Automated detection of severe diabetic retinopathy using deep learning method.

PURPOSE: The purpose of this study is to develop and validate the intelligent diagnosis of severe DR with lesion recognition based on color fundus photography. METHODS: The Kaggle public dataset for DR grading is used in the project, including 53,576 fundus photos in the test set, 28,101 in the training set, and 7,025 in the validation set. We randomly select 4,192 images for lesion annotation. Inception V3 structure is adopted as the classification algorithm. Both 299 × 299 pixel images and 896 × 896 pixel images are used as the input size. ROC curve, AUC, sensitivity, specificity, and their harmonic mean are used to evaluate the performance of the models. RESULTS: The harmonic mean and AUC of the model of 896 × 896 input are higher than those of the 299 × 299 input model. The sensitivity, specificity, harmonic mean, and AUC of the method with 896 × 896 resolution images as input for severe DR are 0.925, 0.907, 0.916, and 0.968, respectively. The prediction error mainly occurs in moderate NPDR, and cases with more hard exudates and cotton wool spots are easily predicted as severe cases. Cases with preretinal hemorrhage and vitreous hemorrhage are easily identified as severe cases, and IRMA is the most difficult lesion to recognize. CONCLUSIONS: We have studied the intelligent diagnosis of severe DR based on color fundus photography. This artificial intelligence-based technology offers a possibility to increase the accessibility and efficiency of severe DR screening.

Deep learning-based detection and stage grading for optimising diagnosis of diabetic retinopathy.

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.

Ultra-wide field swept-source optical coherence tomography angiography in patients with diabetes without clinically detectable retinopathy.

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.

Clinical efficacy of optical coherence tomography in sellar mass lesions: a meta-analysis.

PURPOSE: Although optical coherence tomography (OCT) of the eyes has been studied to detect and monitor sellar masses, there is no recommendation for selecting the most effective measurement of OCT in clinical practice. Thus, we conducted a meta-analysis to examine the efficacy of OCT in sellar mass lesions. METHODS: We conducted a literature search in PubMed and EMBASE through April 26, 2020. The primary outcomes were the thickness of the peripapillary retinal nerve fiber layer (pRNFL) and the macular ganglion cell complex (mGCC). The secondary outcomes included the thickness of the macular ganglion cell and inner plexiform layer (mGCIPL) and macular thickness. Random-effects models were used in all meta-analyses. Additionally, we conducted meta-regressions and subgroup analyses. RESULTS: We included 22 studies, involving 1347 eyes of patients and 1198 eyes of controls. When compared with the control group, the reductions in pRNFL, mGCC and macular thickness in the patient group were significantly different, whereas significant thinning of the mGCIPL was restricted to the nasal hemiretina. Furthermore, we found that before visual field (VF) defects occurred, significant thinning of the pRNFL and mGCC thickness could be detected by OCT. The change in OCT parameters also showed different patterns in different types of pituitary adenomas. CONCLUSIONS: Sellar mass lesions were associated with the changes in OCT measurements. The characteristic patterns of the OCT parameters may refine the diagnostic accuracy. Moreover, the alterations of OCT metrics before VF defects indicate the efficacy of OCT in early detection. Different types of pituitary adenomas may vary in OCT measurements, and their specific features warrant further research efforts.

Efficacy of intracameral preservative-free triamcinolone acetonide in pediatric cataract surgery: a meta-analysis.

PURPOSE: The aim of this study is to evaluate the efficacy of intracameral preservative-free triamcinolone acetonide (TA) on reducing inflammatory reactions after pediatric cataract surgery. METHODS: Researches were comprehensively searched in PubMed, Embase, and the Cochrane Central Register of Controlled Trials up to 30 November, 2019. Data of interest were extracted and analyzed by Review Manager 5.2. The primary outcome was cell deposits. The secondary outcomes included posterior synechias, fibrinous anterior chamber reaction, visual axis obscuration, and posterior capsule opacification. The odds ratio (OR), weight mean difference (WMD), and their 95% confidence intervals (95% CI) were used to assess the strength of the association. RESULTS: In total, 45 articles were obtained. Finally, 5 studies with a total of 308 eyes were enrolled in this meta-analysis. Among these, 134 eyes underwent intracameral TA treatment and 174 eyes did not. In intracameral TA treatment group, the incidence of cell deposits (OR = 0.35, 95% CI 0.16-0.76, P = 0.008), posterior synechias (OR = 0.44, 95% CI 0.23-0.86, P = 0.02), and fibrinous anterior chamber reaction (OR = 0.12, 95% CI 0.01-1.05, P = 0.05) were lower compared to those in patients without intracameral TA treatment. Meanwhile, the incidence of visual axis obscuration (OR = 0.10, 95% CI 0.01-0.85, P = 0.04) and posterior capsule opacification (OR = 0.09, 95% CI 0.02-0.55, P = 0.009) were also reduced significantly. The intraocular pressure (IOP) was evaluated at the first month postoperatively (WMD = 0.84 mmHg, 95% CI 0.14-1.53, P = 0.02), but within the normal range. There was no difference of IOP between two groups at 6 months or above after operation (P = 0.93). CONCLUSIONS: The intracameral preservative-free TA in pediatric cataract surgery contributed to much less inflammatory reaction with the normal IOP range.

