This observational, cross-sectional study is designed to explore the feasibility to extract spatial-spectral features from hyperspectral retinal images captured with Optina Diagnostics' MHRC that are characteristic to the different types of drusenoid deposits associated with dry age-related macular degeneration.
In this observational, cross-sectional, prospective study, participants with dry AMD in at least one eye will undergo a hyperspectral retinal imaging session with the Optina Diagnostics' MHRC in addition to retinal imaging with OCT, used as the gold standard method to identify and classify the drusenoid deposits. Eligible participants visiting the eye clinic for AMD with dry AMD in at least one eye will be invited to participate in the study. Subjects who sign an informed consent to participate in the study will have their eyes evaluated to confirm that at least one eye is meeting all of the inclusion criteria, and none of the exclusion criteria. The dry AMD status and stage as well as information about eye diseases and conditions will be documented for both eyes. If eligible (no ocular exclusion criteria present in at least one eye), subjects will undergo OCT imaging of the macular region. If the OCT imaging session is successful (as described in the OCT imaging procedure below), the participants will then undergo hyperspectral retinal imaging with the Optina Diagnostics MHRC.
Study Type
OBSERVATIONAL
Enrollment
112
Imaging with the MHRC and optical coherence tomography (OCT).
Clinique Ophtalmologique 2121
Montreal, Quebec, Canada
Creation of a bank of hyperspectral retinal images
Creation of a bank of hyperspectral retinal images that are normalized, registered, segmented and annotated by visual inspection for drusenoid deposit types (soft, hard or reticular pseudodrusen) identified in OCT images re-examined in these re
Time frame: 12 months
Evaluation of the segmented drusenoid deposit
Evaluation of the segmented drusenoid deposit to identify characteristic spatial-spectral features extracted with the use of a method such as, but not limited, to spatial-spectral texture analysis, local spectral normalization, spectral angle mapper (SAM) or Dimension Reduction by Orthogonal Projection for Discrimination (DROP-D) for each type and a creation of classifier.
Time frame: 12 months
Explore if spatial-spectral features identified for different drusenoid deposit
Explore if spatial-spectral features identified for different drusenoid deposit types, and in particular for soft drusen, may be present in locations outside the segmented regions visible to the observer on the hyperspectral images and OCT images. Indeed, these regions could be related to basal linear and basal laminar deposits regions and the OCT scans could be re-examined in these regions to evaluate if there is a visible "split" between the RPE and Bruch's membrane previously associated with basal laminar deposits (Sura et al., 2020).
Time frame: 12 months
Effect of the location each type of drusenoid deposit
Explore the effect of the location each type of drusenoid deposit on the characteristic spatial-spectral features. In this optional sub-study, the drusenoid deposit annotations will include the location based, for example, on circles centered on the fovea within a diameter of 1 mm, 3 mm, 6 mm and beyond 6 mm (if available in the OCT images). (Optional)
Time frame: 12 months
This platform is for informational purposes only and does not constitute medical advice. Always consult a qualified healthcare professional.