AimTo explore and evaluate an appropriate deep learning system (DLS) for the detection of 12 major fundus diseases using colour fundus photography.MethodsDiagnostic performance of a DLS was tested on the detection of normal fundus and 12 major fundus diseases including referable diabetic retinopathy, pathologic myopic retinal degeneration, retinal vein occlusion, retinitis pigmentosa, retinal detachment, wet and dry age-related macular degeneration, epiretinal membrane, macula hole, possible glaucomatous optic neuropathy, papilledema and optic nerve atrophy. The DLS was developed with 56 738 images and tested with 8176 images from one internal test set and two external test sets. The comparison with human doctors was also conducted.ResultsThe area under the receiver operating characteristic curves of the DLS on the internal test set and the two external test sets were 0.950 (95% CI 0.942 to 0.957) to 0.996 (95% CI 0.994 to 0.998), 0.931 (95% CI 0.923 to 0.939) to 1.000 (95% CI 0.999 to 1.000) and 0.934 (95% CI 0.929 to 0.938) to 1.000 (95% CI 0.999 to 1.000), with sensitivities of 80.4% (95% CI 79.1% to 81.6%) to 97.3% (95% CI 96.7% to 97.8%), 64.6% (95% CI 63.0% to 66.1%) to 100% (95% CI 100% to 100%) and 68.0% (95% CI 67.1% to 68.9%) to 100% (95% CI 100% to 100%), respectively, and specificities of 89.7% (95% CI 88.8% to 90.7%) to 98.1% (95%CI 97.7% to 98.6%), 78.7% (95% CI 77.4% to 80.0%) to 99.6% (95% CI 99.4% to 99.8%) and 88.1% (95% CI 87.4% to 88.7%) to 98.7% (95% CI 98.5% to 99.0%), respectively. When compared with human doctors, the DLS obtained a higher diagnostic sensitivity but lower specificity.ConclusionThe proposed DLS is effective in diagnosing normal fundus and 12 major fundus diseases, and thus has much potential for fundus diseases screening in the real world.
Aims To establish an automated method for identifying referable diabetic retinopathy (DR), defined as moderate nonproliferative DR and above, using deep learning‐based lesion detection and stage grading. Materials and Methods A set of 12,252 eligible fundus images of diabetic patients were manually annotated by 45 licenced ophthalmologists and were randomly split into training, validation, and internal test sets (ratio of 7:1:2). Another set of 565 eligible consecutive clinical fundus images was established as an external test set. For automated referable DR identification, four deep learning models were programmed based on whether two factors were included: DR‐related lesions and DR stages. Sensitivity, specificity and the area under the receiver operating characteristic curve (AUC) were reported for referable DR identification, while precision and recall were reported for lesion detection. Results Adding lesion information to the five‐stage grading model improved the AUC (0.943 vs. 0.938), sensitivity (90.6% vs. 90.5%) and specificity (80.7% vs. 78.5%) of the model for identifying referable DR in the internal test set. Adding stage information to the lesion‐based model increased the AUC (0.943 vs. 0.936) and sensitivity (90.6% vs. 76.7%) of the model for identifying referable DR in the internal test set. Similar trends were also seen in the external test set. DR lesion types with high precision results were preretinal haemorrhage, hard exudate, vitreous haemorrhage, neovascularisation, cotton wool spots and fibrous proliferation. Conclusions The herein described automated model employed DR lesions and stage information to identify referable DR and displayed better diagnostic value than models built without this information.
Purpose. To quantitatively explore the correlation between optical coherence tomography (OCT) parameters and vision impairment in patients with diabetic macular edema (DME). Methods. This study was a retrospective observational case series. One-hundred eyes from 66 patients with DME were retrospectively included. OCT parameters, including central macular thickness (CMT), height of intraretinal cystoid, subretinal fluid and sponge-like retinal swelling, density of hyperreflective foci (HRF), and integrity of the ellipsoidal zone (EZ), were assessed. Correlation analyses and multiple linear regression analysis were performed to quantitatively explore the relationship between best-corrected visual acuity (BCVA) and OCT parameters. Results. Among all OCT parameters, CMT, height of intraretinal cystoid, height of sponge-like retinal swelling, and density of HRF and EZ integrity were significantly correlated with BCVA (r = −0.550, −0.526, −0.411, −0.277, and −0.501, respectively; P<0.01). In multiple linear regression analysis, CMT, density of HRF, and EZ integrity fit a significant linear equation (β = 0.482, 0.184, and 0.447, respectively), with the adjusted R square reaching 0.522 (P<0.001). In eyes without SRF, the height of intraretinal cystoid, density of HRF, and EZ integrity were included in the model and an adjusted R square of 0.605 (P<0.001) was obtained. Conclusion. In DME eyes, OCT parameters, including the density of HRF, the EZ integrity together with CMT, or the height of intraretinal cystoid, could explain 52.2% to 60.5% of the variation in BCVA and were weighted approximately 2 : 1 : 2, respectively.
