engleski

Optical flow algorithm for cardiac motion estimation

East Adriatic coast is characterized by a large Diagnostic techniques in cardiology require complex image analysis of single images and image sequences obtained by a variety of medical imaging modalities such as ECG-gated MR,CT,and ultrasound.Cardiac motion estimation provides useful information about cardiac func- tion.In this work,we present a novel brightness-based al- gorithm for computation of optical flow.The advantage of brightness-based techniques as opposed to shape-based tech- niques is that they do not require segmentation of images to obtain the shape of various heart regions.The proposed optical flow algorithm is applied to ECG-gated MR image sequence of the heart.The method used in this work is based on minimization of an energy function that is com- puted for two consecutive image frames.The energy func- tion consists of two terms.The first energy term represents a measure of similarity between the regions in two image frames.The second energy term calculates the neighbor- hood in fluence and is increased based on the di fference in velocities and the cross-correlation of neighboring regions. The regions are dinamically grown and are of variable size. The minimal energy state corresponds to the optimal so- lution of the optical flow estimation problem.The energy function minimization is based on a steepest descent algo- rithm.The proposed algorithm has been implemented in C language and tested on mathematical phantoms and real pa- tient images.Experiments have shown encouraging results.

cardiac image analysis;optical flow;velocity field

nije evidentirano