Features extraction and analysis methods for sequences of ultrasound images
Image and Vision Computing - Special issue: 2nd European Conference on Computer Vision
Recovery and Tracking of Continuous 3D Surfaces from Stereo Data Using a Deformable Dual-Mesh
ICCV '99 Proceedings of the International Conference on Computer Vision-Volume 2 - Volume 2
An Information Fusion Framework for Robust Shape Tracking
IEEE Transactions on Pattern Analysis and Machine Intelligence
| Hi-index | 0.00 |
This paper introduces a new ultrasound technique called acoustic flow which is the flow of the echoed acoustic signal amplitudes in time. Acoustic flow can be used for a wide variety of medical tasks that require analysis of structures in motion. Since it is designed specifically for ultrasound, we expect acoustic flow to be robust and efficient for the analysis of ultrasound image sequences. Estimation of the acoustic flow is performed by a novel method which is based on the optimization of a deformable mesh energy. This estimation method can impose both spatial and temporal smoothness on the extracted flow vectors. It is also efficient, intuitive, and fully automatic. We applied acoustic flow to echocardiographic image sequences. We used the variance of the acoustic flow vectors to visually validate our results. The extracted flow vectors were also used to estimate the distance of the heart center from the ultrasound transducer, which showed the effectiveness of the technique. Other application areas of acoustic flow are also proposed.