Evaluation of spatial distribution of initial marking strategy among inexperienced graders in diabetic retinopathy: A retrospective cross-sectional analysis.
Lowater Simon Joel Ellerup SJE, Núñez Andrea Blasi AB, Andersen Jakob Kristian Holm JKH, Dinesen Sebastian S et al.
Manual diabetic retinopathy (DR) grading may prefer certain regions and underestimate others. It is unclear if inexperienced graders' initial marking strategy reflects a specialist's marking pattern. By the virtual ocular learning platform (VIOLA), we evaluated if initial DR-lesion markings among inexperienced graders spatially corresponded to a specialist-based lesion map. We used retinal 6-field VIOLA images with at least 500 DR-lesion markings covering all DR-levels (0-4) according to the international clinical diabetic retinopathy (ICDR) scale. We divided images into quadrants and counted the initial three markings per lesion type, per image, per grader. A retinal specialist served reference for annotation of all DR-lesions. The primary outcome was difference in spatial distribution of DR-markings across quadrants relative to the reference, further characterised with spatial metrics. p-Value < 0.05 indicated statistical significance. Across 24 images, 97 graders marked 16 925 DR-lesions: 1633 microaneurysms (MA), 3228 haemorrhages, 1549 hard exudates (HE), 3081 cotton wool spots (CWS), 3844 intraretinal microvascular abnormalities (IRMA), 1832 new vessels (NV) and 1758 panretinal photocoagulation scars (PRP). A difference was observed across all lesion types (χ2-test, p < 0.001) relative to the reference lesion map. Most lesion types demonstrated high sensitivity, but low PPV, indicating a liberal marking approach. Distribution of initial markings from inexperienced graders spatially misaligns with a specialist-derived lesion map across all lesion types. As the ICDR-scale depends on identifying the most severe lesion type, systematically inconsistent search strategies may pose a risk for overlooking important lesions under time constraints. The results support the promotion of attention guiding during DR-training.