ObjectiveTo establish an artificial intelligence robot-assisted diagnosis system for fundus diseases based on deep learning optical coherence tomography (OCT) and evaluate its application value. MethodsDiagnostic test studies. From 2016 to 2019, 25 000 OCT images of 25 000 patients treated at the Eye Center of the Second Affiliated Hospital of Zhejiang University School of Medicine were used as training sets and validation sets for the fundus intelligent assisted diagnosis system. Among them, macular epiretinal membrane (MERM), macular edema, macular hole, choroidal neovascularization (CNV), and age-related macular degeneration (AMD) were 5 000 sheets each. The training set and the verification set are 18 124 and 6 876 sheets, respectively. Through the transfer learning Attention ResNet structure algorithm, the OCT image was characterized by lesion identification, the disease feature was extracted by a specific procedure, and the given image was distinguished from other types of disease according to the statistical characteristics of the target lesion. The model algorithms of MERM, macular edema, macular hole, CNV and AMD were initially formed, and the fundus intelligent auxiliary diagnosis system of five models was established. The performance of each model-assisted diagnosis in the fundus intelligent auxiliary diagnostic system was evaluated by applying the subject working characteristic curve, area under the curve (AUC), sensitivity, and specificity. ResultsWith the intelligent auxiliary diagnosis system, the diagnostic sensitivity of the MERM was 93.5%, the specificity was 99.23%, and AUC was 0.983 7; the diagnostic sensitivity of macular edema was 99.02%, the specificity was 98.17%, and AUC was 0.994 6; the diagnostic sensitivity of macular hole was 98.91%, the specificity was 99.91%, AUC was 0.996 2; the diagnostic sensitivity of CNV was 97.54%, the specificity was 94.71%, AUC was 0.987 5; the diagnostic sensitivity of AMD was 95.12%, the specificity was 97.09%, AUC was 0.985 3. ConclusionsThe artificial intelligence robot-assisted diagnosis system for fundus diseases based on deep learning for OCT images has accurate and efficient diagnostic performance for assisting the diagnosis of MERM, macular edema, macular hole, CNV, and AMD.
Objective To investigate the correlation between systemic immune inflammatory index (SII) and other metabolic indicators and diabetic epiretinal membranes (dERM). MethodsA retrospective case-control study. From March 2022 to July 2023, 81 patients (81 eyes) with dERM in Department of Ophthalmology, Affiliated Jinhua Hospital of Zhejiang University of Medicine School diagnosed by fundus screening were included in the study. A total of 81 patients (81 eyes) with diabetes who were matched in age, gender, and duration of diabetes and had no dERM or diabetic macular edema in both eyes during fundus screening were selected as the control group. All patients underwent optical coherence tomography (OCT) examination and laboratory tests for peripheral blood neutrophil, lymphocyte, platelet counts, serum albumin, blood lipids, uric acid, and glycosylated hemoglobin (HbA1c). SII was calculated. Random urine samples were collected for urinary albumin/creatinine ratio (ACR) testing. The OCT device's own analysis software obtained the macular volume coefficient, including central foveal thickness (CMT), macular volume, and average macular thickness. The macular volume coefficient, SII, serum albumin, blood lipids, uric acid, HbA1c, and ACR between the two groups were compared using paired t tests or Mann-Whitney U tests. Conditional logistic regression analysis was performed to evaluate the risk factors for dERM; Spearman correlation test was used to analyze the correlation between CMT, SII, ACR, disorganization of retinal inner layers (DRIL), intraretinal cyst (IRC), and hyper-reflective foci (HRF) in patients with dERM. ResultsThere were significant differences in CMT, macular volume, average macular thickness, SII, serum albumin, and ACR between the dERM group and the control group (Z=−7.234, −6.306, −6.400, −3.063, −2.631, −3.868; P＜0.05). Conditional logistics regression analysis showed that high SII [odds ratio (OR)= 3.919, 95% confidence interval (CI) 1.591-9.654, P=0.003] and ACR (OR=4.432, 95%CI 1.885-10.420, P=0.001) were risk factors for dERM. Spearman correlation analysis showed that HRF, IRC, DRIL were positively correlated with CMT (Rs=0.234, 0.330, 0.248; P=0.036, 0.003, 0.026); HRF was positively correlated with SII and ACR (Rs=0.233, 0.278; P=0.036, 0.012). ConclusionElevated SII and ACR are independent risk factors for the occurrence of dERM.