ObjectiveTo observe and explore the fundus characteristics and fundus fluorescein angiography of familial exudative vitreoretinopathy (FEVR) in different stages. MethodsA total of 15 patients (23 eyes) diagnosed as FEVR in the West China Hospital of Sichuan University from January 2007 to November 2013 were included. Clinical data and reports of fundus exams and fundus fluorescein angiography (FFA) were retrospectively analyzed. ResultsOne eye (4.35%) was classified as stage Ⅰ, 10 eyes (43.48%) were classified as stage Ⅱ, 8 eyes (34.78%) were classified as stage Ⅲ, and 1 eye (4.35%) and 3 eyes (13.04%) were classified as stage Ⅳ and V, respectively. The outcomes of fundus exams showed that the number of peripheral retinal blood vessels increased, and vessels straightened as well as narrowed, especially in the temporal area. FFA showed blood vessels suddenly shut in the equatorial retina and peripheral non-perfusion areas were observed. ConclusionTypical fundus characteristics and fundus fluorescein angiography changes of FEVR can be observed in different stages. Comprehensive fundus exams and family history are helpful to confirm relevant diagnosis.
ObjectiveTo conduct an objective record of stroke patient’s retinal diseases by retinal photography, and analyze the incidence of various retinal diseases between different subtypes of stroke.MethodsFrom June to October 2007, the consecutive cases of stroke admitted to the Department of Neurology, West China Hospital of Sichuan University were prospectively registered. Ischemic stroke patients were classified into different subtypes by the Oxfordshire Community Stroke Project criteria, and intracerebral hemorrhage (ICH) patients were classified based on the clinical manifestation and neuroimaging. We collected other clinical data associated with the incidence of stroke. The retinal abnormalities including retinopathy, arteriovenous nicking and arteriolar narrowing were recorded. Multivariate logistic regression was performed to investigate the relationship between retinal abnormalities and stroke.ResultsThis study included 199 patients with ischemic stroke and 95 patients with ICH. Among the patients with ischemic stroke, 43 (21.6%) had retinopathy, 52 (26.1%) presented with arteriovenous nicking, and 43 (21.6%) developed arteriolar narrowing. Among the patients with ICH, retinopathy occurred in 23 (24.2%), arteriovenous nicking occurred in 14 (14.7%), and arteriolar narrowing occurred in 25 (26.3%). In multivariate analysis, retinopathy was independently associated with partial anterior circulation infarct (PACI) (P=0.029) and anterior ICH (P=0.041).ConclusionsRetinopathy is independently associated with PACI and anterior ICH. Further community-based study with large sample should be conducted to confirm the predictive value of retinal diseases on the incidence of anterior stroke.
ObjectiveTo compare the imaging characteristics and detection of various types of lesions in diabetic retinopathy (DR) with colorful laser scanning fundus imaging (MSLI) and traditional color fundus photography (CFP).MethodsProspective case series observational study. A total of 38 eyes of 38 patients with DR diagnosed by clinical examination were included in the study. Among them, 21 were male and 17 were female; the mean age was 62.6±11.2 years; the average duration of diabetes was 14.3±7.5 years. All the patients were performed CFP, MSLI, frequency domain optical coherence tomography (SD-OCT), fluorescein angiography (FFA) examination. Using the Helielberg Spectralis HRA+OCT MSLI inspection, one scan simultaneously obtained 488 nm blue reflection (BR), 515 nm green light reflection (GR), 820 nm infrared light reflection (IR), and multicolor image (MC). The detection of traditional CFP and MC on microaneurysm (MA), hard exudation (HEX), cotton plaque (CWS), intraretinal hemorrhage (IRH), intraretinal microvascular abnormality (IRMA), venous bead (VB), venous ring (VL), macular edema (DME), macular anterior membrane (MEM) and laser photocoagulation (LB) were comparatively observed. The results of FFA examination were used as the diagnostic criteria for lesions. SD-OCT was used to determine the location and depth of lesions and the diagnostic reference for DME and MEM.ResultsThe numbers of eyes with MA (χ2=10.460), DME (χ2=4.006), MEM (χ2=4.444) was significantly higher in MC than that of traditional CFP. But the number of eyes with IRH (χ2=0.103), CWS (χ2=1.515), HEX (χ2=0.227), IRMA (χ2=0.051), VB (χ2=0.001), VL (χ2=0.149), VH (χ2=0.693) and LB (χ2=0.720) were not statistically significant between two methods (P>0.05). The imaging quality of MSLI mode is obviously better than that of traditional CFP. Among them, GR imaging shows the best structural changes of superficial retina in MA, CWS, HEX, MEM, etc. IR imaging shows clear depth in deep retina such as LB. DME was green on MC and the weak low-reflection dark area was visible on the IR image, which were consistent with the DME range indicated by the SD-OCT examination.ConclusionsCompared with the traditional CFP, the MSLI can clearly show the DR lesion. The number of checkouts is high on MA, DME and MEM by MC image.
