Discovery of retinal biomarkers for vascular conditions through advancement of artery-vein detection and fractal analysis
Research into automatic retina image analysis has become increasingly important, not just in ophthalmology but also in other clinical specialities such as cardiology and neurology. In the retina, blood vessels can be directly visualised non-invasively in-vivo, and hence it serves as a "window" to cardiovascular and neurovascular complications. Biomarker research, i.e. investigating associations between the morphology of the retinal vasculature (as a means of revealing microvascular health or disease) and particular conditions affecting the body or brain could play an important role in detecting disease early enough to impact on patient treatment and care. A fundamental requirement of biomarker research is access to large datasets to achieve sufficient power and significance when ascertaining associations between retinal measures and clinical characterisation of disease. Crucially, the vascular changes that appear can affect arteries and veins differently. An essential part of automatic systems for retinal morphology quantification and biomarker extraction is, therefore, a computational method for classifying vessels into arteries and veins. Artery-vein classification enables the efficient extraction of biomarkers such as the Arteriolar to Venular Ratio, which is a well-established predictor of stroke and other cardiovascular events. While structural parameters of the retinal vasculature such as vessels calibre, branching angle, and tortuosity may individually convey some information regarding specific aspects of the health of the retinal vascular network, they do not convey a global summary of the branching pattern and its state or condition. The retinal vascular tree can be considered a fractal structure as it has a branching pattern that exhibits the property of self-similarity. Fractal analysis, therefore, provides an additional means for the quantitative study of changes to the retinal vascular network and may be of use in detecting abnormalities related to retinopathy and systemic diseases. In this thesis, new developments to fully automated retinal vessel classification and fractal analysis were explored in order to extract potential biomarkers. These novel processes were tested and validated on several datasets of retinal images acquired with fundus cameras. The major contributions of this thesis include: 1) developing a fully automated retinal blood vessel classification technique, 2) developing a fractal analysis technique that quantifies regional as well as global branching complexity, 3) validating the methods using multiple datasets, and 4) applying the proposed methods in multiple retinal vasculature analysis studies.