Efficacy of mineralocorticoid receptor antagonist for central serous chorioretinopathy: a meta-analysis.

PURPOSE: To evaluate the efficacy of mineralocorticoid receptor antagonist (MRA) for patients with central serous chorioretinopathy (CSCR). METHODS: The Pubmed, Embase, and the Cochrane Central Register of Controlled Trials were comprehensively searched up to February 2020, to identify the studies comparing the efficacy of MRA with placebo/observation or photodynamic therapy (PDT) for CSCR. The primary outcomes were maximal subretinal fluid height and central macular thickness (CMT). The secondary outcomes included subfoveal choroidal thickness (SFCT) and best-corrected visual acuity (BCVA). Data of interest were extracted and analyzed by R version 3.6.0. The weighted mean difference and their 95% confidence intervals were used to assess the strength of the association. RESULTS: Ten studies including 284 affected eyes were involved, with 168 undergoing MRA treatment, 60 taking placebo/observation, and 56 receiving PDT. The pooling results showed that MRA was significantly more effective in resolving maximal subretinal fluid height (P < 0.01) and diminishing CMT (P < 0.01) than placebo/observation, while PDT could achieve significantly better CMT reduction than MRA (P = 0.03). For BCVA improvement and SFCT reduction, no statistical difference was detected among the groups of MRA, observation, placebo, or PDT (P > 0.05). CONCLUSION: MRA is an effective therapy for the management of CSCR, which is only slightly inferior to PDT in terms of CMT reduction. For patients who could not afford PDT, MRA could function as an alternative treatment with acceptable efficacy and safety.

Microvascular alterations detected by optical coherence tomography angiography in non-arteritic anterior ischaemic optic neuropathy: a meta-analysis.

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.

Validating automated eye disease screening AI algorithm in community and in-hospital scenarios.

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. Methods: We 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. Results: On 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. Conclusion: The AI algorithm can work robustly with various fundus camera models and achieve high accuracies for detecting RDR, RMD, and GCS.

Development and evaluation of a deep learning model for the detection of multiple fundus diseases based on colour fundus photography.

AIM: To explore and evaluate an appropriate deep learning system (DLS) for the detection of 12 major fundus diseases using colour fundus photography. METHODS: Diagnostic 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. RESULTS: The 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. CONCLUSION: The 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.

Case Report: Ocular Manifestations and Treatments of Ciliary Body Involvement by Lymphoma.

PURPOSE: To describe the ocular clinical features, histopathological findings, and treatment outcomes of lymphomas involving the ciliary body. METHODS: We 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. RESULTS: The 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. CONCLUSION: Lymphomatous 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.

Early Detection of Microvascular Impairments With Optical Coherence Tomography Angiography in Diabetic Patients Without Clinical Retinopathy: A Meta-analysis.

PURPOSE: To evaluate microvascular impairments with optical coherence tomography angiography (OCTA) in the eyes of diabetic patients with no diabetic retinopathy (NDR). DESIGN: Systematic review and meta-analysis. METHODS: The PubMed and Embase databases were comprehensively searched to identify studies comparing the microvascular changes between diabetic eyes without clinical retinopathy and healthy controls using OCTA. Data of interest were extracted and analyzed by Review Manager V.5.3 and Stata V.14.0. The weighted mean differences and their 95% confidence intervals were used to assess the strength of the association. RESULTS: Forty-five cross-sectional studies involving 2241 diabetic and 1861 healthy eyes were ultimately included. OCTA unambiguously revealed that compared with the healthy control group, the NDR group manifested enlarged areas and increased perimeters of the foveal avascular zone, with decreased perfusion density (PD) in both superficial and deep capillary plexus of the macula (except parafoveal PD of the inner retina and foveal PD) and reduced radial peripapillary capillary PD. In addition, subgroup analyses according to the type of diabetes mellitus indicated that most of those differences became nonsignificant (except parafoveal PD in the deep capillary plexus) in type 1 diabetes mellitus, while in type 2 diabetes mellitus they remained statistically significant. CONCLUSION: Our results suggested that retinal microvascular impairments might have occurred antecedent to clinically visible diabetic retinopathy and could be detected early by OCTA. However, those manifestations could be inconsistent according to the types of diabetes mellitus.

Optical Coherence Tomography Parameters Related to Vision Impairment in Patients with Diabetic Macular Edema: A Quantitative Correlation Analysis.

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 (ß = 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.