Modeling the Activity Pattern of the Constellation of Cardiac Chambers in Echocardiogram Videos
A novel approach is presented for modeling the complex activity pattern of the heart in echocardiogram videos. In this approach, the heart is represented by the constellation of its chambers, where the constellation is modeled by pictorial structure at each instance in time. Pictorial structure is then extended to the temporal domain to simultaneously capture the evolution pattern of the appearance of each chamber, the evolving spatial relationships between them, and the topological transformations in their constellation due to phase transitions. Inference and learning algorithms are presented for the model. The problem of correspondence is solved at each stage of the inference process, by matching the evolving model of the complex activity pattern to the observed constellations. The model, which is trained using examples of normal echocardiogram videos is shown to be efficient in temporal segmentation of the content of echocardiogram videos into different phases during one cycle of heart activity.
KeywordsActivity Pattern Cardiac Chamber Dynamic Bayesian Network Topological Transformation Temporal Segmentation
Unable to display preview. Download preview PDF.
- 1.Feigenbaum, H.: Echocardiography. LeaFebiger (1993)Google Scholar
- 2.Ebadollahi, S., Chang, S.F., Wu, H.: Automatic View Recognition in Echocardiogram Videos Using Parts-Based Representation. In: Proceeding of IEEE International Conference on Computer Vision and Pattern Recognition, pp. 2–9 (2004)Google Scholar
- 3.Fergus, R., Perona, P., Zisserman, A.: Object Class Recognition by Unsupervised Scale-Invariant Learning. In: Proceeding of IEEE Conference on Computer Vision and Pattern Recognition (2003)Google Scholar
- 4.Felzenszwalb, P., Huttenlocher, D.: Efficient Matching of Pictorial Structures. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 66–73 (2000)Google Scholar
- 5.Pavlovic, V., Rehg, J.M., MacCormick, J.: Learning Switching Linear Models of Human Motion. In: Proceedings of the Advances in Neural Information Processing Systems (NIPS), pp. 981–987 (2000)Google Scholar
- 7.Hamid, R., Huang, Y., Essa, I.: ARGMode-Activity Recognition using Graphical Models. In: Proceedings of the 2nd IEEE Workshop on Detection and Recognition of Events in Video, Madison, Wisconsin (2003)Google Scholar
- 8.Wang, Y., Zhu, S.C.: Modeling Complex Motion by Tracking and Editing Hidden Markov Graphs. In: Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2004), vol. 1, pp. 856–863 (2004)Google Scholar
- 12.Ghahramani, Z., Hinton, G.E.: Parameter Estimation for Linear Dynamical Systems. Technical Report CRG-TR-96-2 (1996)Google Scholar