Background: The oxygen induced retinopathy rodent model is widely used, notably for the assessment of developmental dystrophies in preclinical studies of vascular retinal diseases. Typically, the quantification of vessel tufts and avascular regions is computed manually from flat mounted retinas imaged using fluorescent probes that highlight the vascular network. However, such manual measurements are time-consuming and hampered by user variability and bias, thus a rapid and objective alternative is required.
Methods: We employ a machine learning approach to segment and characterize vascular tufts. The proposed quantitative retinal vascular assessment (QuRVA) technique uses quadratic discrimination analysis and morphological techniques to provide reliable measurements of vascular density and pathological vascular tuft regions, devoid of user intervention within seconds. Our algorithms allow also delineating the whole vasculature network, and identifying and analyzing avascular regions.
Results: Our first experiment shows the high degree of error and variability of manual segmentations. In consequence, we developed a set of algorithms to perform this task automatically. We benchmark and validate the results of our analysis pipeline using the consensus of several manually curated segmentations using commonly used computer tools. We describe the method, provide details for reproducing the algorithm, and validate all aspects of the analysis.
Conclusions: Manual and semi-automated procedures for tuft detection present strong fluctuations among users, demonstrating the need for fast and unbiased tools in this highly active research field with tremendous implications for basic research and industry.
Abstract: Uveitis can cause significant visual morbidity and often affects younger adults of working age. Anterior uveitis, or inflammation limited to the anterior chamber (AC), iris, and/or ciliary body comprises the majority of uveitis cases. Current clinical biomarkers and conventional grading scales for intraocular inflammation are mostly subjective and have only a moderate degree of interobserver reliability, and as such they have significant limitations when used in either clinical practice or research related to uveitis. In recent years, novel imaging techniques and applications have emerged that can supplement exam findings to detect subclinical disease, monitor quantitative biomarkers of disease progression or treatment effect, and provide overall a more nuanced understanding of disease entities. The first part of this review discusses automated algorithms for optical coherence tomography (OCT) image processing and analysis as a means to assess and describe intraocular inflammation with higher resolution than that afforded by conventional AC and vitreous cell ordinal grading scales. The second half of the review focuses on anterior segment OCT and OCT angiography (OCTA) in scleritis and iritis, especially with regards to their ability to directly image and characterize the pathologic structures and vasculature underlying these diseases. Finally, we briefly review experimental animal research with promising but more distant human clinical applications, including in vivo molecular microscopy of inflammatory markers and investigation of gold nanoparticles as a potential contrast agent in OCT imaging. Imaging modalities are discussed in the broader context of trends within the field of uveitis towards greater objectivity and quantifiable outcome measures and biomarkers.
