Recent methods for automatic blood vessel segmentation from fundus images have been commonly implemented as convolutional neural networks. While these networks report high values for objective metrics, the clinical viability of recovered segmentation masks remains unexplored. In this paper, we perform a pilot study to assess the clinical viability of automatically generated segmentation masks in the diagnosis of diseases affecting retinal vascularization. Five ophthalmologists with clinical experience were asked to participate in the study. The results demonstrate low classification accuracy, inferring that generated segmentation masks cannot be used as a standalone resource in general clinical practice. The results also hint at possible clinical infeasibility in experimental design. In the follow-up experiment, we evaluate the clinical quality of masks by having ophthalmologists rank generation methods. The ranking is established with high intra-observer consistency, indicating better subjective performance for a subset of tested networks. The study also demonstrates that objective metrics are not correlated with subjective metrics in retinal segmentation tasks for the methods involved, suggesting that objective metrics commonly used in scientific papers to measure the method’s performance are not plausible criteria for choosing clinically robust solutions.

Pterygium is a common ocular surface disorder linked to chronic ultraviolet exposure, local inflammation, and oxidative stress, yet no reliable circulating biomarker currently guides diagnosis, activity assessment, or recurrence risk. Peripheral-blood studies addressing this gap have produced inconsistent findings across hematological, inflammatory, and micronutrient domains, often using heterogeneous case definitions and isolated marker panels. In this prospective case–control study, 30 patients with newly diagnosed, clinically active primary pterygium and 17 healthy controls frequency-matched for age and sex underwent a comprehensive peripheral blood panel comprising 46 hematological, biochemical, iron-related, inflammatory, and vitamin/metabolic-bone parameters, including osteocalcin, ceruloplasmin, and immunoglobulin E. Lesions were graded using the Maheshwari and Tan classification systems, and group and severity-stratified comparisons were corrected for multiple testing using the Benjamini–Hochberg procedure. No parameter differed significantly between groups after correction. Nominal, uncorrected differences included higher total protein, albumin, and mean platelet volume in patients with pterygium, and severity-linked patterns of higher platelet count, plateletcrit, and ceruloplasmin, and higher vitamin B12, folic acid, and serum iron in less advanced lesions. None of these nominal differences survived correction, so no single marker distinguished pterygium from controls or tracked severity. Platelet indices and ceruloplasmin showed the most consistent severity-linked pattern, but this was nominal only and hypothesis-generating, warranting evaluation in larger, adequately powered cohorts.