Diabetic retinopathy (DR) is one of the most common causes of visual impairment and blindness in diabetic patients. It is particularly important to set up simpler, safer, non-invasive and highly effective methods for diagnosis as well as monitoring DR. A variety of new fundus imaging techniques show great advantages in early diagnosis, treatment and monitoring of DR in recent years. The main characteristics of wide-field scanning laser imaging system is achieving a large range of retinal image in a single photograph and without mydriasis. It provides several options for color images, FFA and FAF, which satisfy to detect the retina, choroid and vascular structure. Multi spectral fundus imaging system is suitable for DR screening, because it is able to recognize the typical characteristics of DR, such as microaneurysms, hemorrhage and exudation, and is non-invasive and convenient. OCT angiography is a quantitative examination that provides foveal avascular zone area, macular blood flow density, which provides strong evidence for DR diagnosis. The improvement of these new techniques will help us to build up a personalized evaluation system of DR.
ObjectiveTo compare the consistency of artificial analysis and artificial intelligence analysis in the identification of fundus lesions in diabetic patients.MethodsA retrospective study. From May 2018 to May 2019, 1053 consecutive diabetic patients (2106 eyes) of the endocrinology department of the First Affiliated Hospital of Zhengzhou University were included in the study. Among them, 888 patients were males and 165 were females. They were 20-70 years old, with an average age of 53 years old. All patients were performed fundus imaging on diabetic Inspection by useing Japanese Kowa non-mydriatic fundus cameras. The artificial intelligence analysis of Shanggong's ophthalmology cloud network screening platform automatically detected diabetic retinopathy (DR) such as exudation, bleeding, and microaneurysms, and automatically classifies the image detection results according to the DR international staging standard. Manual analysis was performed by two attending physicians and reviewed by the chief physician to ensure the accuracy of manual analysis. When differences appeared between the analysis results of the two analysis methods, the manual analysis results shall be used as the standard. Consistency rate were calculated and compared. Consistency rate = (number of eyes with the same diagnosis result/total number of effective eyes collected) × 100%. Kappa consistency test was performed on the results of manual analysis and artificial intelligence analysis, 0.0≤κ＜0.2 was a very poor degree of consistency, 0.2≤κ＜0.4 meant poor consistency, 0.4≤κ＜0.6 meant medium consistency, and 0.6≤κ＜1.0 meant good consistency.ResultsAmong the 2106 eyes, 64 eyes were excluded that cannot be identified by artificial intelligence due to serious illness, 2042 eyes were finally included in the analysis. The results of artificial analysis and artificial intelligence analysis were completely consistent with 1835 eyes, accounting for 89.86%. There were differences in analysis of 207 eyes, accounting for 10.14%. The main differences between the two are as follows: (1) Artificial intelligence analysis points Bleeding, oozing, and manual analysis of 96 eyes (96/2042, 4.70%); (2) Artificial intelligence analysis of drusen, and manual analysis of 71 eyes (71/2042, 3.48%); (3) Artificial intelligence analyzes normal or vitreous degeneration, while manual analysis of punctate exudation or hemorrhage or microaneurysms in 40 eyes (40/2042, 1.95%). The diagnostic rates for non-DR were 23.2% and 20.2%, respectively. The diagnostic rates for non-DR were 76.8% and 79.8%, respectively. The accuracy of artificial intelligence interpretation is 87.8%. The results of the Kappa consistency test showed that the diagnostic results of manual analysis and artificial intelligence analysis were moderately consistent (κ=0.576, P＜0.01).ConclusionsManual analysis and artificial intelligence analysis showed moderate consistency in the diagnosis of fundus lesions in diabetic patients. The accuracy of artificial intelligence interpretation is 87.8%.
