A MULTITASK DEEP-LEARNING SYSTEM FOR ASSESSMENT OF DIABETIC MACULAR ISCHEMIA ON OPTICAL COHERENCE TOMOGRAPHY ANGIOGRAPHY IMAGES.

PURPOSE: We aimed to develop and test a deep-learning system to perform image quality and diabetic macular ischemia (DMI) assessment on optical coherence tomography angiography (OCTA) images. METHODS: This study included 7,194 OCTA images with diabetes mellitus for training and primary validation and 960 images from three independent data sets for external testing. A trinary classification for image quality assessment and the presence or absence of DMI for DMI assessment were labeled on all OCTA images. Two DenseNet-161 models were built for both tasks for OCTA images of superficial and deep capillary plexuses, respectively. External testing was performed on three unseen data sets in which one data set using the same model of OCTA device as of the primary data set and two data sets using another brand of OCTA device. We assessed the performance by using the area under the receiver operating characteristic curves with sensitivities, specificities, and accuracies and the area under the precision-recall curves with precision. RESULTS: For the image quality assessment, analyses for gradability and measurability assessment were performed. Our deep-learning system achieved the area under the receiver operating characteristic curves >0.948 and area under the precision-recall curves >0.866 for the gradability assessment, area under the receiver operating characteristic curves >0.960 and area under the precision-recall curves >0.822 for the measurability assessment, and area under the receiver operating characteristic curves >0.939 and area under the precision-recall curves >0.899 for the DMI assessment across three external validation data sets. Grad-CAM demonstrated the capability of our deep-learning system paying attention to regions related to DMI identification. CONCLUSION: Our proposed multitask deep-learning system might facilitate the development of a simplified assessment of DMI on OCTA images among individuals with diabetes mellitus at high risk for visual loss.

Clinically relevant factors associated with a binary outcome of diabetic macular ischaemia: an OCTA study.

AIMS: We investigated the demographic, ocular, diabetes-related and systemic factors associated with a binary outcome of diabetic macular ischaemia (DMI) as assessed by optical coherence tomography angiography (OCTA) evaluation of non-perfusion at the level of the superficial capillary plexus (SCP) and deep capillary plexus (DCP) in a cohort of patients with diabetes mellitus (DM). MATERIALS AND METHODS: 617 patients with DM were recruited from July 2015 to December 2020 at the Chinese University of Hong Kong Eye Centre. Image quality assessment (gradable or ungradable for assessing DMI) and DMI evaluation (presence or absence of DMI) were assessed at the level of the SCP and DCP by OCTA. RESULTS: 1107 eyes from 593 subjects were included in the final analysis. 560 (50.59%) eyes had DMI at the level of SCP, and 647 (58.45%) eyes had DMI at the level of DCP. Among eyes without diabetic retinopathy (DR), DMI was observed in 19.40% and 24.13% of eyes at SCP and DCP, respectively. In the multivariable logistic regression models, older age, poorer visual acuity, thinner ganglion cell-inner plexiform layer thickness, worsened DR severity, higher haemoglobin A1c level, lower estimated glomerular filtration rate and higher low-density lipoprotein cholesterol level were associated with SCP-DMI. In addition to the aforementioned factors, presence of diabetic macular oedema and shorter axial length were associated with DCP-DMI. CONCLUSION: We reported a series of associated factors of SCP-DMI and DCP-DMI. The binary outcome of DMI might promote a simplified OCTA-based DMI evaluation before subsequent quantitative analysis for assessing DMI extent and fulfil the urge for an updating diabetic retinal disease staging to be implemented with OCTA.

Optical Coherence Tomography Angiography Compared with Multimodal Imaging for Diagnosing Neovascular Central Serous Chorioretinopathy.

