Glaucoma is a degenerative disease that constitutes the second cause of blindness in developed countries. Although it cannot be cured, its progression can be prevented through early diagnosis. In this paper, we propose a new algorithm for automatic glaucoma diagnosis based on retinal colour images. We focus on capturing the inherent colour changes of optic disc (OD) and cup borders by computing several colour derivatives in CIE L^∗a^∗b^∗ colour space with CIE94 colour distance. In addition, we consider spatial information retaining these colour derivatives and the original CIE L^∗a^∗b^∗ values of the pixel and adding other characteristics such as its distance to the OD centre. The proposed strategy is robust due to a simple structure that does not need neither initial segmentation nor removal of the vascular tree or detection of vessel bends. The method has been extensively validated with two datasets (one public and one private), each one comprising 60 images of high variability of appearances. Achieved class-wise-averaged accuracy of 95.02% and 81.19% demonstrates that this automated approach could support physicians in the diagnosis of glaucoma in its early stage, and therefore, it could be seen as an opportunity for developing low-cost solutions for mass screening programs.

The retina functions as a neurovascular unit. How early vascular alterations affect neuronal layers remains controversial; early vascular failure could lead to edema increasing retinal thicknesses, but alternatively neuronal loss could lead to reduced retinal thickness. Objective. To evaluate retinal thickness in a cohort of pediatric patients with type 1 diabetes mellitus (PwT1DM) and to analyze differences according to the presence or absence of nonproliferative diabetic retinopathy (NPDR), poor metabolic control, and diabetes duration. Patients and Methods. We performed retinographies and optical coherence tomography (OCT) (TOPCON 3D1000®) to PwT1DM followed at our center and healthy controls. Measurements of the control group served to calculate reference values. Results. 59 PwT1DM (age 12.51 ± 2.59) and 22 healthy controls (age 10.66 ± 2.51) volunteered. Only two PwT1DM, both adolescents with poor metabolic control, presented NPRD. Both showed decreased thicknesses and retinal volumes. The odds ratio of having decreased retinal thickness when signs of NPDR were present was 11.72 (95% IC 1.16–118.28; p=0.036). Conclusions. PwT1DM with NPDR have increased odds of decreased retinal thicknesses and volumes. Whether these changes are reversible by improving metabolic control or not remains to be elucidated.