Tandent Vision Science, Inc.

Carnegie Mellon University

University of Pittsburgh

David Tolliver

Andrew Neil Stein

Casey Arthur Smith

James Andrew Bagnell

Bartholomeus Christianus Leonardus Nabbe

Bruce Allen Maxwell

Kristin Jean Dana

Iljung Samuel Kwak

Richard Mark Friedhoff

Steven Joseph Bushell

Timothy King Rodgers, Jr

Milan Diebel

Joel Steven Schuman

Hiroshi Ishikawa

Gary Lee Miller

Neil Alldrin

Juan Xu

Chaim Gad Wollstein

In the context of the early detection and monitoring of eye diseases, such as glaucoma and diabetic retinopathy, the use of optical coherence tomography presents the difficulty, with respect to blood vessel segmentation, of weak visibility of vessel pattern in the OCT fundus image. To address this problem, a boosting learning approach uses three-dimensional (3D) information to effect automated segmentation of retinal blood vessels. The automated blood vessel segmentation technique described herein is based on 3D spectral domain OCT and provides accurate vessel pattern for clinical analysis, for retinal image registration, and for early diagnosis and monitoring of the progression of glaucoma and other retinal diseases. The technique employs a machine learning algorithm to identify blood vessel automatically in 3D OCT image, in a manner that does not rely on retinal layer segmentation.

Blood vessel segmentation with three-dimensional spectral domain optical coherence tomography

In a first exemplary embodiment of the present invention, an automated, computerized method is provided for processing an image. According to a feature of the present invention, the method comprises the steps of providing an image file depicting an image, in a computer memory, assembling a feature vector for the image file, the feature vector containing information regarding a likelihood that a selected pair of regions of the image file are of a same intrinsic characteristic, providing a classifier derived from a computer learning technique, computing a classification score for the selected pair of regions of the image file, as a function of the feature vector and the classifier and classifying the regions as being of the same intrinsic characteristic, as a function of the classification score.

Method and system for learning a same-material constraint in an image

A method of partitioning a weighted combinatorial graph representative of a dataset consists of the steps of generating a generalized Laplacian matrix corresponding to the combinatorial graph, computing the eigenstructure of the generalized Laplacian matrix, determining if an end criterion is satisfied using the eigenstructure, and if the end criterion is not satisfied, calculating new values for at least some of the plurality of weighting factors using the eigenstructure, updating the combinatorial graph with the new values for at least some of the weighting factors, and returning to the generating step.

Method for partitioning combinatorial graphs

In a first exemplary embodiment of the present invention, an automated, computerized method is provided for processing an image. According to a feature of the present invention, the method comprises the steps of providing an image file depicting an image, in a computer memory, forming a set of selectively varied representations of the image file and performing an image segregation operation on at least one preselected representation of the image of the image file, to generate intrinsic images corresponding to the image. According to a feature of the exemplary embodiment of the present invention, the selectively varied representations comprise multi-resolution representations such as a scale-spaced pyramid of representations. In a further feature of the exemplary embodiment of the present invention, the intrinsic images comprise a material image and an illumination image.

Multi-resolution analysis in image segregation

In an exemplary embodiment of the present invention, a test bed for optimizing an image segregation is provided. According to a feature of the present invention, the test bed comprises a memory storing an image file containing an image, a set of operations, a set of constraint software modules and a set of parameters relevant to the image, a transform module for performing a preselected one of the set of operations, defined by a preselected one of the set of constraint software modules, on the image, as a function of preselected ones of the set of parameters, to provide an output image, a test module utilizing the transform module output image, an analysis module for analyzing test module performance, and a feedback loop for varying selected ones of the operations, constraint software modules and parameters, for input to the transform module, to provide a new output image for input to the test module.

Test bed for optimizing an image segregation

In an exemplary embodiment of the present invention, an automated, computerized method is provided for processing an image. According to a feature of the present invention, the method comprises the steps of providing an image, organizing spatio-spectral information for the image in a matrix equation expressed by: [A][x]=[b], wherein [A] expresses values determined by a constraining relationship imposed upon the spatio-spectral information, [b] expresses recorded information for the image, and [x] expresses an unknown material/illumination component of the image, and utilizing the matrix equation in an image segregation operation.

Constraint generation for use in image segregation

In an exemplary embodiment of the present invention, an automated, computerized method is provided for processing an image. According to a feature of the present invention, the method comprises the steps of generating spatio-spectral information for the image, defining a constraint as a function of the spatio-spectral information, and performing an optimization operation as a function of the constraint to generate an intrinsic image corresponding to the image.

Image segregation system architecture

Growing community of inventors

Pittsburgh, PA, United States of America

David Tolliver