CHOROIDAL IMAGING BIOMARKERS TO PREDICT HIGHLY RESPONSIVE AND RESISTANT CASES TREATED WITH STANDARDIZED ANTI-VASCULAR ENDOTHELIAL GROWTH FACTOR REGIMEN IN NEOVASCULAR AGE-RELATED MACULAR DEGENERATION.

PURPOSE: To determine structural predictors of treatment response in neovascular age-related macular degeneration analyzing optical coherence tomography (OCT)-related biomarkers. METHODS: A retrospective review of patients undergoing treatment for neovascular age-related macular degeneration at a tertiary institute was performed at presentation. High-intensity regimen included eyes on long-term anti-vascular endothelial growth factor treatment with the inability to extend beyond a month without a relapse and needed double the dose of medication (n = 25). Low-intensity regimen had eyes that went into long-term remission after at least three injections and remained dry for more than a year until the last visit (n = 20). Multimodal imaging including fluorescein angiogram, OCT, and comprehensive ocular evaluation were done. Choroidal vascularity index, total choroidal area, luminal area, subfoveal choroidal thickness, choriocapillaris thickness and Haller and Sattler layer thickness were analyzed for statistical significance. RESULTS: The groups had no significant difference at baseline in age, gender, incidence of reticular pseudodrusen, polypoidal choroidal vasculopathy feature on OCT, type of choroidal neovascular membrane, and geographic atrophy. Multinomial logistic regression revealed that thicker subfoveal choroidal thickness and larger total choroidal area were the significant predictors of poor response to anti-vascular endothelial growth factor treatment (E = 0.02; P = 0.02; E = 1.82; P = 0.0075). CONCLUSION: Thicker subfoveal choroidal thickness and higher total choroidal area are useful variables to predict a poor treatment response.

Ultra-wide field and new wide field composite retinal image registration with AI-enabled pipeline and 3D distortion correction algorithm.

PURPOSE: This study aimed to compare a new Artificial Intelligence (AI) method to conventional mathematical warping in accurately overlaying peripheral retinal vessels from two different imaging devices: confocal scanning laser ophthalmoscope (cSLO) wide-field images and SLO ultra-wide field images. METHODS: Images were captured using the Heidelberg Spectralis 55-degree field-of-view and Optos ultra-wide field. The conventional mathematical warping was performed using Random Sample Consensus-Sample and Consensus sets (RANSAC-SC). This was compared to an AI alignment algorithm based on a one-way forward registration procedure consisting of full Convolutional Neural Networks (CNNs) with Outlier Rejection (OR CNN), as well as an iterative 3D camera pose optimization process (OR CNN + Distortion Correction [DC]). Images were provided in a checkerboard pattern, and peripheral vessels were graded in four quadrants based on alignment to the adjacent box. RESULTS: A total of 660 boxes were analysed from 55 eyes. Dice scores were compared between the three methods (RANSAC-SC/OR CNN/OR CNN + DC): 0.3341/0.4665/4784 for fold 1-2 and 0.3315/0.4494/4596 for fold 2-1 in composite images. The images composed using the OR CNN + DC have a median rating of 4 (out of 5) versus 2 using RANSAC-SC. The odds of getting a higher grading level are 4.8 times higher using our OR CNN + DC than RANSAC-SC (p < 0.0001). CONCLUSION: Peripheral retinal vessel alignment performed better using our AI algorithm than RANSAC-SC. This may help improve co-localizing retinal anatomy and pathology with our algorithm.

Accuracy and Time Comparison Between Side-by-Side and Artificial Intelligence Overlayed Images.

