Michael J. Beyeler

Jose D. Vargas Quiros, Michael J. Beyeler, Sofia Ortin Vela et al.

The automatic extraction of retinal vascular biomarkers from color fundus images (CFI) is essential for large-scale studies of the retinal vasculature. We present VascX, an open-source Python toolbox designed for the automated extraction of biomarkers from artery and vein segmentations. The VascX workflow processes vessel segmentation masks into skeletons to build undirected and directed vessel graphs, which are then used to resolve segments into continuous vessels. This architecture enables the calculation of a comprehensive suite of biomarkers, including vascular density, bifurcation angles, central retinal equivalents (CREs), tortuosity, and temporal angles, alongside image quality metrics. A distinguishing feature of VascX is its region awareness; by utilizing the fovea, optic disc, and CFI boundaries as anatomical landmarks, the tool ensures spatially standardized measurements and identifies when specific biomarkers are not computable. Spatially localized biomarkers are calculated over grids relative to these landmarks, facilitating precise clinical analysis. Released via GitHub and PyPI, VascX provides an explainable and modifiable framework that supports reproducible vascular research through integrated visualizations. By enabling the rapid extraction of established biomarkers and the development of new ones, VascX advances the field of oculomics, offering a robust, computationally efficient solution for scalable deployment in large-scale clinical and epidemiological databases.

Jiayi Liu, Yilin Wang, Michael Beyeler

Cloud-based machine learning is increasingly explored as a preprocessing strategy for next-generation visual neuroprostheses, where advanced scene understanding may exceed the computational and energy constraints of battery-powered visual processing units. Offloading computation to remote servers enables the use of state-of-the-art vision models, but also introduces sensitivity to network latency, jitter, and packet loss, which can disrupt the temporal consistency of the delivered neural stimulus. In this work, we examine the feasibility of cloud-assisted visual preprocessing for artificial vision by framing remote inference as a perceptually constrained systems problem. We present a network-adaptive cloud-assisted pipeline in which real-time round-trip-time feedback is used to dynamically modulate image resolution, compression, and transmission rate, explicitly prioritizing temporal continuity under adverse network conditions. PIDNet is used as a fixed real-time semantic segmentation backbone, allowing us to isolate how network-adaptive input encoding affects communication delay, inference time, and perceptual fidelity. Results show that adaptive visual encoding substantially reduces end-to-end latency during network congestion, with only modest degradation of global scene structure, while boundary precision degrades more sharply. Together, these findings delineate operating regimes in which cloud-assisted preprocessing may remain viable for future visual neuroprostheses and underscore the importance of network-aware adaptation for maintaining perceptual stability.