ABSTRACT
AIM: To evaluate the clinical application value of the artificial intelligence assisted pathologic myopia (PM-AI) diagnosis model based on deep learning. METHODS: A total of 1156 readable color fundus photographs were collected and annotated based on the diagnostic criteria of Meta-pathologic myopia (PM) (2015). The PM-AI system and four eye doctors (retinal specialists 1 and 2, and ophthalmologists 1 and 2) independently evaluated the color fundus photographs to determine whether they were indicative of PM or not and the presence of myopic choroidal neovascularization (mCNV). The performance of identification for PM and mCNV by the PM-AI system and the eye doctors was compared and evaluated via the relevant statistical analysis. RESULTS: For PM identification, the sensitivity of the PM-AI system was 98.17%, which was comparable to specialist 1 (P=0.307), but was higher than specialist 2 and ophthalmologists 1 and 2 (P<0.001). The specificity of the PM-AI system was 93.06%, which was lower than specialists 1 and 2, but was higher than ophthalmologists 1 and 2. The PM-AI system showed the Kappa value of 0.904, while the Kappa values of specialists 1, 2 and ophthalmologists 1, 2 were 0.968, 0.916, 0.772 and 0.730, respectively. For mCNV identification, the AI system showed the sensitivity of 84.06%, which was comparable to specialists 1, 2 and ophthalmologist 2 (P>0.05), and was higher than ophthalmologist 1. The specificity of the PM-AI system was 95.31%, which was lower than specialists 1 and 2, but higher than ophthalmologists 1 and 2. The PM-AI system gave the Kappa value of 0.624, while the Kappa values of specialists 1, 2 and ophthalmologists 1 and 2 were 0.864, 0.732, 0.304 and 0.238, respectively. CONCLUSION: In comparison to the senior ophthalmologists, the PM-AI system based on deep learning exhibits excellent performance in PM and mCNV identification. The effectiveness of PM-AI system is an auxiliary diagnosis tool for clinical screening of PM and mCNV.
ABSTRACT
AIM: To evaluate the therapeutic effect of combined phacovitrectomy with membrane peeling and intraocular lens (IOL) implantation in patients with severe idiopathic epiretinal membrane (iERM) and concurrent cataract. METHODS: A total of 34 eyes from 34 patients who underwent phacovitrectomy and epiretinal membrane (ERM) peeling at the First Affiliated Hospital of Zhejiang University between 2015 and 2017. The best-corrected visual acuity (BCVA) and central foveal thickness (CFT) were measured preoperatively and at 1, 3, 6mo and 1y postoperatively. Temporal changes and bivariate correlations of these parameters were analyzed. RESULTS: Mean logMAR BCVA improved and CFT decreased significantly (P<0.001) until 6mo after surgery. Correlation analysis revealed a positive correlation between preoperative and postoperative logMAR BCVA (r=0.716, P<0.001 at 1mo, r=0.417, P=0.014 at 3mo, r=0.359, P=0.037 at 6mo, and r=0.369, P=0.032 at 12mo post-op respectively), but preoperative CFT was neither associated with postoperative CFT nor with postoperative logMAR BCVA. There was a positive correlation between CFT and logMAR BCVA at 1mo (r=0.346, P=0.045), 6mo (r=0.347, P=0.045), and 12mo (r=0.342, P=0.048) post-operatively. The intra- and postoperative complications were relatively mild, and the incidences were generally low. CONCLUSION: For severe iERM patients with significant visual symptoms, combined phacovitrectomy with membrane peeling and IOL implantation is safe and effective in improving BCVA and decreasing CFT. Early surgery in selected patients may help preserving better visual function.
ABSTRACT
As cataract occurs frequently in patients with glaucoma, combining phacoemulsification and endoscopic cyclophotocoagulation has been gaining attention recently due to its minimally invasive nature. A variety of studies had evaluated the efficacy and safety of this procedure and had shown extremely promising results. This review article has shown here that combined phacoemulsification and endoscopic cyclophotocoagulation procedure could effectively reduce intraocular pressure in medically uncontrolled glaucoma patients while avoiding serious complications associated with traditional cyclophotocoagulation procedure and adverse effects related to filtering surgery such as trabeculectomy.
ABSTRACT
To explore whether the complement factor H (CFH) polymorphism rs1061170/Y402H is associated with responsiveness to antivascular endothelial growth factor (VEGF) agents in age-related macular degeneration (AMD). We reviewed the English literature to examine the association between the polymorphism rs1061170/Y402H of the CFH gene and responsiveness to treatment with anti-VEGF drugs in AMD patients. A meta-analysis of eligible studies was also performed. Pooled odds ratios (ORs) and 95% CIs were estimated using Stata V.12.0. Statistical heterogeneity was measured using Q-statistic testing. Fourteen relevant studies including a total of 2963 AMD patients were eligible. In AMD patients without a treatment history, individuals carrying the rs1061170/Y402H TT genotype were more likely to achieve a better outcome (OR = 1.932, 95% CI = 1.125-3.317, p = 0.017) than those carrying the CC genotype. The polymorphism rs1061170/Y402H might be a genetic predictor of treatment response to anti-VEGF therapy in AMD patients. Further prospective research including a larger number of patients is needed to validate this finding.