ObjectiveTo analyze the distribution characteristics of peripheral retinopathy in Chinese patients with diabetic retinopathy (DR).MethodsA cross-sectional study. From January to December 2019, 265 cases of 388 eyes of DR patients diagnosed in the eye examination of Guangdong Provincial People's Hospital were included in the study. Among them, there were 211 eyes in 148 males and 177 eyes in 117 females; the average age was 58.4±12.3 years. Ultra-wide-angle fundus imaging (UWF) examination was performed by Daytona in Aalborg, UK. Use Photoshop to simulate the standard 7-azimuth (S7F) area, which was used as the central retinal area 1-7. The peripheral retinal areas 3-7 (P3-P7) were the adjacent peripheral retinal areas of the central retinal area 3-7, respectively. Divided DR into peripheral lesion predominant type (PPL) and central lesion predominant type (PCL). PPL was defined as at least one peripheral retinal area with more severe disease than its adjacent central area. χ2 test was performed on the difference of PPL composition ratio in each retinal area of eyes with different DR stages.ResultsAmong 388 eyes, 200 eyes were PPL (51.5%, 200/388). Compared of PPL composition ratios of eyes with different stages of DR, mild non-proliferative DR (NPDR), moderate NPDR, severe NPDR and proliferative DR were 32 (36.8%, 32/87), 89 (55.3%, 89/161)), 42 (51.9%, 42/81), 37 (62.6%, 37/59), the difference was statistically significant (χ2=11.440, P=0.010). Comparison of the distribution of PPL in each retinal area in DR eyes: in 200 PPL eyes, areas 3, 4, 5, 6, and 7 have 87, 101, 78, 67, and 38 eyes, respectively. The distribution of PPL in each retinal area in DR eyes was compared, and the difference was statistically significant (χ2=37.640, P＜0.001).ConclusionsPPL accounts for 51.5% of the eyes with DR. The DR stage are more severe, the proportion of PPL is higher. The temporal retinal peripheral lesions are the most common.
