Optimal registration of multiple deformed images using a physical model of the imaging distortion
AssigneeUniversity of Iowa Research Foundation
InventorsMichael Abramoff, Meindert Niemeijer, Sangyeol Lee, Joseph Reinhardt
Life of this patent
Estimating the term…
Abstract
Methods and systems for image registration implementing a feature-based strategy that uses a retinal vessel network to identify features, uses an affine registration model estimated using feature correspondences, and corrects radial distortion to minimize the overall registration error. Also provided are methods and systems for retinal atlas generation. Further provided are methods and systems for testing registration methods.
Claims27
A method for image distortion correction, comprising:
- receiving a target image and a reference image;
- correcting radial distortion in the target image and the reference image according to a distortion parameter;
- detecting feature correspondence points in the distortion corrected target image and the distortion corrected reference image;
- initializing an affine registration model with the feature correspondence points;
- minimizing vessel centerline error measure (CEM) between the distortion corrected target image and the distortion corrected reference image to determine an optimal distortion parameter and an optimal affine registration model;
- correcting radial distortion in the target image and the reference image according to the optimal distortion parameter;
- applying an affine transform to the optimally distortion corrected target image and the optimally distortion corrected reference image according to the optimal affine registration model;
- combining the transformed optimally distortion corrected target image and the transformed optimally distortion corrected reference image into a montage image;
- and
- outputting the montage image.
A method for generating a retinal atlas, comprising:
- defining a retinal atlas coordinate system;
- receiving a plurality of fundus images;
- performing registration within the plurality of fundus images, resulting in a plurality of registered fundus images;
- performing landmark selection within the plurality of registered fundus images;
- performing atlas coordinate mapping within the plurality of registered fundus images, resulting in a retinal atlas;
- and
- outputting the retinal atlas.
A retinal atlas, comprising:
- an atlas coordinate system;
- and
- a plurality of registered pairs of fundus images mapped to the atlas coordinate system, wherein mapping the plurality of registered pairs of fundus images comprises
- performing landmark selection within the plurality of registered pairs of fundus images, and
- mapping the plurality of registered pairs of fundus images to the atlas coordinate system according to the landmark selection.
A computer readable medium having computer executable instructions embodied thereon for image distortion correction, comprising:
- receiving a target image and a reference image;
- correcting radial distortion in the target image and the reference image according to a distortion parameter;
- detecting feature correspondence points in the distortion corrected target image and the distortion corrected reference image;
- initializing an affine registration model with the feature correspondence points;
- minimizing vessel centerline error measure (CEM) between the distortion corrected target image and the distortion corrected reference image to determine an optimal distortion parameter and an optimal affine registration model;
- correcting radial distortion in the target image and the reference image according to the optimal distortion parameter;
- applying an affine transform to the optimally distortion corrected target image and the optimally distortion corrected reference image according to the optimal affine registration model;
- combining the transformed optimally distortion corrected target image and the transformed optimally distortion corrected reference image into a montage image;
- and
- outputting the montage image.
A computer readable medium for generating a retinal atlas, comprising:
- defining a retinal atlas coordinate system;
- receiving a plurality of fundus images;
- performing registration within the plurality of fundus images, resulting in a plurality of registered fundus images;
- performing landmark selection within the plurality of registered fundus images;
- performing atlas coordinate mapping within the plurality of registered fundus images, resulting in a retinal atlas;
- and
- outputting the retinal atlas.
A system for image distortion correction, comprising:
- a memory, configured for storing image data;
- and
- a processor, coupled to the memory, configured for
- receiving a target image and a reference image,
- correcting radial distortion in the target image and the reference image according to a distortion parameter,
- detecting feature correspondence points in the distortion corrected target image and the distortion corrected reference image,
- initializing an affine registration model with the feature correspondence points,
- minimizing vessel centerline error measure (CEM) between the distortion corrected target image and the distortion corrected reference image to determine an optimal distortion parameter and an optimal affine registration model,
- correcting radial distortion in the target image and the reference image according to the optimal distortion parameter,
- applying an affine transform to the optimally distortion corrected target image and the optimally distortion corrected reference image according to the optimal affine registration model,
- combining the transformed optimally distortion corrected target image and the transformed optimally distortion corrected reference image into a montage image, and
- outputting the montage image.
A system for generating a retinal atlas, comprising:
- a memory, configured for storing image data;
- and
- a processor, coupled to the memory, configured for
- defining a retinal atlas coordinate system,
- receiving a plurality of fundus images,
- performing registration within the plurality of fundus images, resulting in a plurality of registered fundus images,
- performing landmark selection within the plurality of registered fundus images,
- performing atlas coordinate mapping within the plurality of registered fundus images, resulting in a retinal atlas, and
- outputting the retinal atlas.
Dependencies are inferred from the claim text.