Confidence-based method and system for analyzing images of a retina
AssigneeMacuject Pty Ltd
InventorDevinder Singh Chauhan
Life of this patent
Estimating the term…
Abstract
Methods and systems of analyzing images of a retina captured by an Optical Coherence Tomography (OCT) scanner are disclosed. The methods and systems use a processor configured to implement a series of instructions that include creating a training set of images of a retina of a patient captured by an OCT scanner including labeled regions of diffuse intraretinal fluid (DIRF) such as by assessing maximum and minimum regions of DIRF and regions of pathology of the retina to generate a model, and analyzing the DIRF region or regions of pathology by the model to derive an assessment of the retina of the patient. The assessment of the retina enables, for instance, the treatment of the patient's retina to be evaluated and determined.
Claims10
A system for analyzing images of a retina captured by an optical coherence tomography (OCT) scanner, the system comprising:
- at least one OCT image of a retina obtained from a patient;
- a memory comprising a trained model configured to determine a location of diffuse intraretinal fluid in the patient retina based upon the at least one OCT image
- wherein the trained model is configured to determine the location of diffuse intraretinal fluid based on different OCT images in a training set,
- wherein the trained model is further configured to determine the location of focal intraretinal fluid (FIRF) in the retina, and
- wherein the different OCT images of the training set comprise a plurality of images that each comprise at least two labels of a region of diffuse intraretinal fluid and
- wherein a first label of the at least two labels represents a first probability that diffuse intraretinal fluid exists in the location and a second label of the at least two labels represents a second probability that diffuse intraretinal fluid exists in the location;
- and
- a display that outputs a fluid confidence map that reflects the location of the diffuse intraretinal fluid in the patient retina within the at least one OCT image based on the trained model.
Dependencies are inferred from the claim text.