Purpose: To investigate whether Fractal Dimension (FD)-based oculomics could be used for individual risk prediction by evaluating repeatability and robustness. Methods: We used two datasets: Caledonia, healthy adults imaged multiple times in quick succession for research (26 subjects, 39 eyes, 377 colour fundus images), and GRAPE, glaucoma patients with baseline and follow-up visits (106 subjects, 196 eyes, 392 images). Mean follow-up time was 18.3 months in GRAPE, thus it provides a pessimistic lower-bound as vasculature could change. FD was computed with DART and AutoMorph. Image quality was assessed with QuickQual, but no images were initially excluded. Pearson, Spearman, and Intraclass Correlation (ICC) were used for population-level repeatability. For individual-level repeatability, we introduce measurement noise parameter {\lambda} which is within-eye Standard Deviation (SD) of FD measurements in units of between-eyes SD. Results: In Caledonia, ICC was 0.8153 for DART and 0.5779 for AutoMorph, Pearson/Spearman correlation (first and last image) 0.7857/0.7824 for DART, and 0.3933/0.6253 for AutoMorph. In GRAPE, Pearson/Spearman correlation (first and next visit) was 0.7479/0.7474 for DART, and 0.7109/0.7208 for AutoMorph (all p<0.0001). Median {\lambda} in Caledonia without exclusions was 3.55\% for DART and 12.65\% for AutoMorph, and improved to up to 1.67\% and 6.64\% with quality-based exclusions, respectively. Quality exclusions primarily mitigated large outliers. Worst quality in an eye correlated strongly with {\lambda} (Pearson 0.5350-0.7550, depending on dataset and method, all p<0.0001). Conclusions: Repeatability was sufficient for individual-level predictions in heterogeneous populations. DART performed better on all metrics and might be able to detect small, longitudinal changes, highlighting the potential of robust methods.

翻译：目的：探究基于分形维数（FD）的眼部组学能否通过评估重复性与稳健性用于个体风险预测。方法：采用两个数据集：Caledonia数据集（为研究目的而快速连续成像的健康成人，26名受试者，39只眼，377张彩色眼底图像）和GRAPE数据集（基线及随访的青光眼患者，106名受试者，196只眼，392张图像）。GRAPE数据集的平均随访时间为18.3个月，因此该数据集提供了悲观的较低界限（因为血管结构可能发生变化）。采用DART和AutoMorph计算FD。使用QuickQual评估图像质量，但初始阶段未排除任何图像。采用Pearson、Spearman相关和组内相关系数（ICC）评估群体水平重复性。对于个体水平重复性，引入测量噪声参数λ（即同一眼内FD测量值的标准差，以眼间标准差为单位表示）。结果：在Caledonia数据集中，DART的ICC为0.8153，AutoMorph为0.5779；Pearson/Spearman相关（首末图像）在DART中为0.7857/0.7824，在AutoMorph中为0.3933/0.6253。在GRAPE数据集中，Pearson/Spearman相关（首次与下次访视）在DART中为0.7479/0.7474，在AutoMorph中为0.7109/0.7208（所有p值均<0.0001）。在Caledonia数据集中，未经图像排除时，DART的中位λ值为3.55%，AutoMorph为12.65%；经基于质量排除后，分别改善至1.67%和6.64%。质量排除主要减少了较大离群值。眼内最差质量与λ值高度相关（Pearson相关系数0.5350-0.7550，取决于数据集和方法，所有p值均<0.0001）。结论：在异质性人群中，重复性足以支持个体水平预测。DART在所有指标上表现更优，可能能够检测微小的纵向变化，凸显了稳健方法的潜力。