Systems and methods for automated classification of abnormalities in optical coherence tomography images of the eye

摘要

Systems and methods for classifying abnormalities within optical coherence tomography images of the eye are presented. One embodiment of the present invention is the classification of pigment epithelial detachments (PEDs) based on characteristics of their internal reflectivity, size and shape. The classification can be based on selected subsets of the data located within or surrounding the abnormalities. Training data can be used to generate the classification scheme and the classification can be weighted to highlight specific classes of particular clinical interest.

主权项

1. A method of analyzing an abnormality in the retinal layers of the eye, said method comprising:
collecting three dimensional optical coherence tomography (OCT) intensity data of the retinal layers of the eye including the abnormality; segmenting the OCT intensity data to identify the boundaries of the abnormality; determining a first representative value associated with the identified abnormality; determining a second representative value associated with the identified abnormality, said first and second representative values being selected from the following characteristics of the identified abnormality:
average intensity of the data within the boundaries of the abnormality;uniformity of the intensity of the data within the boundaries of the abnormality;shape of the abnormality;size of the abnormality;blood flow within the abnormality; andlocation of the abnormality; provided, however, that the characteristic selected for the first representative value is different from the characteristic selected for the second representative value; classifying the abnormality based on the first and second representative values using predetermined criteria; and displaying or storing the classification.