of image variability. We used an autoencoder to represent retinal optical coherence tomography (OCT) images from 31,135 UK Biobank participants. For each subject, we obtained a 64-dimensional vector representing features of retinal structure. GWAS of these autoencoder-derived imaging parameters identified 118 statistically significant loci; 41 of these associations were also significant in a replication study. These loci encompassed variants previously linked with retinal thickness measurements, ophthalmic disorders and/or neurodegenerative conditions. Notably, the generated retinal phenotypes were found to contribute to predictive models for glaucoma and cardiovascular disorders. Overall, we demonstrate that self-supervised phenotyping of OCT images enhances the discoverability of genetic factors influencing retinal morphology and provides epidemiologically-informative biomarkers. Code and data links available at https://github.com/tf2/autoencoder-oct. Supplementary data are available at Bioinformatics online.

Optical clearing with tartrazine enables deep transscleral imaging with optical coherence tomography.

Imaging deep structures with optical coherence tomography (OCT) is difficult in highly scattering biological tissue, such as the sclera. There is a need to visualize the suprachoroidal space and choroid through the sclera to study suprachoroidal drug delivery. We aim to develop optical methods to image through the highly scattering sclera with a custom-built OCT system to visualize the suprachoroidal space and drug delivery within. We developed a custom handheld OCT scanner to image the anterior segment and suprachoroidal space in ex vivo eye models. Tartrazine (Yellow 5) solution, which has been shown to optically clear biological tissue in the visible regime, was tested as a clearing agent to optimize near infrared OCT imaging through the sclera. Tartrazine dramatically increased OCT signal return from the deeper sclera and choroid and thus enabled visualization of the suprachoroidal drug delivery after transscleral injection. We demonstrated successful optical clearing of the thick, porcine sclera with a compact handheld OCT system to image the suprachoroidal space. We believe there is broader potential to use optical clearing with handheld OCT for a variety of previously inaccessible, highly scattering tissue samples.