System and method for a semi-automatic quantification of delayed enchancement images
AssigneeSiemens Medical Solutions USA, Inc.
InventorsThomas O'Donnell, Engin DiKici, Randolph M. Setser, Richard D. White
Life of this patent
Estimating the term…
Abstract
A method and device for image processing to determine image characteristics includes operations of segmenting of first images to create segmentation contours corresponding to the first images; and registering the segmented first images to second images. Further, operations of transferring the segmentation contours from the first images to second images; and fitting the transferred segmentation contours in the second images are performed.
Claims23
A method for processing images to determine image characteristics, the method comprising:
- segmenting one or more first images to create one or more segmentation contours corresponding to the first images;
- registering the segmented first images to one or more second images, wherein the first images and the second images have substantially the same position and phase;
- transferring the segmentation contours from the first images to second images;
- and
- fitting the transferred segmentation contours in the second images,
- wherein the first images comprise one or more Cine MR (Magnetic Resonance) images and the second images comprise one or more DEMR (Delayed Enhancement Magnetic Resonance) viability images, and wherein the step of registering comprises registering one or more Cine MR images surrounding the viability image to create at least one deformation field, and interpolating at least one of the segmentation contours to a phase of the viability image using the deformation field to create a prior model.
The method of claim1, wherein the step of fitting further comprises:
- creating one or more energy field images to fit the prior model to a given one of the viability images;
- and
- fitting the prior model to the energy field images that include one or more energy fields.
A method for processing one or more Cine MR (Magnetic Resonance) images that include one or more corresponding cine images and at least one Delayed Enhancement Magnetic Resonance (DEMR) viability image to analyze a candidate, the method comprising:
- segmenting the Cine MR images to create one or more segmentation contours;
- deforming the segmentation contour such that it is interpolated to appear as it would for a phase corresponding to the viability image's phase to generate a prior model;
- localizing the candidate in the viability image by registering the corresponding cine images to the viability image;
- creating one or more energy fields image to fit the prior model to the viability image;
- fitting the prior model to the energy field images using one or more transformations;
- and
- classifying the candidate using a classifier in the processed viability images that include the fitted prior model.
A program storage device readable by machine, tangibly embodying a program of instructions executable by the machine to perform method steps for image processing to determine image characteristics, the method steps comprising:
- segmenting one or more first images to create one or more segmentation contours corresponding to the first images;
- registering the segmented first images to one or more second images, wherein the first images and the second images have substantially the same position and phase;
- transferring the segmentation contours from the first images to second images;
- and
- fitting the transferred segmentation contours in the second images,
- wherein the first images comprise one or more Cine MR (Magnetic Resonance) images and the second images comprise one or more DEMR (Delayed Enhancement Magnetic Resonance) viability images, and wherein the step of registering comprises instructions for registering one or more Cine MR images surrounding the viability image to create at least one deformation field, wherein the viability image has a predetermined position corresponding to a location within the Cine MR images;
- and intepolating at least one of the segmentation contours to the viability images using the deformation field to create a prior model.
Dependencies are inferred from the claim text.