Prediction of postoperative visual acuity restoration in macula off rhegmatogenous retinal detachment using artificial intelligence

Abstract

PurposeTo assess feasibility of automatic segmentation of OCT biomarkers of visual acuity (VA) and the possibility of prediction of postoperative VA after successful reattachment in macula off rhegmatogenous retinal detachment (RRD) eyes using artificial intelligence (AI). Designretrospective case control study MethodsPatients operated of pars plana vitrectomy (PPV) for macula-off non-traumatic RRD with available good quality OCT acquisitions were included. Ellipsoid zone(EZ) foveal damage and reflectivity, external limiting membrane(ELM) foveal damage, foveal flattening, outer nuclear layer(ONL) thickness and the presence of cysts and hyperreflective foci(HRFs) was assessed on preoperative OCT B scan images by both a trained segmenter and human graders. Different machine learning(ML)models were tested for detection of cases with VA>0.4 logMar at 6 months from surgery.Segmentation performance of the model was compared with ground truth segmentation provided by human graders. Postoperative VA prediction based on the segmented OCT biomarkers, preoperative VA and age was compared with actual postoperative VA to assess accuracy of the model. ResultsA total of 58 eyes of 58 patients were included. A significant difference in preoperative VA, foveal flattening, foveal EZ and ELM damage, EZ reflectivity and presence of HRF in the ONL was detected between groups(all p < 0.001).The segmenter showed good agreement with human assessment in both qualitative and quantitative variables. The Optimizable Naïve Bayes model was the best performing ML model and showed an accuracy of 86.2 % in detection of cases with postoperative VA>0.4 logMar. ConclusionsThe results confirm the prognostic relevance of EZ and ELM integrity and reflectivity, foveal flattening, ONL cysts and ONL HRF in macula off RRD, and, for the first time in literature, reports feasibility of the segmentation of these factors in preoperative OCT B scan images. We also report good classification performances of Naïve Bayes models based on OCT biomarkers, preoperative VA and age in distinguishing patients that should expect a postoperative VA>0.4 logMar at 6 months from surgery.