The present study was conducted to investigate the potential of radiomics to develop an explainable AI-based system to be applied to ultra-widefield fundus retinographies (UWF-FRTs) with the objective of predicting the presence of the early signs of Age-related Macular Degeneration (AMD) and stratifying subjects with low- versus high-risk of AMD. The ultimate aim was to provide clinicians with an automatic classifier and a signature of objective quantitative image biomarkers of AMD. The use of Machine Learning (ML) and radiomics was based on intensity and texture analysis in the macular region, detected by a Deep Learning (DL)-based macular detector. Two-hundred and twenty six UWF-FRTs were retrospectively collected from two centres and manually annotated to train and test the algorithms. Notably, the combination of the ML-based radiomics model and the DL-based macular detector reported 93% sensitivity and 74% specificity when applied to the data of the centre used for external testing, capturing explainable features associated with drusen or pigmentary abnormalities. In comparison to the human operator’s annotations, the system yielded a 0.79 Cohen κ, demonstrating substantial concordance. To our knowledge, these results are the first provided by a radiomic approach for AMD supporting the suitability of an explainable feature extraction method combined with ML for UWF-FRT.

Purpose: To evaluate the anatomical and functional outcomes of an epiretinal cryopreserved human amniotic membrane (hAM) overlay technique for the management of recurrent retinal detachment (RD) associated with peripapillary breaks in highly myopic eyes. Methods: Retrospective interventional case series including five eyes with recurrent RD (mean axial length 30.70 ± 2.03 mm). Two eyes presented with recurrence under silicone oil (SO) tamponade, and three after prior SO removal. All eyes underwent 25-gauge pars plana vitrectomy with SO removal when present. A customized 8–9 mm hAM patch was positioned epiretinally and unrolled bimanually under perfluorocarbon liquid (PFCL). Final tamponade was achieved with SO 1000 cSt, followed by scheduled SO removal. Results: Complete retinal reattachment was achieved in all cases (100%) after a single procedure and remained stable throughout follow-up. Mean best-corrected visual acuity (BCVA) improved from 1.00 ± 0.60 to 0.68 ± 0.58 logMAR at 2 months after SO removal (p = 0.068). Optical coherence tomography demonstrated stable integration of the hAM as a hyperreflective layer over the peripapillary defects. No cases of graft dislocation, proliferative vitreoretinopathy, or significant inflammatory complications were observed. Conclusions: The epiretinal hAM overlay technique appears to be a safe and effective approach for sealing complex peripapillary breaks in highly myopic eyes with chorioretinal atrophy. By providing both mechanical support and a biological scaffold for tissue repair, this technique may represent a valuable surgical option in cases where conventional retinopexy is not feasible or has failed.