PURPOSE: To assess the diagnostic accuracy of optical coherence tomography angiography (OCTA) compared with multimodal imaging for choroidal neovascularization (CNV) in central serous chorioretinopathy (CSC) eyes and to determine the features that predicted CNV. DESIGN: Prospective cross-sectional study. METHODS: Consecutive CSC patients were recruited from retina clinic. The reference standard for CNV was determined by interpretation of multimodal imaging with OCTA, structural OCT line scan, fluorescein angiography (FA), indocyanine green angiography (ICGA), ultra-widefield fundus photography and fundus autofluorescence (FAF). Two independent masked graders examined OCTA without FA and ICGA to diagnose CNV. Univariate and multivariate analyses were performed to evaluate factors associated with CNV. RESULTS: CNV was detected in 69 eyes in 64 out of 277 CSC patients according to reference standard. The two masked graders who examined OCTA had sensitivity of 81.2% (95% Confidence Interval [CI], 71.9%-90.4%) and 78.3% (95% CI, 68.5%-88.0%), specificity of 97.3% (95% CI, 95.9%-98.8%) and 96.2% (95% CI, 94.5%-98.0%), positive predictive values of 82.4% (95% CI, 73.3%-91.4%) and 76.1% (95% CI, 66.1%-86.0%), and negative predictive values of 97.1% (95% CI, 95.6%-98.7%) and 96.7% (95% CI, 95.0%-98.3%). Their mean area under the receiver operating characteristic curve (AUC) was 0.88 with good agreement (Kappa coefficient 0.80 [95% CI, 0.72-0.89]). Flat irregular pigment epithelial detachment on structural OCT, neovascular network on OCTA and ill-defined late leakage on FA significantly correlated with CNV in CSC from multiple regression (P < 0.001, P < 0.001 and P = 0.005, respectively). CONCLUSIONS: There is discordance between OCTA and multimodal imaging in diagnosing CNV in CSC. This study demonstrated the caveats in OCTA interpretation, such as small extrafoveal lesions and retinal pigment epithelial alterations. Comprehensive interpretation of OCTA with dye angiography and structural OCT is recommended.

A Multitask Deep-Learning System to Classify Diabetic Macular Edema for Different Optical Coherence Tomography Devices: A Multicenter Analysis.

OBJECTIVE: Diabetic macular edema (DME) is the primary cause of vision loss among individuals with diabetes mellitus (DM). We developed, validated, and tested a deep learning (DL) system for classifying DME using images from three common commercially available optical coherence tomography (OCT) devices. RESEARCH DESIGN AND METHODS: We trained and validated two versions of a multitask convolution neural network (CNN) to classify DME (center-involved DME [CI-DME], non-CI-DME, or absence of DME) using three-dimensional (3D) volume scans and 2D B-scans, respectively. For both 3D and 2D CNNs, we used the residual network (ResNet) as the backbone. For the 3D CNN, we used a 3D version of ResNet-34 with the last fully connected layer removed as the feature extraction module. A total of 73,746 OCT images were used for training and primary validation. External testing was performed using 26,981 images across seven independent data sets from Singapore, Hong Kong, the U.S., China, and Australia. RESULTS: In classifying the presence or absence of DME, the DL system achieved area under the receiver operating characteristic curves (AUROCs) of 0.937 (95% CI 0.920-0.954), 0.958 (0.930-0.977), and 0.965 (0.948-0.977) for the primary data set obtained from CIRRUS, SPECTRALIS, and Triton OCTs, respectively, in addition to AUROCs >0.906 for the external data sets. For further classification of the CI-DME and non-CI-DME subgroups, the AUROCs were 0.968 (0.940-0.995), 0.951 (0.898-0.982), and 0.975 (0.947-0.991) for the primary data set and >0.894 for the external data sets. CONCLUSIONS: We demonstrated excellent performance with a DL system for the automated classification of DME, highlighting its potential as a promising second-line screening tool for patients with DM, which may potentially create a more effective triaging mechanism to eye clinics.

Ranibizumab for myopic choroidal neovascularization.

INTRODUCTION: Myopic choroidal neovascularization (CNV) is one of the most vision-threatening complications in patients with pathologic myopia. Over the last decade, anti-angiogenesis therapy with anti-vascular endothelial growth factor (anti-VEGF) agents has become the standard-of-care treatment for myopic CNV and ranibizumab has been approved for treating myopic CNV. AREAS COVERED: Review of preclinical studies and clinical trials data supporting the use of ranibizumab for myopic CNV. Discussion on the mechanisms, efficacy, safety, regulatory affairs, and future directions of ranibizumab for myopic CNV are highlighted. EXPERT OPINION: Ranibizumab has demonstrated good efficacy and safety profile in multiple clinical trials and long-term studies for treating myopic CNV. Cost-effective analysis has shown that ranibizumab therapy is a cost-effective treatment for myopic CNV. Among the currently available anti-VEGF agents, ranibizumab is the only drug that is approved for the treatment of myopic CNV by the US Food and Drug Administration. In the coming few years, biosimilars of ranibizumab may become available and will have the potential to lower the cost of ranibizumab. Long-term visual gain after ranibizumab treatment for myopic CNV is limited by chorioretinal atrophy associated with pathologic myopia and further research is required to tackle the development of chorioretinal atrophy.