Automatic segmentation of the foveal avascular zone in ophthalmological OCT-A images

Abstract

Angiography by Optical Coherence Tomography (OCT-A) is a non-invasive retinal imaging modality of recent appearance that allows the visualization of the vascular structure at predefined depths based on the detection of the blood movement through the retinal vasculature. In this way, OCT-A images constitute a suitable scenario to analyze the retinal vascular properties of regions of interest as is the case of the macular area, measuring the characteristics of the foveal vascular and avascular zones. Extracted parameters of this region can be used as prognostic factors that determine if the patient suffers from certain pathologies (such as diabetic retinopathy or retinal vein occlusion, among others), indicating the associated pathological degree. The manual extraction of these biomedical parameters is a long, tedious and subjective process, introducing a significant intra and inter-expert variability, which penalizes the utility of the measurements. In addition, the absence of tools that automatically facilitate these calculations encourages the creation of computer-aided diagnosis frameworks that ease the doctor’s work, increasing their productivity and making viable the use of this type of vascular biomarkers. In this work we propose a fully automatic system that identifies and precisely segments the region of the foveal avascular zone (FAZ) using a novel ophthalmological image modality as is OCT-A. The system combines different image processing techniques to firstly identify the region where the FAZ is contained and, secondly, proceed with the extraction of its precise contour. The system was validated using a representative set of 213 healthy and diabetic OCT-A images, providing accurate results with the best correlation with the manual measurements of two experts clinician of 0.93 as well as a Jaccard’s index of 0.82 of the best experimental case in the experiments with healthy OCT-A images. The method also provided satisfactory results in diabetic OCT-A images, with a best correlation coefficient with the manual labeling of an expert clinician of 0.93 and a Jaccard’s index of 0.83. This tool provides an accurate FAZ measurement with the desired objectivity and reproducibility, being very useful for the analysis of relevant vascular diseases through the study of the retinal micro-circulation.

Automatic quantification of superficial foveal avascular zone in optical coherence tomography angiography implemented with deep learning

“…The final sFAZ segmentation result was obtained by applying morphological operators and an active contour model. Díaz et al [13] identified all potential FAZ (both sFAZ and dFAZ) candidates by applying morphological operators and edge detection techniques. Subsequently, specific domain knowledge was used to preserve the most suitable FAZ localization from all the FAZ candidates.…”

A Novel Automatic Method to Estimate Visual Acuity and Analyze the Retinal Vasculature in Retinal Vein Occlusion Using Swept Source Optical Coherence Tomography Angiography

“…Ghasemi et al [31] used another device to study the vascular changes in five central RVO eyes after a single intravitreal antiVEGF injection for ME eyes using a manual tool to outline the FAZ. In this respect, the intrapersonal and interpersonal variability of the manual FAZ identifications has to be considered as this introduces subjectivity into the calculation, in contrast to the objectivity and repeatability of the computational procedure that we have proposed [18].…”

“…In the current study, we proposed a novel, fully automatic, objective, and time-efficient methodology for assessing different vascular parameters which are considered as prognostic biomarkers in RVO eyes. We used a metric based on a new application of the methodology previously validated by Díaz et al [18] for healthy and diabetic patients, summarized in Materials and Methods, which we applied here to RVO OCTA images, and integrated an image processing technique to include the VD information. Finally, we implemented this information to estimate VA, based on the extracted parameters.…”

“…Recently, Díaz et al [18] validated an automated computational methodology to localize and measure the FAZ region using 213 healthy and diabetic retinopathy SS-OCTA images captured with the DRI OCTA Triton. The principal steps of the methodology are image processing, vascular edge identification, extraction of the FAZ candidates, FAZ region final identification (especially important for pathological conditions, the morphological characteristics of the FAZ are analyzed to remove the main false positives), and precise FAZ segmentation and area calculation.…”

“…It also provides semiautomatic quantitative information about vascular density in the 3 × 3 and 6 × 6 mm images of the SCP, but unfortunately does not provide any quantitative information about the DCP. Recently, Díaz et al [18] validated an automated method for localizing and measuring the FAZ region using 213 healthy and diabetic retinopathy SS-OCTA images.…”