Purpose:To assess the accuracy and robustness of the AI algorithm for detecting referable diabetic retinopathy (RDR), referable macular diseases (RMD), and glaucoma suspect (GCS) from fundus images in community and in-hospital screening scenarios.MethodsWe collected two color fundus image datasets, namely, PUMCH (556 images, 166 subjects, and four camera models) and NSDE (534 images, 134 subjects, and two camera models). The AI algorithm generates the screening report after taking fundus images. The images were labeled as RDR, RMD, GCS, or none of the three by 3 licensed ophthalmologists. The resulting labels were treated as “ground truth” and then were used to compare against the AI screening reports to validate the sensitivity, specificity, and area under the receiver operating characteristic curve (AUC) of the AI algorithm.ResultsOn the PUMCH dataset, regarding the prediction of RDR, the AI algorithm achieved overall results of 0.950 ± 0.058, 0.963 ± 0.024, and 0.954 ± 0.049 on sensitivity, specificity, and AUC, respectively. For RMD, the overall results are 0.919 ± 0.073, 0.929 ± 0.039, and 0.974 ± 0.009. For GCS, the overall results are 0.950 ± 0.059, 0.946 ± 0.016, and 0.976 ± 0.025.ConclusionThe AI algorithm can work robustly with various fundus camera models and achieve high accuracies for detecting RDR, RMD, and GCS.
Background To investigate alterations in retinal microvasculature in eyes with preclinical diabetic retinopathy (DR) using ultra-wide field swept-source optical coherence tomography angiography (UWF SS OCTA). Methods Prospective cross-sectional study. Fifty-five eyes of 30 diabetic patients without clinical retinal signs were included. All subjects underwent OCTA examination with a 12 × 12 mm2 field of view of 5 visual fixations (1 central fixation and 4 peripheral fixations) to compose a UWF OCTA image. In the UWF images, the central area corresponded to the original central image obtained using central fixation, and the peripheral area was the remaining area. Lesions, including nonperfusion areas (NPAs), microvascular dilation and tortuosity, and neovascularization (NV), were recorded in different areas. Diabetes history was also recorded. Results Peripheral areas presented significantly more microvascular dilation and tortuosity than central areas (P = 0.024) and more NPAs than central areas, with borderline significance (P = 0.085). The number of lesion types was associated with HbA1c levels in the peripheral and overall areas (all P values < 0.001). Conclusions UWF SS OCTA is a promising imaging method for detecting vascular alterations in diabetic eyes without clinical signs to reveal retinal microvascular alterations. These alterations were correlated with systemic conditions.
Purpose: To evaluate microvascular alterations with optical coherence tomography angiography (OCTA) in eyes with non-arteritic anterior ischaemic optic neuropathy (NAION) and the unaffected fellow eyes. Design: Systematic review and meta-analysis. Methods: A comprehensive literature search was conducted in the PubMed and Embase databases through 6 September 2020, to identify the studies on NAION and the unaffected fellow eyes using OCTA. Eligible studies and data of interest were extracted and analysed by RevMan Software v. 5.4 and Stata Software v.14.0. The weighted mean differences and 95% confidence intervals were used to assess the strength of the association. Results: Seventeen observational comparative studies, including 379 eyes with NAION, 175 unaffected contralateral eyes and 470 eyes of healthy controls, were identified. Compared to those of the healthy controls, the perfusion density (PD) of radial peripapillary capillary (RPC) and peripapillary superficial capillary plexus (ppSCP) of NAION were significantly lower. Moreover, the PD of the macular SCP (mSCP) in NAION was significantly reduced in the whole image, superior quadrant and temporal quadrant, while the macular deep capillary plexus (mDCP) showed a decreasing PD only within the whole image. Between unaffected fellow eyes and healthy eyes, significant differences of PD were demonstrated in the whole image and some peripapillary regions of the RPC and ppSCP. Conclusion: Our results suggested that compared to those of healthy controls, the eyes affected by NAION and unaffected fellow eyes demonstrated significant microvascular impairments in different regions. Between acute and non-acute NAION, macular OCTA parameters showed different characteristic patterns.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.