Techniques for automatically segmenting ocular imagery and predicting progression of age-related macular degeneration

A computer-implemented method of automatically detecting an area of an eye exhibiting geographic atrophy, the method comprising:

• receiving, by an image analysis computing system, optical coherence tomography data (OCT data);
• determining, by the image analysis computing system, an optical attenuation coefficient for each pixel of the OCT data to create optical attenuation coefficient data (OAC data) corresponding to the OCT data;
• and
• determining, by the image analysis computing system, an area exhibiting geographic atrophy based on the OAC data;
• wherein determining the area exhibiting geographic atrophy based on the OAC data includes:
• determining a location of a Bruch's membrane within the OAC data;
• extracting a slab from the OAC data located above the Bruch's membrane;
• generating an en face OAC maximum projection image for a slab from the OAC data located above the Bruch's membrane;
• generating an en face OAC sum projection image for the slab;
• generating an en face retinal pigment epithelium to Bruch's membrane distance map (RPE-BM distance map) for the slab;
• generating an en face false color image for the slab by combining the en face OAC maximum projection image, the en face OAC sum projection image, and the en face RPE-BM distance map;
• and
• providing the en face false color image to a machine learning model trained to detect areas exhibiting geographic atrophy within en face false color images.

A non-transitory computer-readable medium having computer-executable instructions stored thereon that, in response to execution by one or more processors of an image analysis computing system, cause the computing system to perform actions comprising:

• receiving, by the image analysis computing system, optical coherence tomography data (OCT data);
• determining, by the image analysis computing system, an optical attenuation coefficient for each pixel of the OCT data to create optical attenuation coefficient data (OAC data) corresponding to the OCT data;
• and
• determining, by the image analysis computing system, an area exhibiting geographic atrophy based on the OAC data;
• wherein determining the optical attenuation coefficient for each pixel of the OCT data to create OAC data corresponding to the OCT data includes calculating, for each pixel i, a value μ[i] that represents the OAC of the ith pixel, wherein:
• μ
• [
• i
• ]
• =
• I
• [
• i
• ]
• 2
• ⁢
• Δ
• ⁢
• ∫
• i
• +
• 1
• ∞
• I
• [
• i
• ]
• wherein Δ is an axial size of each pixel;
• wherein I[i] is a detected OCT signal intensity at the ith pixel;
• and
• wherein
• ∫
• i
• +
• 1
• ∞
• I
• [
• i
• ]
• is calculated by adding OCT signal intensities of all pixels beneath the ith pixel.