Segmentation of 3D radio frequency echocardiography using a spatio-temporal predictor

Pearlman, P.C.; Tagare, H.D.; Lin, B.A.; Sinusas, A.J.; Duncan, J.S.

doi:10.1016/j.media.2011.09.002

« Previous Next »Medical Image Analysis
Volume 16, Issue 2 , Pages 351-360, February 2012

Segmentation of 3D radio frequency echocardiography using a spatio-temporal predictor

P.C. Pearlman
- Department of Electrical Engineering, Yale University, New Haven, CT 06520-8042, USA
- Corresponding author. Present address: University Medical Center Utrecht, 3508 GA, Utrecht, The Netherlands. Tel.:+31 88 75 56053.
H.D. Tagare
- Department of Electrical Engineering, Yale University, New Haven, CT 06520-8042, USA
- Department of Biomedical Engineering, Yale University, New Haven, CT 06520, USA
- Department of Diagnostic Radiology, Yale University, New Haven, CT 06520, USA
B.A. Lin
- Department of Internal Medicine, Yale University, New Haven, CT 06520, USA
A.J. Sinusas
- Department of Diagnostic Radiology, Yale University, New Haven, CT 06520, USA
- Department of Internal Medicine, Yale University, New Haven, CT 06520, USA
J.S. Duncan
- Department of Electrical Engineering, Yale University, New Haven, CT 06520-8042, USA
- Department of Biomedical Engineering, Yale University, New Haven, CT 06520, USA
- Department of Diagnostic Radiology, Yale University, New Haven, CT 06520, USA

Received 28 January 2011; received in revised form 30 August 2011; accepted 14 September 2011. published online 17 October 2011.

Graphical abstract

- View Large Image
- Download to PowerPoint

Highlights

► We segment left ventricular endocardial boundaries from RF ultrasound. ► Our M.A.P. segmentation uses a joint spatial model and a multiframe conditional. ► The conditional model relates neighboring frames using a linear predictor. ► The linear predictor exploits spatio-temporal coherence in the data. ► We overcome problems due to image inhomogeneities amplified in B-mode segmentation.

Abstract

This paper presents an algorithm for segmenting left ventricular endocardial boundaries from RF ultrasound. Our method incorporates a computationally efficient linear predictor that exploits short-term spatio-temporal coherence in the RF data. Segmentation is achieved jointly using an independent identically distributed (i.i.d.) spatial model for RF intensity and a multiframe conditional model that relates neighboring frames in the image sequence. Segmentation using the RF data overcomes challenges due to image inhomogeneities often amplified in B-mode segmentation and provides geometric constraints for RF phase-based speckle tracking. The incorporation of multiple frames in the conditional model significantly increases the robustness and accuracy of the algorithm. Results are generated using between 2 and 5 frames of RF data for each segmentation and are validated by comparison with manual tracings and automated B-mode boundary detection using standard (Chan and Vese-based) level sets on echocardiographic images from 27 3D sequences acquired from six canine studies.

Keywords: Ultrasound, Cardiac imaging, Segmentation, Radiofrequency signal