ABSTRACT
Purpose: To train and validate a convolutional neural network to segment nonperfusion areas (NPAs) in multiple retinal vascular plexuses on widefield optical coherence tomography angiography (OCTA). Methods: This cross-sectional study included 202 participants with a full range of diabetic retinopathy (DR) severities (diabetes mellitus without retinopathy, mild to moderate non-proliferative DR, severe non-proliferative DR, and proliferative DR) and 39 healthy participants. Consecutive 6 × 6-mm OCTA scans at the central macula, optic disc, and temporal region in one eye from 202 participants in a clinical DR study were acquired with a 70-kHz OCT commercial system (RTVue-XR). Widefield OCTA en face images were generated by montaging the scans from these three regions. A projection-resolved OCTA algorithm was applied to remove projection artifacts at the voxel scale. A deep convolutional neural network with a parallel U-Net module was designed to detect NPAs and distinguish signal reduction artifacts from flow deficits in the superficial vascular complex (SVC), intermediate capillary plexus (ICP), and deep capillary plexus (DCP). Expert graders manually labeled NPAs and signal reduction artifacts for the ground truth. Sixfold cross-validation was used to evaluate the proposed algorithm on the entire dataset. Results: The proposed algorithm showed high agreement with the manually delineated ground truth for NPA detection in three retinal vascular plexuses on widefield OCTA (mean ± SD F-score: SVC, 0.84 ± 0.05; ICP, 0.87 ± 0.04; DCP, 0.83 ± 0.07). The extrafoveal avascular area in the DCP showed the best sensitivity for differentiating eyes with diabetes but no retinopathy (77%) from healthy controls and for differentiating DR by severity: DR versus no DR, 77%; referable DR (rDR) versus non-referable DR (nrDR), 79%; vision-threatening DR (vtDR) versus non-vision-threatening DR (nvtDR), 60%. The DCP also showed the best area under the receiver operating characteristic curve for distinguishing diabetes from healthy controls (96%), DR versus no DR (95%), and rDR versus nrDR (96%). The three-plexus-combined OCTA achieved the best result in differentiating vtDR and nvtDR (81.0%). Conclusions: A deep learning network can accurately segment NPAs in individual retinal vascular plexuses and improve DR diagnostic accuracy. Translational Relevance: Using a deep learning method to segment nonperfusion areas in widefield OCTA can potentially improve the diagnostic accuracy of diabetic retinopathy by OCT/OCTA systems.
Subject(s)
Diabetic Retinopathy , Neural Networks, Computer , Retinal Vessels , Tomography, Optical Coherence , Humans , Tomography, Optical Coherence/methods , Diabetic Retinopathy/diagnostic imaging , Diabetic Retinopathy/diagnosis , Cross-Sectional Studies , Retinal Vessels/diagnostic imaging , Male , Middle Aged , Female , Fluorescein Angiography/methods , Aged , Algorithms , Adult , Deep LearningABSTRACT
Optical coherence tomography (OCT) and its extension OCT angiography (OCTA) have become essential clinical imaging modalities due to their ability to provide depth-resolved angiographic and tissue structural information non-invasively and at high resolution. Within a field of view, the anatomic detail available is sufficient to identify several structural and vascular pathologies that are clinically relevant for multiple prevalent blinding diseases, including age-related macular degeneration (AMD), diabetic retinopathy (DR), and vein occlusions. The main limitation in contemporary OCT devices is that this field of view is limited due to a fundamental trade-off between system resolution/sensitivity, sampling density, and imaging window dimensions. Here, we describe a swept-source OCT device that can capture up to a 12 × 23-mm field of view in a single shot and show that it can identify conventional pathologic features such as non-perfusion areas outside of conventional fields of view. We also show that our approach maintains sensitivity sufficient to visualize novel features, including choriocapillaris morphology beneath the macula and macrophage-like cells at the inner limiting membrane, both of which may have implications for disease.
