Aim of this study was to evaluate the efficacy of switching treatment to faricimab in neovascular age-related macular degeneration (nAMD) from other anti-VEGF agents. Fifty-eight eyes of fifty-one patients with nAMD and a full upload series of four faricimab injections were included. Demographic data, multimodal imaging and treatment parameters were recorded. The primary outcome measures were changes in central subfield thickness (CST) and subfoveal choroidal thickness (SFCT). A subgroup analysis was performed for eyes with prior ranibizumab (R) or aflibercept (A) treatment. Mean injection intervals before and after switching were comparable (33.8 ± 11.2 vs. 29.3 ± 2.6 days; p = 0.08). Mean CST of 361.4 ± 108.1 µm prior to switching decreased significantly to 318.3 ± 97.7 µm (p < 0.01) after the third faricimab injection, regardless of prior anti-VEGF treatment (p < 0.01). Although SFCT slightly improved for the whole cohort from 165.8 ± 76.8 µm to 161.0 ± 82,8 µm (p = 0.029), subgroup analysis did not confirm this positive effect (subgroup R: p = 0.604; subgroup A: p = 0.306). In patients with a suboptimal response to aflibercept or ranibizumab in nAMD, farcimab can improve CST and slightly improve or maintain SFCT. Further prospective randomized trials are warranted.

To determine real-life quantitative changes in OCT biomarkers in a large set of treatment naive patients in a real-life setting undergoing anti-VEGF therapy. For this purpose, we devised a novel deep learning based semantic segmentation algorithm providing the first benchmark results for automatic segmentation of 11 OCT features including biomarkers for neovascular age-related macular degeneration (nAMD). Training of a Deep U-net based semantic segmentation ensemble algorithm for state-of-the-art semantic segmentation performance which was used to analyze OCT features prior to, after 3 and 12 months of anti-VEGF therapy. High F1 scores of almost 1.0 for neurosensory retina and subretinal fluid on a separate hold-out test set with unseen patients. The algorithm performed worse for subretinal hyperreflective material and fibrovascular PED, on par with drusenoid PED, and better in segmenting fibrosis. In the evaluation of treatment naive OCT scans, significant changes occurred for intraretinal fluid (mean: 0.03 µm3 to 0.01 µm3, p < 0.001), subretinal fluid (0.08 µm3 to 0.01 µm3, p < 0.001), subretinal hyperreflective material (0.02 µm3 to 0.01 µm3, p < 0.001), fibrovascular PED (0.12 µm3 to 0.09 µm3, p = 0.02) and central retinal thickness C0 (225.78 µm3 to 169.40 µm3). The amounts of intraretinal fluid, fibrovascular PED, and ERM were predictive of poor outcome. The segmentation algorithm allows efficient volumetric analysis of OCT scans. Anti-VEGF provokes most potent changes in the first 3 months while a gradual loss of RPE hints at a progressing decline of visual acuity. Additional research is required to understand how these accurate OCT predictions can be leveraged for a personalized therapy regimen.

Optical coherence tomography (OCT) imaging from different camera devices causes challenging domain shifts and can cause a severe drop in accuracy for machine learning models. In this work, we introduce a minimal noise adaptation method based on a singular value decomposition (SVDNA) to overcome the domain gap between target domains from three different device manufacturers in retinal OCT imaging. Our method utilizes the difference in noise structure to successfully bridge the domain gap between different OCT devices and transfer the style from unlabeled target domain images to source images for which manual annotations are available. We demonstrate how this method, despite its simplicity, compares or even outperforms state-of-the-art unsupervised domain adaptation methods for semantic segmentation on a public OCT dataset. SVDNA can be integrated with just a few lines of code into the augmentation pipeline of any network which is in contrast to many state-of-the-art domain adaptation methods which often need to change the underlying model architecture or train a separate style transfer model. The full code implementation for SVDNA will be made available at https://github.com/ValentinKoch/SVDNA .