An Empirical Analysis of Loss Functions for Deep Retinal Vessel Segmentation

Retinal vessel segmentation underpins computer-assisted screening and monitoring of ocular and systemic disease. While encoder–decoder networks such as U-Net are widely used, their behavior is strongly shaped by the training objective. This work presents a controlled empirical study of loss functions for vessel segmentation using a U-Net architecture that employs strided convolutions in the encoder, together with a consistent preprocessing pipeline based on morphological enhancement and principal component analysis. We compare cross-entropy, weighted cross-entropy, and Dice losses on the DRIVE and STARE datasets under identical settings, reporting pixel-wise and overlap-based measures to reflect both detection and spatial agreement. The configuration with weighted cross-entropy provides a balanced outcome, achieving sensitivity and accuracy of 0.873 and 0.969 on DRIVE, and 0.821 and 0.961 on STARE. Rather than proposing architectural novelty, the contribution of this study is a reproducible data-driven comparison that clarifies the trade-offs each loss imposes on recall, specificity, and boundary fidelity, offering practical guidance for selecting objectives in retinal vessel segmentation.