RETINAL AND VITREOUS CHANGES ASSOCIATED WITH SPONTANEOUS IMPROVEMENT IN MYOPIC MACULAR SCHISIS.

PURPOSE: To describe the retinal and vitreous changes in eyes showing myopic macular schisis (MMS) improvement when vitrectomy was not performed and identify triggering factors. DESIGN: Retrospective observational study. SUBJECTS: Patients with non-operated myopic macular schisis METHODS: The records of patients with MMS who were followed without performing surgery for more than 6 months were retrospectively reviewed, and the eyes showing an anatomical improvement were included. MMS evolution was analyzed quantitatively (central foveal thickness [CFT], parafoveal thickness, maximum height) and qualitatively (presence/absence of foveal detachment, lamellar hole, epiretinal membrane, choroidal neovascularization, inner and outer retinoschisis, vitreous status) at baseline and at the final visit. An anatomical improvement was defined as a decrease in CFT by at least 50 µm. MAIN OUTCOME MEASURE: The rate anatomical improvement of MMS without performing vitrectomy and the morphological changes observed in these cases. RESULTS: In a cohort of 74 non-operated eyes with MMS, MMS improved in 14 eyes (19%) after a mean follow-up of 55 ± 38 months (range: 8-138). In these improved cases, the mean decrease in CFT was 153 ± 166 µm (range: 24-635, p=0.005) and a complete resolution of MMS was observed in 9 eyes (64%). In 9 eyes (64%), the improvement was associated with visible vitreous changes in the macular area on the OCT scans. The mean visual acuity, which was already good at baseline (20/50, 0.4 ± 0.2 LogMAR), increased at the last visit (20/40, 0.3 ± 0.3 LogMAR) but without reaching significance. CONCLUSION: This long-term follow-up analysis showed that almost 20% of MMS in eyes without indication for surgery could improve over time. In most cases, the improvement was associated with an apparent resolution of vitreous tensions.

Deep Learning for prediction of late recurrence of retinal detachment using preoperative and postoperative ultra-wide field imaging.

PURPOSE: To elaborate a deep learning (DL) model for automatic prediction of late recurrence (LR) of rhegmatogenous retinal detachment (RRD) using pseudocolor and fundus autofluorescence (AF) ultra-wide field (UWF) images obtained preoperatively and postoperatively. MATERIALS AND METHODS: We retrospectively included patients >18 years who underwent either scleral buckling (SB) or pars plana vitrectomy (PPV) for primary or recurrent RRD with a post-operative follow-up >2 years. Records of RRD recurrence between 6 weeks and 2 years after surgery served as a ground truth for the training of the deep learning (DL) models. Four separate DL models were trained to predict LR within the 2 postoperative years (binary outputs) using, respectively, UWF preoperative and postoperative pseudocolor images and UWF preoperative and postoperative AF images. RESULTS: A total of 412 eyes were included in the study (332 eyes treated with PPV and 80 eyes with SB). The mean follow-up was 4.0 ± 2.1 years. The DL models based on preoperative and postoperative pseudocolor UWF imaging predicted recurrence with 85.6% (sensitivity 86.7%, specificity 85.4%) and 90.2% accuracy (sensitivity 87.0%, specificity 90.8%) in PPV-treated eyes, and 87.0% (sensitivity 86.7%, specificity 87.0%) and 91.1% (sensitivity 88.2%, specificity 91.9%) in SB-treated eyes, respectively. The DL models using preoperative and postoperative AF-UWF imaging predicted recurrence with 87.6% (sensitivity 84.0% and specificity 88.3%) and 91.0% (sensitivity 88.9%, specificity 91.5%) accuracy in PPV eyes, and 86.5% (sensitivity 87.5%; specificity 86.2%) and 90.6% (sensitivity 90.0%, specificity 90.7%) in SB eyes, respectively. Among the risk factors detected with visualisation methods, potential novel ones were extensive laser retinopexy and asymmetric staphyloma. CONCLUSIONS: DL can accurately predict the LR of RRD based on UWF images (especially postoperative ones), which can help refine follow-up strategies. Saliency maps might provide further insight into the dynamics of RRD recurrence.

Myopic Foveoschisis Completely Resolves within 12 Months after Vitrectomy.

PURPOSE: To assess the sequence of anatomical resolution of myopic foveoschisis (MFS) after vitrectomy. DESIGN: Monocentric retrospective observational case series. SUBJECTS: The files of consecutive patients with MFS who underwent vitreoretinal surgery and were followed postoperatively for at least 6 months were reviewed. METHODS: Patients underwent pars plana vitrectomy for MFS. The central foveal thickness (CFT) was measured. The presence of a foveal involvement, and/or outer retinoschisis (ORS), with or without inner retinoschisis (IRS), and foveal detachment (FD) were analyzed. Anatomical success was defined as the resolution of foveal ORS and FD. MAIN OUTCOME MEASURES: The main outcome was the time to resolution of the different morphologic features of MFS after surgery. RESULTS: Thirty-nine eyes of 36 patients were included in the analysis. The mean follow-up was 14.8 ± 12.9 months (range, 6-84 months). Anatomical success was achieved in 82% of cases at the end of the follow-up and in > 80% of cases during the first year. The CFT was significantly decreased in 79% of cases at 3 months. Inner retinoschisis, present in 18 eyes (46%), resolved in all cases after a median time of 1 month. Foveal ORS, present in all cases, resolved in 82% of cases after a median time of 3 months. The FD, present in 23 eyes (59%), resolved in 91% of cases after a median time of 6 months. Extrafoveal ORS resolved in 59% of cases after a median time of 12 months. The mean best-corrected visual acuity significantly improved from 0.80 ± 0.64 logarithm of the minimum angle of resolution (logMAR) (Snellen Eq 20/148) to 0.48 ± 0.52 logMAR (Snellen Eq 20/70). CONCLUSIONS: Most MFS (80%) are completely resolved during the first year. The decrease in CFT and early resolution of IRS could be used as early biomarkers of surgical success.