Subject(s)
Diabetic Retinopathy , Retinal Vessels , Humans , Retinal Vessels/pathology , Fluorescein Angiography , Tomography, Optical Coherence/methods , RetinaABSTRACT
Importance: Best recruitment practices for increasing diversity are well established, but the adoption and impact of these practices in ophthalmology residency recruitment are unknown. Objective: To describe the adoption of bias reduction practices in groups underrepresented in ophthalmology (URiO) residency recruitment and determine which practices are effective for increasing URiO residents. Design, Setting, and Participants: This cross-sectional survey study used an 18-item questionnaire included in the online survey of the Association of University Professors in Ophthalmology (AUPO) Residency Program Directors. Data collection occurred from July 2022 to December 2022. The data were initially analyzed on January 16, 2023. Participants included residency program directors (PDs) in the AUPO PD listserv database. Main Outcomes and Measures: Descriptive analysis of resident selection committee approaches, evaluation of applicant traits, and use of bias reduction tools. Primary outcome was diversity assessed by presence of at least 1 resident in the last 5 classes who identified as URiO, including those underrepresented in medicine (URiM), lesbian, gay, bisexual, transgender, queer, intersex, and asexual plus, or another disadvantaged background (eg, low socioeconomic status). Multivariate analyses of recruitment practices were conducted to determine which practices were associated with increased URiO and URiM. Results: Among 106 PDs, 65 completed the survey (61.3%). Thirty-nine PDs used an interview rubric (60.0%), 28 used interview standardization (43.0%), 56 provided at least 1 bias reduction tool to their selection committee (86.2%), and 44 used postinterview metrics to assess diversity, equity, and inclusion efforts (67.7%). Application filters, interview standardization, and postinterview metrics were not associated with increased URiO. Multivariate logistic regression analysis showed larger residency class (odds ratio [OR], 1.34; 95% CI, 1.09-1.65; P = .01) and use of multiple selection committee bias reduction tools (OR, 1.47; 95% CI, 1.13-1.92; P = .01) were positively associated with increased URiO, whereas use of interview rubrics (OR, 0.72; 95% CI, 0.59-0.87; P = .001) and placing higher importance of applicant interest in a program (OR, 0.83; 95% CI, 0.75-0.92; P = .02) were negatively associated. URiM analyses showed similar associations. Conclusions and Relevance: Ophthalmology residency interviews are variably standardized. In this study, providing multiple bias reduction tools to selection committees was associated with increased URiO and URiM residents. Prioritizing applicant interest in a program may reduce resident diversity. Interview rubrics, while intended to reduce bias, may inadvertently increase inequity.
Subject(s)
Internship and Residency , Ophthalmology , Personnel Selection , Humans , Cross-Sectional Studies , Ophthalmology/education , Female , Male , Surveys and Questionnaires , United States , Cultural Diversity , Education, Medical, Graduate/standards , Minority Groups/statistics & numerical data , AdultABSTRACT
Objective: To determine the impact of documentation workflow on the accuracy of coded diagnoses in electronic health records (EHRs). Design: Cross-sectional study. Participants: All patients who completed visits at the Casey Eye Institute Retina Division faculty clinic between April 7, 2022 and April 13, 2022. Main Outcome Measures: Agreement between coded diagnoses and clinical notes. Methods: We assessed the rate of agreement between the diagnoses in the clinical notes and the coded diagnosis in the EHR using manual review and examined the impact of the documentation workflow on the rate of agreement in an academic retina practice. Results: In 202 visits by 8 physicians, 78% (range, 22%-100%) had an agreement between the coded diagnoses and the clinical notes. When physicians integrated the diagnosis code entry and note composition, the rate of agreement was 87.9% (range, 62%-100%). For those who entered the diagnosis codes separately from writing notes, the agreement was 44.4% (22%-50%, P < 0.0001). Conclusion: The visit-specific agreement between the coded diagnosis and the progress note can vary widely by workflow. The workflow and EHR design may be an important part of understanding and improving the quality of EHR data. Financial Disclosures: Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.
ABSTRACT
Purpose: To assess whether the combination of en face OCT and OCT angiography (OCTA) can capture observable, but subtle, structural changes that precede clinically evident retinal neovascularization (RNV) in eyes with diabetic retinopathy (DR). Design: Retrospective, longitudinal study. Participants: Patients with DR that had at least 2 visits. Methods: We obtained wide-field OCTA scans of 1 eye from each participant and generated en face OCT, en face OCTA, and cross-sectional OCTA. We identified eyes with RNV sprouts, defined as epiretinal hyperreflective materials on en face OCT with flow signals breaching the internal limiting membrane on the cross-sectional OCTA without recognizable RNV on en face OCTA and RNV fronds, defined as recognizable abnormal vascular structures on the en face OCTA. We examined the corresponding location from follow-up or previous visits for the presence or progression of the RNV. Main Outcome Measures: The characteristics and longitudinal observation of early signs of RNV. Results: From 71 eyes, we identified RNV in 20 eyes with the combination of OCT and OCTA, of which 13 (65%) were photographically graded as proliferative DR, 6 (30%) severe nonproliferative DR, and 1 (5%) moderate nonproliferative diabetic retinopathy. From these eyes, we identified 38 RNV sprouts and 26 RNV fronds at the baseline. Thirty-four RNVs (53%) originated from veins, 24 (38%) were from intraretinal microabnormalities, and 6 (9%) were from a nondilated capillary bed. At the final visit, 53 RNV sprouts and 30 RNV fronds were detected. Ten eyes (50%) showed progression, defined as having a new RNV lesion or the development of an RNV frond from an RNV sprout. Four (11%) RNV sprouts developed into RNV fronds with a mean interval of 7.0 months. Nineteen new RNV sprouts developed during the follow-up, whereas no new RNV frond was observed outside an identified RNV sprout. The eyes with progression were of younger age (P = 0.014) and tended to be treatment naive (P = 0.07) compared with eyes without progression. Conclusions: Longitudinal observation demonstrated that a combination of en face OCT and cross-sectional OCTA can identify an earlier form of RNV before it can be recognized on en face OCTA. Financial Disclosures: Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.