Deep Learning-Based Quantification of Vitreous Hyperreflective Foci as a Biomarker for Intraocular Inflammation.
Artificial intelligence-measured vitreous debris density accurately identified eyes with concurrent intraocular inflammation.
Deep Learning-Based Quantification of Vitreous Hyperreflective Foci as a Biomarker for Intraocular Inflammation.
To develop and validate an artificial intelligence (artificial intelligence)-driven pipeline to quantify vitreous hyperreflective foci (vHRF) from OCT images and assess their association with intraocular inflammation (intraocular inflammation).
SUBJECTS: A clinical analysis cohort of 369 patients from the GALLEGO clinical trial (Galegenimab vs. placebo in patients with geographic atrophy, clinical trial ID: NCT03972709).
Higher vitreous cloudiness density on OCT scans distinguished inflamed from non-inflamed eyes (AUC 0.84).
The U-Net Transformer model demonstrated strong segmentation performance.
In eye-clustered logistic generalized estimating equation models, 5 filtered biomarkers were significantly associated with inflammation, with the strongest association for filtered vHRF density [vHRF/μm 3 ] (odds ratio per standard deviation 1.62, 95% confidence interval 1.26-2.07, P < 0.001).
At the optimal threshold for vHRF density, sensitivity was 67.7%, specificity 89.0%, and positive predictive value was 16.9% despite an intraocular inflammation prevalence of 3.2%.
Our artificial intelligence-driven pipeline accurately quantified vHRF from OCT images, and the resulting metrics, particularly vHRF volume density, were significantly associated with concurrent intraocular inflammation.
These findings support automated vHRF quantification as a promising imaging biomarker for inflammation assessment, although further validation in larger and more diverse datasets is needed.