What is it about?

This works presents a novel algorithm for myocardial segmentation in 3D echocardiographic image sequences using a classification approach based on fractional Brownian motion (fBm) and a refinement stage using second-order moments.

Featured Image

Why is it important?

The topic of correct left ventricle segmentation in 3D echocardiographic images has been studied for several years now, and it is still an ongoing and open subject in the cardiology field. Despite the multitude of methodologies available in the literature, a sufficiently robust and accurate approach to completely replace the typical manual approach is still lacking.

Perspectives

Due to the nature of the speckle pattern, it is hard to draw conclusions about the boarder of the left ventricle (LV) from still frames. Thus, cardiologists usually examine videos of the deformation of the LV wall during the echocardiographic examination. It is logical to assume the speckle pattern structure is better localized when the spatio-temporal coherence is considered. Dealing with the LV segmentation problem from a spatio-temporal perspective can give further information on the shape boundaries. To our knowledge, this is the first time a spatio-temporal fBm process is used for LV segmentation in 3D ultrasound sequences. The algorithm was validated in synthetic and canine data, showing improved results against an algorithm from literature.

Dr Omar S Al-Kadi
University of Jordan

Read the Original

This page is a summary of: Spatio-Temporal Segmentation in 3D Echocardiographic Sequences using Fractional Brownian Motion, IEEE Transactions on Biomedical Engineering, January 2019, Institute of Electrical & Electronics Engineers (IEEE),
DOI: 10.1109/tbme.2019.2958701.
You can read the full text:

Read

Resources

Contributors

The following have contributed to this page