Choroidal image analysis for OCT image sequences with applications in systemic health

TL;DR

This work advances choroidal image analysis in OCT by transitioning from manual to fully automatic, open-source segmentation tools. It introduces GPET, MMCQ, DeepGPET, and Choroidalyzer to segment choroidal space and vasculature, enabling reproducible measurements of choroidal thickness, area, CVI, and vessel metrics. Through three systemic-health applications—OCTANE, PREVENT, and D-RISCii—it demonstrates the choroid as a promising biomarker for kidney function, Alzheimer's risk, and critical care physiology. The methods emphasize standardization, reproducibility, and end-user accessibility, with extensive open-source tooling, comprehensive evaluation, and discussion of limitations and future directions. Overall, this framework lays the groundwork for scalable, objective ocular biomarkers of systemic health via choroidal analysis in OCT image sequences.

Abstract

The choroid, a highly vascular layer behind the retina, is an extension of the central nervous system and has parallels with the renal cortex, with blood flow far exceeding that of the brain and kidney. Thus, there has been growing interest of choroidal blood flow reflecting physiological status of systemic disease. Optical coherence tomography (OCT) enables high-resolution imaging of the choroid, but conventional analysis methods remain manual or semi-automatic, limiting reproducibility, standardisation and clinical utility. In this thesis, I develop several new methods to analyse the choroid in OCT image sequences, with each successive method improving on its predecessors. I first develop two semi-automatic approaches for choroid region (Gaussian Process Edge Tracing, GPET) and vessel (Multi-scale Median Cut Quantisation, MMCQ) analysis, which improve on manual approaches but remain user-dependent. To address this, I introduce DeepGPET, a deep learning-based region segmentation method which improves on execution time, reproducibility, and end-user accessibility, but lacks choroid vessel analysis and automatic feature measurement. Improving on this, I developed Choroidalyzer, a deep learning-based pipeline to segment the choroidal space and vessels and generate fully automatic, clinically meaningful and reproducible choroidal features. I provide rigorous evaluation of these four approaches and consider their potential clinical value in three applications into systemic health: OCTANE, assessing choroidal changes in renal transplant recipients and donors; PREVENT, exploring choroidal associations with Alzheimer's risk factors at mid-life; D-RISCii, assessing choroidal variation and feasibility of OCT in critical care. In short, this thesis contributes many open-source tools for standardised choroidal measurement and highlights the choroid's potential as a biomarker in systemic health.

Figures (130)

• Figure 1: Schematic of the PhD research journey. (A) Current approaches to choroidal image analysis. (B) Work conducted during research period, with boxes and arrows identifying analysis methods from applications and their relationships. (C) Past, current and planned future applications of the methods developed from this thesis.
• Figure 2: Typical horizontal-line, OCT scan from a Heidelberg Engineering OCT imaging device. En face localiser SLO image (A) and corresponding OCT B-scan (B), with annotations overlaid of major anatomical landmarks.
• Figure 3: Schematic of how TD-OCT works to generate an OCT B-scan. Note that this B-scan is from an SD-OCT device and is purely demonstrative of how the system works in general.
• Figure 4: Comparison of TD-OCT and SD-OCT for a single OCT B-scan of the same eye and approximately the same anatomical location. Reprinted with permission from Christopher Mody mody2016past.
• Figure 5: Comparison of an SD-OCT B-scan without EDI mode (A) and with EDI mode (B). Beside each B-scan plots the approximate signal sensitivity as a function of axial distance (from sclera to vitreous).