System and method for using a similarity function to perform appearance matching in image pairs
View Patent ↗The present invention is directed to a method for populating a database with a set of images of an anatomical structure. The database is used to perform appearance matching in image pairs of the anatomical structure. A set of image pairs of anatomical structures is received, where each image pair is annotated with a plurality of location-sensitive regions that identify a particular aspect of the anatomical structure. Weak learners are iteratively selected and an image patch is identified. A boosting process is used to identify a strong classifier based on responses to the weak learners applied to the identified image patch for each image pair. The responses comprise a feature response and a location response associated with the image patch. Positive and negative image pairs are generated. The positive and negative image pairs are used to learn a similarity function. The learned similarity function and iteratively selected weak learners are stored in the database.
1. A method for estimating the motion of an anatomical structure in a video sequence, the method comprising the steps of:
receiving a video sequence comprising a plurality of sequential images of an anatomical structure;
initializing a first image in the video with a plurality of control points that are associated with a corresponding image patch;
using a boosting algorithm to learn a similarity function by selectively combining weak learners that are associated with the image patch;
using the learned similarity function to identify a location in subsequent image frames of the video sequence that corresponds to the control points; and
using the identified location to track motion of the anatomical structure within the video sequence,
wherein the above steps are performed using a computer.
2. The method of claim 1 wherein the anatomical structure is a left ventricle and the plurality of control points identify a contour of the ventricle.
3. A system for estimating the motion of an anatomical structure, the system comprising:
a database that stores a set of image pairs of anatomical structures, each image pair being annotated with a plurality of location-sensitive regions that identify a particular aspect of the anatomical structure;
a processor that receives an input video sequence comprising a plurality of sequential images of an anatomical structure, the processor performing the following steps:
initializing a first image in the video with a plurality of control points that are associated with a corresponding image patch;
using a boosting algorithm to learn a similarity function by selectively combining weak learners that are associated with the image patch;
using the learned similarity function to identify a location in subsequent image frames of the video sequence that corresponds to the control points; and
using the identified location to track motion of the anatomical structure within the video sequence; and
a display to display the tracked anatomical structure.
4. The system of claim 3 wherein the anatomical structure is a left ventricle and the plurality of control points identify a contour of the ventricle.