BACKGROUND AND OBJECTIVE: The purpose of this study was to evaluate the accuracy and the time to find a lesion, taken in different platforms, color fundus photographs and infrared scanning laser ophthalmoscope images, using the traditional side-by-side (SBS) colocalization technique to an artificial intelligence (AI)-assisted technique. PATIENTS AND METHODS: Fifty-three pathological lesions were studied in 11 eyes. Images were aligned using SBS and AI overlaid methods. The location of each color fundus lesion on the corresponding infrared scanning laser ophthalmoscope image was analyzed twice, one time for each method, on different days, for two specialists, in random order. The outcomes for each method were measured and recorded by an independent observer. RESULTS: The colocalization AI method was superior to the conventional in accuracy and time (P < .001), with a mean time to colocalize 37% faster. The error rate using AI was 0% compared with 18% in SBS measurements. CONCLUSIONS: AI permitted a more accurate and faster colocalization of pathologic lesions than the conventional method. [Ophthalmic Surg Lasers Imaging Retina 2023;54:108-113.].

ACCURATE REGISTRATION BETWEEN ULTRA-WIDE-FIELD AND NARROW ANGLE RETINA IMAGES WITH 3D EYEBALL SHAPE OPTIMIZATION.

The Ultra-Wide-Field (UWF) retina images have attracted wide attentions in recent years in the study of retina. However, accurate registration between the UWF images and the other types of retina images could be challenging due to the distortion in the peripheral areas of an UWF image, which a 2D warping can not handle. In this paper, we propose a novel 3D distortion correction method which sets up a 3D projection model and optimizes a dense 3D retina mesh to correct the distortion in the UWF image. The corrected UWF image can then be accurately aligned to the target image using 2D alignment methods. The experimental results show that our proposed method outperforms the state-of-the-art method by 30%.

Retinal tissue and microvasculature loss in COVID-19 infection.

This cross-sectional study aimed to investigate the hypothesis that permanent capillary damage may underlie the long-term COVID-19 sequela by quantifying the retinal vessel integrity. Participants were divided into three subgroups; Normal controls who had not been affected by COVID-19, mild COVID-19 cases who received out-patient care, and severe COVID-19 cases requiring intensive care unit (ICU) admission and respiratory support. Patients with systemic conditions that may affect the retinal vasculature before the diagnosis of COVID-19 infection were excluded. Participants underwent comprehensive ophthalmologic examination and retinal imaging obtained from Spectral-Domain Optical Coherence Tomography (SD-OCT), and vessel density using OCT Angiography. Sixty-one eyes from 31 individuals were studied. Retinal volume was significantly decreased in the outer 3 mm of the macula in the severe COVID-19 group (p = 0.02). Total retinal vessel density was significantly lower in the severe COVID-19 group compared to the normal and mild COVID-19 groups (p = 0.004 and 0.0057, respectively). The intermediate and deep capillary plexuses in the severe COVID-19 group were significantly lower compared to other groups (p < 0.05). Retinal tissue and microvascular loss may be a biomarker of COVID-19 severity. Further monitoring of the retina in COVID-19-recovered patients may help further understand the COVID-19 sequela.

Two-Step Registration on Multi-Modal Retinal Images via Deep Neural Networks.

Multi-modal retinal image registration plays an important role in the ophthalmological diagnosis process. The conventional methods lack robustness in aligning multi-modal images of various imaging qualities. Deep-learning methods have not been widely developed for this task, especially for the coarse-to-fine registration pipeline. To handle this task, we propose a two-step method based on deep convolutional networks, including a coarse alignment step and a fine alignment step. In the coarse alignment step, a global registration matrix is estimated by three sequentially connected networks for vessel segmentation, feature detection and description, and outlier rejection, respectively. In the fine alignment step, a deformable registration network is set up to find pixel-wise correspondence between a target image and a coarsely aligned image from the previous step to further improve the alignment accuracy. Particularly, an unsupervised learning framework is proposed to handle the difficulties of inconsistent modalities and lack of labeled training data for the fine alignment step. The proposed framework first changes multi-modal images into a same modality through modality transformers, and then adopts photometric consistency loss and smoothness loss to train the deformable registration network. The experimental results show that the proposed method achieves state-of-the-art results in Dice metrics and is more robust in challenging cases.

Effective treatment of retinal neovascular leakage with fusogenic porous silicon nanoparticles delivering VEGF-siRNA.

