No abstract

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.

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.

No abstract

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.

PurposeTo describe the ocular clinical features, histopathological findings, and treatment outcomes of lymphomas involving the ciliary body.MethodsWe demonstrate three cases of ciliary body involvement by lymphoma from 2013 to 2019 in Peking Union Medical College Hospital (PUMCH). All patients underwent examinations including best corrected visual acuity (BCVA), slit-lamp microscopy, indirect ophthalmoscope, ultrasound biomicroscopy (UBM), and diagnostic vitrectomy. In addition, cytopathology, immunohistochemistry, gene rearrangement, cytometric immunophenotypic, or in-situ hybridization were used for determining the pathological type of lymphoma.ResultsThe patients were a 25-year-old man, a 52-year-old woman, and a 54-year-old man. Two patients had unilateral involvement, and one patient had bilateral involvement. All patients presented with anterior uveitis and elevated intraocular pressure. Ciliary body masses or infiltration were found in 3 patients. Two patients had diffuse large B-cell lymphoma and one patient had natural killer/T-cell lymphoma. All patients received 0.4 mg methotrexate intravitreal injections, and the ciliary body lesions regressed completely.ConclusionLymphomatous involvement of the ciliary body usually presents as an atypical anterior chamber reaction. Vitreous biopsy should be considered in these patients for diagnosis. Methotrexate intravitreal injection combine with chemotherapy or radiotherapy, might extend the survival time and preserve visual acuity for patients with ciliary body involvement by lymphoma.