ObjectiveTo build a small-sample ultra-widefield fundus images (UWFI) multi-disease classification artificial intelligence model, and initially explore the ability of artificial intelligence to classify UWFI multi-disease tasks. MethodsA retrospective study. From 2016 to 2021, 1 608 images from 1 123 patients who attended the Eye Center of the Renmin Hospital of Wuhan University and underwent UWFI examination were used for UWFI multi-disease classification artificial intelligence model construction. Among them, 320, 330, 319, 268, and 371 images were used for diabetic retinopathy (DR), retinal vein occlusion (RVO), pathological myopia (PM), retinal detachment (RD), and normal fundus images, respectively. 135 images from 106 patients at the Tianjin Medical University Eye Hospital were used as the external test set. EfficientNet-B7 was selected as the backbone network for classification analysis of the included UWFI images. The performance of the UWFI multi-task classification model was assessed using the receiver operating characteristic curve, area under the curve (AUC), sensitivity, specificity, and accuracy. All data were expressed using numerical values and 95% confidence intervals (CI). The datasets were trained on the network models ResNet50 and ResNet101 and tested on an external test set to compare and observe the performance of EfficientNet with the 2 models mentioned above. ResultsThe overall classification accuracy of the UWFI multi-disease classification artificial intelligence model on the internal and external test sets was 92.57% (95%CI 91.13%-92.92%) and 88.89% (95%CI 88.11%-90.02%), respectively. These were 96.62% and 92.59% for normal fundus, 95.95% and 95.56% for DR, 96.62% and 98.52% for RVO, 98.65% and 97.04% for PM, and 97.30% and 94.07% for RD, respectively. The mean AUC on the internal and external test sets was 0.993 and 0.983, respectively, with 0.994 and 0.939 for normal fundus, 0.999 and 0.995 for DR, 0.985 and 1.000 for RVO, 0.991 and 0.993 for PM and 0.995 and 0.990 for RD, respectively. EfficientNet performed better than the ResNet50 and ResNet101 models on both the internal and external test sets. ConclusionThe preliminary UWFI multi-disease classification artificial intelligence model using small samples constructed in this study is able to achieve a high accuracy rate, and the model may have some value in assisting clinical screening and diagnosis.
Objective To observe the change of retinal artery angle in eyes with idiopathic epiretinal membrane (ERM) and to analyze the relationship between retinal artery angle, ERM classification based on optical coherence tomography (OCT), and visual acuity. MethodsA retrospective cross-sectional clinical study. A total of 187 eyes in 187 patients diagnosed with monocular idiopathic ERM (IERM group) in Department of Ophthalmology of Zhejiang Provincial People's Hospital and the Affiliated Eye Hospital of Wenzhou Medical University at Hangzhou from November 2018 to January 2023 were included in the study. The contralateral healthy eyes were included as the control group. All patients underwent best corrected visual acuity (BCVA), fundus photography, spectral-domain OCT, OCT angiography (OCTA) and axial length (AL) measurement. BCVA examination was performed using the standard logarithmic visual acuity chart, which was converted to the logarithm of the minimum angle of resolution (logMAR) visual acuity. The foveal avascular zone (FAZ) area was measured by OCTA. The central macular thickness (CMT) was measured by spectral domain OCTaccording to the grading criteria of ectopic inner foveal layer (EIFL) was divided into stages 1 to 4 with 42, 45, 62, and 38 eyes, and the IERM group was subdivided into stage 1, stage 2, stage 3, and stage 4 groups accordingly. Image J was used to measure the retinal artery angle and the 1/2 retinal artery angle on fundus images. Multiple linear regression analysis was used to analyze the correlation between BCVA and artery angle, 1/2 artery Angle, CMT, FAZ area and AL. ResultsCompared with the control group, eyes in IERM group had worse BCVA (t=9.727), thicker CMT (t=12.452), smaller FAZ area (t=－14.329), smaller artery angle (t=－9.165) and smaller 1/2 artery angle (t=－9.549). The differences were statistically significant (P＜0.001). With the increase of IERM stage, the artery angle and 1/2 artery angle decreased significantly (F=21.763, 12.515; P＜0.001). There was no significant difference in artery angle and 1/2 artery angle between stage 1 group and stage 2 group, and 1/2 arterial angle between stage 2 group and stage 3 group (P＞0.05). There were significant differences in artery angle and 1/2 artery angle between the other groups (P＜0.05). There were significant differences in CMT and logMAR BCVA among different classification subgroups in IERM groups (P＜0.05). There was no significant difference in FAZ area between grade 3 group and grade 4 group (P＞0.05). There were significant differences in FAZ area between the other groups (P＜0.05). Correlation analysis showed that decreased artery angle (P=0.013) and increased CMT (P＜0.001) were associated with decreased BCVA. ConclusionsCompared with healthy eyes, the artery angle decreases significantly with the increase of ERM stage. Decreased retinal artery angle is associated with decreased visual acuity in IERM eyes.