Voxeleron, LLC

Carl Zeiss Meditec Gmbh

Other

Johns Hopkins University

Jonathan David Oakley

Daniel Benjamin Russakoff

Matthew J Everett

Mary K Durbin

Robert W Knighton

Joseph L Mankowski

Daniel B Russakoff

Optical coherence tomography (OCT) data can be analyzed with neural networks trained on OCT data and known clinical outcomes to make more accurate predictions about the development and progression of retinal diseases, central nervous system disorders, and other conditions. The methods take 2D or 3D OCT data derived from different light source configurations and analyze it with neural networks that are trained on OCT images correlated with known clinical outcomes to identify intensity distributions or patterns indicative of different retina conditions. The methods have greater predictive power than traditional OCT analysis because the invention recognizes that subclinical physical changes affect how light interacts with the tissue matter of the retina, and these intensity changes in the image can be distinguishable by a neural network that has been trained on imaging data of retinas.

Method and system for disease analysis and interpretation

Methods are disclosed for the generation and editing of layer delineations within three-dimensional tomography scans. Cross sections of a subject are generated and presented to an operator, who has the ability to edit layer delineations within the cross section, or determine parameters used to generate new cross sections. By guiding an operator through a set of displayed cross sections, the methods can allow for a more rapid, efficient, and error-free segmentation of the subject. The cross sections can be nonplanar in shape or planar and non-axis-aligned. The cross sections can be restricted to exclude one or more user-defined regions of the subject, or to include only one or more user-defined regions of the subject. The cross sections can be localized to a point-of-interest. Iterative implementations of the methods can be used to arrive at a segmentation deemed satisfactory by the user.

Method and apparatus for generation or editing of layer delineations

The present invention relates to structural analysis of the optic nerve head (ONH). In one approach, a 3D volume of intensity data which includes the optic nerve head is acquired using an optical coherence tomography (OCT) system. The vitreoretinal interface (VRI) and the optic disc margin are identified from the 3D data. The minimum area of a surface from the optic disc margin to the VRI is determined. This minimum area can be displayed as an image or in the alternative, a value corresponding to this minimum area can be displayed. The minimum area measurement provides relevant clinical information to determine the health of the eye.

Automated analysis of the optic nerve head via optical coherence tomography measurements, methods and representations

Methods for analyzing optical coherence tomography (OCT) images of the macula to reduce variance and improve disease diagnosis are presented. One embodiment of the invention is directed towards selecting analysis locations and data segmentation techniques to take advantage of structural homogeneities. Another embodiment is directed towards reducing the variance in a collection of normative data by transforming the individual members of the database to correspond to a Standard Macula. Variations in foveal size are corrected by radial transformation. Variations in layer thickness are corrected by axial shifting. Diagnosis is performed by comparing OCT images from a patient to the improved normative database.

Methods to reduce variance in OCT analysis of the macula

The present invention is directed to a software algorithm that measures the number of corneal nerve fibers in images captured by microscopy including images from patients obtained by in vivo corneal confocal microscopy, a noninvasive technique. The present invention solves a complicated segmentation problem, by exploiting the piece wise linear nature of the nerve fibers&#x2014;i.e., the nerves are made up of a lot of straight line segments. The image is split into sub-regions, where each sub-region contains nerves mostly running in the same, straight direction. Having the nerves all in straight-lines within a single 2d image region dramatically simplifies the segmentation problem. The image intensities are summed in the direction of the nerves to reduce the 2d representation to a 1d signal having pronounced peaks where the nerves are located.

Automated methods to count corneal subbasal nerves

A method is provided that includes identifying a plurality of data sets, each data set is associated with a distribution model and each data set is associated with an image having a first noise level. The method includes partitioning the data sets into a plurality of groups and generating a best representative estimate for each group, the estimate is associated with a second noise level that is less than the first noise level. The method further includes annotating each group and receiving an input data set. The method includes assigning the input data set to a group and annotating the input data set according to that group's annotation.

Growing community of inventors

Pleasanton, CA, United States of America

Jonathan David Oakley