General Electric Company

London Health Sciences Centre Research Inc.

Ian Ross

Shuo Li

Richard Rankin

Ismail Ben Ayed

Kumaradevan Punithakumar

Ali Islam

Prakash Mahesh

Dave Roeder

Example methods, apparatus and articles of manufacture to process cardiac images to detect heart motion abnormalities are disclosed. A disclosed example method includes using a filter coefficient based on a plurality of cardiac images to characterize motion of a heart; computing an information-theoretic metric from the filter coefficient; and comparing the information-theoretic metric to a threshold to determine whether the motion of the heart is abnormal.

Methods, apparatus and articles of manufacture to process cardiac images to detect heart motion abnormalities

Example methods, apparatus and articles of manufacture to track endocardial motion are disclosed. A disclosed example method includes segmenting a plurality of cardiac images of a left ventricle to form respective ones of a plurality of segmented images, updating a plurality of models based on the plurality of segmented images to form respective ones of a plurality of motion estimates for the left ventricle, computing a plurality of probabilities for respective ones of the plurality of models, and computing a weighted sum of the plurality of motion estimates based on the plurality of probabilities, the weighted sum representing a predicted motion of the left ventricle.

Methods, apparatus and articles of manufacture to track endocardial motion

Example methods, apparatus and articles of manufacture to process cardiac images to detect heart motion abnormalities are disclosed. A disclosed example method includes adapting a state of a state-space model based on a plurality of cardiac images to characterize motion of a heart, computing an information-theoretic metric from the state of the state-space model, and comparing the information-theoretic metric to a threshold to determine whether the motion of the heart is abnormal.

Example methods and apparatus to process left-ventricle cardiac images are disclosed. A disclosed example method includes identifying a first landmark point in a first cardiac image, identifying a first centroid of a left ventricle depicted in the first cardiac image, and performing a Cartesian-to-polar transformation to form a first rectangular representation of the left ventricle depicted in the first cardiac image based on the first landmark point and the first centroid.

Methods and apparatus to process left-ventricle cardiac images

Certain embodiments of the present technology provide systems, methods and computer instructions for computer aided analysis of images. In certain embodiments, for example, such a method includes: isolating a motion area in an image; segmenting the image; utilizing a support vector machine to identify a region of interest in the image; utilizing a graph-cut algorithm to refine the region of interest; and verifying the region of interest. In certain embodiments, for example, such a method further includes: aligning a set of images and/or outputting a set of aligned images sequentially. In certain embodiments, the systems, methods and computer instructions disclosed herein can be used to aid analysis of cardiac images, for example. In certain embodiments, the systems, methods and computer instructions disclosed herein can be used to aid analysis of four dimensional images, for example.

Systems and methods for computer aided analysis of images

Image tracking as described herein can include: segmenting a first image into regions; determining an overlap of intensity distributions in the regions of the first image; and segmenting a second image into regions such that an overlap of intensity distributions in the regions of the second image is substantially similar to the overlap of intensity distributions in the regions of the first image. In certain embodiments, images can depict a heart at different points in time and the tracked regions can be the left ventricle cavity and the myocardium. In such embodiments, segmenting the second image can include generating first and second curves that track the endocardium and epicardium boundaries, and the curves can be generated by minimizing functions containing a coefficient based on the determined overlap of intensity distributions in the regions of the first image.

Growing community of inventors

London, Canada

Ian Ross