Scholars@Duke publication: Learning optical flow propagation strategies using random forests for fast segmentation in dynamic 2D & 3D echocardiography

Learning optical flow propagation strategies using random forests for fast segmentation in dynamic 2D & 3D echocardiography

Publication , Conference

Verhoek, M; Yaqub, M; McManigle, J; Noble, JA

Fast segmentation of the left ventricular (LV) myocardium in 3D+time echocardiographic sequences can provide quantitative data of heart function that can aid in clinical diagnosis and disease assessment. We present an algorithm for automatic segmentation of the LV myocardium in 2D and 3D sequences which employs learning optical flow (OF) strategies. OF motion estimation is used to propagate single-frame segmentation results of the Random Forest classifier from one frame to the next. The best strategy for propagating between frames is learned on a per-frame basis. We demonstrate that our algorithm is fast and accurate. We also show that OF propagation increases the performance of the method with respect to the static baseline procedure, and that learning the best OF propagation strategy performs better than single-strategy OF propagation.

Duke Scholars

Author John McManigle Anesthesiology, Pediatrics

ISBN

978-3-642-24318-9

Start / End Page

75 / 82

Publisher

Springer Berlin Heidelberg

Related Subject Headings

Artificial Intelligence & Image Processing
46 Information and computing sciences

Citation

APA

Chicago

ICMJE

MLA

NLM

Verhoek, M., Yaqub, M., McManigle, J., & Noble, J. A. (n.d.). Learning optical flow propagation strategies using random forests for fast segmentation in dynamic 2D & 3D echocardiography. In K. Suzuki, F. Wang, D. Shen, & P. Yan (Eds.) (pp. 75–82). Springer Berlin Heidelberg.

Verhoek, Michael, Mohammad Yaqub, John McManigle, and J Alison Noble. “Learning optical flow propagation strategies using random forests for fast segmentation in dynamic 2D & 3D echocardiography.” edited by Kenji Suzuki, Fei Wang, Dinggang Shen, and Pingkun Yan, 75–82. Springer Berlin Heidelberg, n.d.

Verhoek M, Yaqub M, McManigle J, Noble JA. Learning optical flow propagation strategies using random forests for fast segmentation in dynamic 2D & 3D echocardiography. In: Suzuki K, Wang F, Shen D, Yan P, editors. Springer Berlin Heidelberg; p. 75–82.

Verhoek, Michael, et al. Learning optical flow propagation strategies using random forests for fast segmentation in dynamic 2D & 3D echocardiography. Edited by Kenji Suzuki et al., Springer Berlin Heidelberg, pp. 75–82.