A Study On The Diagnosis Method And Long-term Treatment Of Polypoid Choroidal Vasculopathy

Part I.Noninvasive multimodal imaging in diagnosing polypoidal choroidal vasculopathyPurpose:To investigate the diagnostic performance of noninvasive multimodal imaging methods in diagnosing polypoidal choroidal vasculopathy(PCV)and distinguishing PCV from typical neovascular age-related macular degeneration(nvAMD).Methods:Diagnostic study using retrospective data.Diagnostic test:Imaging features of noninvasive multimodal imaging methods,including fundus photography(FP),B-scan optical coherence tomography(OCT),en face OCT,OCT angiography,and autofluorescence,of 103 eyes with PCV or typical nvAMD were reviewed.Diagnostic strategy was established based on imaging features.Validation test:The diagnostic strategy was validated in other 105 eyes with PCV or typical nvAMD.Results:Features of subretinal orange nodule on FP,thumb-like pigment epithelium detachment(PED)on OCT,notched PED on OCT,bubble sign on OCT,and Bruch's membrane depression under serosanguinous PED on OCT were more common in PCV.When the diagnostic strategy of using at least 2 of 5 features was performed,there is 0.88 sensitivity and 0.92 specificity for diagnosing PCV.The results of the validation test further confirmed the diagnostic strategy with 0.94 sensitivity and 0.93 specificity.Conclusions:Noninvasive multimodal imaging,especially FP and B-scan OCT,provide high sensitivity and specificity for diagnosing PCV and distinguishing PCV from typical nvAMD,when at least 2 of 5 suggestive imaging features are present.Part II.Utility of artificial intelligence in diagnosis of polypoidal choroidal vasculopathyPurpose:To investigate the feasibility of training an artificial intelligence(AI)on a public-available AI platform to diagnose polypoidal choroidal vasculopathy(PCV)using indocyanine green angiography(ICGA)images.Methods:Two methods using AI models were trained with a data set including 430 ICGA images of normal,neovascular age-related macular degeneration(nvAMD),and PCV eyes on a public-available AI platform.The one-step method distinguished normal,nvAMD,and PCV images simultaneously.The two-step method identifies normal and abnormal ICGA images at the first step and diagnoses PCV from the abnormal ICGA images at the second step.The method with higher performance was used to compare with retinal specialists and ophthalmologic residents on the performance of diagnosing PCV.Results:The two-step method had better performance than the one-step method.Precision of the one-step method was 0.673,and the recall was 0.635.Of the two-step method,the precision was 0.911 and the recall was 0.911 at the first step,and the precision was 0.783,and the recall was 0.783 at the second step.For the test data set,the two-step method distinguished normal and abnormal images with an accuracy of 1 and diagnosed PCV with an accuracy of 0.83,which was comparable to retinal specialists and superior to ophthalmologic residents.Conclusions:In this evaluation of ICGA images from normal,nvAMD,and PCV eyes,the models trained on a public-available AI platform had comparable performance to retinal specialists for diagnosing PCV,which is helpful to improve the diagnostic accuracy in clinical practice.The utility of public-available AI platform might help everyone including ophthalmologists who had no AI-related resources,especially those in less developed areas,for future studies.Part ?.Six-Year Real-World Outcomes of Antivascular Endothelial Growth Factor Monotherapy and Combination Therapy for Various Subtypes of Polypoidal Choroidal VasculopathyPurpose:To compare 6-year visual outcomes of antivascular endothelial growth factor(anti-VEGF)monotherapy and initial combination therapy of photodynamic therapy(PDT)and anti-VEGF therapy for polypoidal choroidal vasculopathy(PCV)in a Chinese population and to investigate imaging biomarkers associated with visual outcomes.Methods:Retrospective study.Forty-eight treatment-naive PCV eyes of 46 patients were reviewed,which underwent anti-VEGF monotherapy or initial combination therapy.PCV was classified into 2 subtypes based on indocyanine green angiography and optical coherence tomography:polypoidal choroidal neovascularization and typical PC V.The visual outcomes and related imaging morphological features were compared between various treatment regimens and various subtypes.Results:No significant differences of mean best-corrected visual acuity(BCVA)changes were noticed between anti-VEGF monotherapy and combination therapy in either subtype 1 PCV or subtype 2 PCV during 6-year period(all P values>0.05).Compared with BCVA at baseline,the mean BCVA at 72 months deteriorated significantly in eyes with subtype 1 PCV(P<0.001),while the mean BCVA at 72 months remained stable in eyes with subtype 2 PCV(P=0.941).In subtype 2 PCV eyes with continuous retina pigment epithelium,the mean changes of BCVA in eyes treated with anti-VEGF monotherapy were better than those in eyes treated with combination therapy(P=0.020).Conclusions:Anti-VEGF monotherapy and combination therapy for various subtypes of PCV had comparable long-term visual outcomes in most cases in real world.Imaging biomarkers which correlate with visual outcomes and treatment response should be included in the classification of PCV and validated in real world furtherly.