Systems and methods of choroidal neovascularization detection using optical coherence tomography angiography
AssigneeOregon Health & Science University
InventorsYali Jia, David Huang, Li Liu
Life of this patent
Estimating the term…
Abstract
Disclosed are systems and methods to automatically detect choroidal neovascularization (CNV) in the outer retina using OCT angiography. Further disclosed are methods of removing projection artifacts from the outer retina and for combining brightness, orientation, and position information in a context-aware saliency model to quantify CNV area in OCT angiograms.
Claims33
1-10. (canceled)
A method of identifying a choroidal neovascularization (CNV) region in an optical coherence tomography (OCT) angiogram comprising:
- obtaining an inner retina angiogram and an outer retina angiogram that correspond to different regions of a retina;
- subtracting the inner retina angiogram from the outer retina angiogram, thereby generating a subtracted outer retina angiogram;
- generating a binary vascular mask from the subtracted outer retina angiogram;
- and
- multiplying the binary vascular mask by the outer retina angiogram, thereby identifying the CNV region in the outer retina angiogram.
A method of determining a choroidal neovascularization (CNV) area in an optical coherence tomography (OCT) angiogram comprising:
- generating a saliency map of CNV from a two-dimensional (2D) en face outer retina angiogram using pattern recognition;
- generating a binary vascular mask from the saliency map;
- multiplying the binary vascular mask by the 2D en face outer retina angiogram, thereby identifying a CNV region in the outer retina angiogram;
- and
- calculating the CNV area of the CNV region.
A system for determining a choroidal neovascularization (CNV) area in an optical coherence tomography (OCT) angiogram, the system comprising:
- an OCT system configured to acquire an OCT dataset for a retina;
- a logic subsystem;
- and
- a data holding subsystem comprising machine-readable instructions stored thereon that are executable by the logic subsystem to:
- obtain an inner retina angiogram and an outer retina angiogram from the OCT dataset, wherein the inner retina angiogram and the outer retina angiogram correspond to different regions of the retina;
- subtract the inner retina angiogram from the outer retina angiogram to generate a subtracted outer retina angiogram;
- generate a binary vascular mask from the subtracted outer retina angiogram;
- and
- apply the binary vascular mask to the outer retina angiogram to identify a CNV region in the outer retina angiogram;
- and
- calculate a CNV area of the CNV region.
Dependencies are inferred from the claim text.