Method for determining the contour of an in vivo organ using multiple image frames of the organ
First Claim
1. A method for automatically determining a contour of an internal organ based upon digital image data of a region in which the organ is disposed, said image data representing a sequence of image frames of the region made over an interval of time during which a wall of the organ has completed at least one cycle of movement, the wall of the organ undergoing repetitive cycles of movement as part of the organ'"'"'s physiological function, each image frame of said sequence of image frames comprising a plurality of pixels, said method comprising the steps of:
- (a) developing an initial estimate of a region bounded by the contour of the organ in each image frame of the sequence, based upon a comparison of the image data with parameters derived from training data that were previously produced through manual evaluation of a plurality of image frames over a corresponding cycle for each of a plurality of corresponding organs in other individuals, said parameters derived from the training data being used to assign classes to the pixels comprising each of the image frames of the sequence, said classes indicating pixels that are most likely inside the contour of the organ in each image frame; and
(b) using boundary motion data that were previously developed through manual evaluation of the corresponding organs in other individuals, refining the initial estimate of the region in each image frame of the sequence to determine the contour, said boundary motion data establishing an allowed range of motion of the contour between subsequent image frames of the sequence.
3 Assignments
0 Petitions
Accused Products
Abstract
A method for automatically evaluating image data taking over a sequence of image frames to determine a contour of a left ventricle (LV). The sequence of image frames are converted to digital data that identify a gray scale value for each pixel in each image frame. Using probability, an initial LV region is estimated based upon previously determined a priori parameters that are derived from processing manually drawn contours of the LV in other hearts, for the sequence of image frames being analyzed. The initial estimate of the LV region is refined using motion constraints, which are also derived from training data determined from the manually-drawn contours of other hearts. An LV region is estimated and its coordinates are extracted for use in applying global shape constraints that provide a more accurate LV boundary estimate for the region around an apex of the left ventricle. Finally, the estimated LV boundary estimate is tested for consistency, yielding an accepted estimate, or warning that the estimate is unreliable. The resulting automatically determined contours of each image frame can be displayed almost immediately after the image data are produced so that a physician can more readily diagnose physiological defects of the heart.
133 Citations
22 Claims
-
1. A method for automatically determining a contour of an internal organ based upon digital image data of a region in which the organ is disposed, said image data representing a sequence of image frames of the region made over an interval of time during which a wall of the organ has completed at least one cycle of movement, the wall of the organ undergoing repetitive cycles of movement as part of the organ'"'"'s physiological function, each image frame of said sequence of image frames comprising a plurality of pixels, said method comprising the steps of:
-
(a) developing an initial estimate of a region bounded by the contour of the organ in each image frame of the sequence, based upon a comparison of the image data with parameters derived from training data that were previously produced through manual evaluation of a plurality of image frames over a corresponding cycle for each of a plurality of corresponding organs in other individuals, said parameters derived from the training data being used to assign classes to the pixels comprising each of the image frames of the sequence, said classes indicating pixels that are most likely inside the contour of the organ in each image frame; and (b) using boundary motion data that were previously developed through manual evaluation of the corresponding organs in other individuals, refining the initial estimate of the region in each image frame of the sequence to determine the contour, said boundary motion data establishing an allowed range of motion of the contour between subsequent image frames of the sequence. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10)
-
-
11. A method for determining the contour of a chamber in an in vivo heart, based on image data of the heart that include a plurality of image frames made during at least one cardiac cycle of the heart, said plurality of image frames including a region of interest in which the chamber is disposed and being recorded at substantially equally spaced intervals of time during the cardiac cycle, each image frame comprising a plurality of pixels, and each pixel having a gray, scale value associated with it, said method comprising the steps of:
-
(a) classifying the pixels in each image frame of the in vivo heart to determine an initial estimate of a region bounded by the contour using training data derived by manually determining contours of corresponding chambers in a plurality of other hearts, thereby indicating whether the pixels in the image frames for the in vivo heart are more likely to be inside the contour or more likely to be outside the contour of the chamber, as a function of a probability, the probability being dependent upon the gray scale values for the pixels in successive image frames in relation to the training data; and (b) refining the initial estimate of the region bounded by the contour of the chamber of the in vivo heart by applying motion constraints to a plurality of spaced-apart points around said contour, for successive image frames, said motion constraints determining limits for movement of each point on the contour, between successive image frames. - View Dependent Claims (12, 13, 14, 15, 16, 17, 18, 19)
-
-
20. A method for diagnostically analyzing and evaluating physiological functions of an in vivo organ, based upon contours of the organ that are determined automatically at different times, comprising the steps of:
-
(a) producing digital image data representing a sequence of image frames of a region in which the organ is disposed, each image frame of said sequence of image frames comprising a plurality of pixels and said sequence of image frames being made over an interval of time during which the organ has completed at least one cycle of a cyclical activity that it undergoes as part of a physiological function of the organ; (b) using training data derived from imaging a plurality of other corresponding organs and manually determining contours for each of the corresponding organs, automatically determining a contour of the in vivo organ in the plurality of image frames during at least one cardiac cycle; and (c) by comparing changes in position of the contour that was automatically determined in sequential image frames, evaluating the physiological function of the organ to detect abnormalities in motion indicative of disease or malfunction. - View Dependent Claims (21, 22)
-
Specification