Algorithm for predicting macular dysfunction based on moment invariants classification of the foveal avascular zone in functional retinal images

Abstract Introduction A new method for segmenting and quantifying the macular area based on morphological alternating sequential filtering (ASF) is proposed. Previous studies show that persons with diabetes present alterations in the foveal avascular zone (FAZ) prior to the appearance of retinopathy. Thus, a proper characterization of FAZ using a method of automatic classification and prediction is a supportive and complementary tool for medical evaluation of the macular region, and may be useful for possible early treatment of eye diseases in persons without diabetic retinopathy. Methods We obtained high-resolution retinal images using a non-invasive functional imaging system called Retinal Function Imager to generate a series of combined capillary perfusion maps. We filtered sequentially the macular images to reduce the complexity by ASF. Then we segmented the FAZ using watershed transform from an automatic selection of markers. Using Hu's moment invariants as a descriptor, we can automatically classify and categorize each FAZ. Results The FAZ differences between non-diabetic volunteers and diabetic subjects were automatically distinguished by the proposed system with an accuracy of 81%. Conclusion This is an innovative method to classify FAZ using a fully automatic algorithm for segmentation (based on morphological operators) and for the classification (based on descriptor formed by Hu's moments) despite the presence of edema or other structures. This is an alternative tool for eye exams, which may contribute to the analysis and evaluation of FAZ morphology, promoting the prevention of macular impairment in diabetics without retinopathy.

Reliability and validity of digital assessment of perifoveal capillary network measurement using high-resolution imaging.

BACKGROUND: Assessment of the perifoveal capillary network (PCN) might indicate macular function and could reflect the systemic microcirculation. The quantification and reliability of this measurement is currently unknown. The aim of this study was to validate quantification of the PCN by a non-invasive technique from high-resolution retinal images. METHODS: Ten healthy volunteers were included in this validation study. At least 320 high-resolution retinal images were used for assessment of inter- and intra-observer reliability. Non-invasive capillary perfusion mapping was performed using a retinal function imager. After the images were enhanced and segmented, the reproducibility was verified by comparing the values of two independent examiners and of a single examiner at two different time points. RESULTS: The inter-observer concordance coefficients were highly significant for PCN (intraclass correlation coefficient (ICC)=0.901, 95% CI 0.655 to 0.975, p<0.001) and normalised PCN (ICC=0.727, 95% CI 0.262 to 0.923, p=0.004). The intra-observer measurements at two different time points were also highly concordant for PCN (ICC=0.879, 95% CI 0.598 to 0.968, p<0.001) and for normalised PCN (ICC=0.960, 95% CI 0.851 to 0.990, p<0.001). CONCLUSIONS: The reliability of PCN measurement is reproducible and could be used as a new tool to quantify the capillary perfusion network of the macular area.