Aim: To evaluate an intravitreally injected nanoparticle platform designed to deliver VEGF-A siRNA to inhibit retinal neovascular leakage as a new treatment for proliferative diabetic retinopathy and diabetic macular edema. Materials & methods: Fusogenic lipid-coated porous silicon nanoparticles loaded with VEGF-A siRNA, and pendant neovascular integrin-homing iRGD, were evaluated for efficacy by intravitreal injection in a rabbit model of retinal neovascularization. Results: For 12 weeks post-treatment, a reduction in vascular leakage was observed for treated diseased eyes versus control eyes (p = 0.0137), with a corresponding reduction in vitreous VEGF-A. Conclusion: Fusogenic lipid-coated porous silicon nanoparticles siRNA delivery provides persistent knockdown of VEGF-A and reduced leakage in a rabbit model of retinal neovascularization as a potential new intraocular therapeutic.

Robust Content-Adaptive Global Registration for Multimodal Retinal Images Using Weakly Supervised Deep-Learning Framework.

Multimodal retinal imaging plays an important role in ophthalmology. We propose a content-adaptive multimodal retinal image registration method in this paper that focuses on the globally coarse alignment and includes three weakly supervised neural networks for vessel segmentation, feature detection and description, and outlier rejection. We apply the proposed framework to register color fundus images with infrared reflectance and fluorescein angiography images, and compare it with several conventional and deep learning methods. Our proposed framework demonstrates a significant improvement in robustness and accuracy reflected by a higher success rate and Dice coefficient compared with other methods.

Evaluation of the clinical utility of optical coherence tomography angiography in age-related macular degeneration.

BACKGROUND/AIMS: To evaluate the ability of optical coherence tomography angiography (OCTA) to identify the presence or absence of choroidal neovascularisation (CNV) and CNV activity in age-related macular degeneration (AMD). METHODS: Clinical parameters, fundus fluorescein angiogram and spectral-domain optical coherence tomography (SD-OCT) were used as the gold standard to determine disease activity. OCTA imaging was performed on the same day and was graded by two masked retina specialists for the presence or absence of CNV. Traditional multimodal imaging and OCTA findings were compared. RESULTS: One hundred and fifty-two eyes of 106 patients with AMD were retrospectively reviewed. Of these, 59 eyes had wet AMD and 93 had dry AMD with high-risk drusen. OCTA had 85.4% and 79.3% specificity and sensitivity, respectively, in determining the presence or absence of CNV. OCTA was 69.5% accurate in determining active CNV. False positives and negatives were 21.6% and 8.0%, respectively. CONCLUSIONS: This study suggests that en-face OCTA images allow a moderate ability to identify CNV and that OCTA alone is weak at recognising active CNV requiring treatment in AMD.

Artificial Intelligence for Automated Overlay of Fundus Camera and Scanning Laser Ophthalmoscope Images.

Purpose: The purpose of this study was to evaluate the ability to align two types of retinal images taken on different platforms; color fundus (CF) photographs and infrared scanning laser ophthalmoscope (IR SLO) images using mathematical warping and artificial intelligence (AI). Methods: We collected 109 matched pairs of CF and IR SLO images. An AI algorithm utilizing two separate networks was developed. A style transfer network (STN) was used to segment vessel structures. A registration network was used to align the segmented images to each. Neither network used a ground truth dataset. A conventional image warping algorithm was used as a control. Software displayed image pairs as a 5 × 5 checkerboard grid composed of alternating subimages. This technique permitted vessel alignment determination by human observers and 5 masked graders evaluated alignment by the AI and conventional warping in 25 fields for each image. Results: Our new AI method was superior to conventional warping at generating vessel alignment as judged by masked human graders (P < 0.0001). The average number of good/excellent matches increased from 90.5% to 94.4% with AI method. Conclusions: AI permitted a more accurate overlay of CF and IR SLO images than conventional mathematical warping. This is a first step toward developing an AI that could allow overlay of all types of fundus images by utilizing vascular landmarks. Translational Relevance: The ability to align and overlay imaging data from multiple instruments and manufacturers will permit better analysis of this complex data helping understand disease and predict treatment.