<p>Diabetes is associated with progressive microvascular remodelling, commonly assessed using retinal imaging, yet alternative non-invasive vascular biomarkers remain underexplored. Conjunctival vessels are directly visible and may reflect systemic microvascular changes; however, reliable quantification is challenged by the need to preserve vascular topology during segmentation. In this work, we introduce a curated conjunctival imaging dataset with diameter-specific vessel annotations and demonstrate that topology-preserving vessel extraction is essential for robust tortuosity estimation. We develop a deep learning framework that prioritises vascular continuity and geometric fidelity while selectively segmenting clinically relevant vessel calibres, integrating multi-scale contextual modelling and attention-guided feature fusion to reduce fragmentation without post-processing. Compared with multiple state-of-the-art segmentation methods, the proposed approach achieves substantially lower tortuosity error and centreline deviation, even when pixel-wise accuracy is comparable. Applied to conjunctival images from individuals with diabetes and healthy controls, mean conjunctival vessel tortuosity was significantly elevated in the diabetic group, consistent with established retinal microvascular findings. Together, these results support conjunctival imaging as a non-invasive modality for microvascular phenotyping and suggest its potential utility for scalable, external-eye–based vascular assessment in diabetes research contexts.</p>