Image Velocity Estimation in Echocardiographs - Isis Project No 1283

A newly developed enhanced method for extracting cardiac boundary pixels from echocardiographic sequences.

Background

There are many instances in which a subject in an image is moving, and it is necessary to track the subject as it moves from frame to frame; this movement is known as optical flow or image velocity. Such measurement of optical flow may be done to improve the image encoding efficiency, or allow enhancement of the display of the movement of some particular tracked part of the image to assist an observer attempting to interpret the image. Optical flow determination methods fit into one of three groups: differential techniques, frequency based methods and matching techniques.

Problem

Medical images present many difficulties in image processing because of their typically high noise level. Thus, the tracking of cardiac walls in cardiac ultrasound images is difficult because of the inherent high level of noise found in such images and also because of the way in which cardiac motion varies during the cardiac cycle. Several means of identifying and tracking cardiac walls in echocardiograms have been proposed, but it is a difficult task which requires improvement.

The Oxford Invention

The Oxford invention for identifying boundary pixels in echocardiographic sequences or other ultrasound image sequences consists of a phase boundary detection stage followed by an optical flow estimation stage based on block matching methods. New contributions to these basic computer vision processes have resulted in a system that is both fast and robust.

Commercialisation Opportunity

This work is now the subject of a patent application, and Isis now wishes to discuss suitable arrangements with companies interested in developing and using this technology.

Keywords

echocardiographs, image velocity, cardiac, optical flow, ultrasound, boundary pixels, cardiac cycle, ultrasound image, medical image

Other Medical Imaging Projects

1260 - Breast Cancer Detection
1405 - Alignment of Multimodal Images
1487 - Lung Nodules Detection in CT Images
2158 - Automated Retinal Image Differencing (ARID)
2468 - Targeted Image Contrast Agent
2586 - Optimal Whole-Heart Ultrasound Imaging

Request Further Information: Project Number 1283 - Image Velocity Estimation in Echocardiographs