Purpose: To predict improvement of best corrected visual acuity(BCVA) 1 year after pars plana vitrectomy (PPV) for epiretinal membrane(ERM) using artificial intelligence(AI) methods on optical coherence tomography(OCT) B-scan images. Methods: Four-hundred eleven(411) patients with stage II ERM were divided in a group improvement(IM)(≥ 15 ETDRS letters of VA recovery)and a group no improvement(N-IM)(<15 letters)according to 1-year VA improvement after 25 G PPV with internal limiting membrane(ILM) peeling.Primary outcome was the creation of a deep learning classifier(DLC) based on OCT B-scan images for prediction.Secondary outcome was assessment of the influence of various clinical and imaging predictors on BCVA improvement. Inception-ResNet-V2 was trained using standard augmentation techniques.Testing was performed on an external dataset.For secondary outcome, B-scan acquisitions were analyzed by graders both before and after fibrillary changes(FC) processing-enhancement. Results: The overall performance of the DLC showed a sensitivity of 87.3% and a specificity of 86.2%. Regression analysis showed a difference in preoperative images prevalence of ectopic inner foveal layer (EIFL),foveal detachment,ellipsoid zone(EZ) interruption, cotton wool sign, unprocessed FC(OR=2.75(CI 2.49-2.96)) and processed FC(OR=5.42(CI 4.81-6.08)) while preoperative BCVA and central macular thickness(CMT) didn't differ between groups. Conclusions: The DLC showed high performances in predicting 1-year visual outcome in ERM surgery patients. FC should also be considered as relevant predictors.

New artificial intelligence analysis for prediction of long-term visual improvement after epiretinal membrane surgery

Kilian, Raphael;Rizzo, Clara;
2022-01-01

Abstract

Purpose: To predict improvement of best corrected visual acuity(BCVA) 1 year after pars plana vitrectomy (PPV) for epiretinal membrane(ERM) using artificial intelligence(AI) methods on optical coherence tomography(OCT) B-scan images. Methods: Four-hundred eleven(411) patients with stage II ERM were divided in a group improvement(IM)(≥ 15 ETDRS letters of VA recovery)and a group no improvement(N-IM)(<15 letters)according to 1-year VA improvement after 25 G PPV with internal limiting membrane(ILM) peeling.Primary outcome was the creation of a deep learning classifier(DLC) based on OCT B-scan images for prediction.Secondary outcome was assessment of the influence of various clinical and imaging predictors on BCVA improvement. Inception-ResNet-V2 was trained using standard augmentation techniques.Testing was performed on an external dataset.For secondary outcome, B-scan acquisitions were analyzed by graders both before and after fibrillary changes(FC) processing-enhancement. Results: The overall performance of the DLC showed a sensitivity of 87.3% and a specificity of 86.2%. Regression analysis showed a difference in preoperative images prevalence of ectopic inner foveal layer (EIFL),foveal detachment,ellipsoid zone(EZ) interruption, cotton wool sign, unprocessed FC(OR=2.75(CI 2.49-2.96)) and processed FC(OR=5.42(CI 4.81-6.08)) while preoperative BCVA and central macular thickness(CMT) didn't differ between groups. Conclusions: The DLC showed high performances in predicting 1-year visual outcome in ERM surgery patients. FC should also be considered as relevant predictors.
artificial intelligence , deep learning , epiretinal membrane , fibrillary changes , optical coherence tomography
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11562/1080688
Citazioni
  • ???jsp.display-item.citation.pmc??? 0
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact