The synergy of 3D SIFT and sparse codes for classification of viewpoints from echocardiogram videos
Conference item
Qian, Y., Wang, L., Wang, C. and Gao, X. 2013. The synergy of 3D SIFT and sparse codes for classification of viewpoints from echocardiogram videos. Greenspan, H., Müller, H. and Syeda-Mahmood, T. (ed.) 3rd MICCAI International Workshop on Medical Content-Based Retrieval for Clinical Decision Support. Nice, France 01 - 01 Oct 2012 Berlin, Heidelberg Springer. https://doi.org/10.1007/978-3-642-36678-9_7
Title | The synergy of 3D SIFT and sparse codes for classification of viewpoints from echocardiogram videos |
---|---|
Authors | Qian, Y., Wang, L., Wang, C. and Gao, X. |
Abstract | Echocardiography plays an important part in diagnostic aid in cardiology. During an echocardiogram exam images or image sequences are usually taken from different locations with various directions in order to comprehend a comprehensive view of the anatomical structure of the 3D moving heart. The automatic classification of echocardiograms based on the viewpoint constitutes an essential step in a computer-aided diagnosis. The challenge remains the high noise to signal ratio of an echocardiography, leading to low resolution of echocardiograms. In this paper, a new synergy is proposed based on well-established algorithms to classify view positions of echocardiograms. Bags of Words (BoW) are coupled with linear SVMs. Sparse coding is employed to train an echocardiogram video dictionary based on a set of 3D SIFT descriptors of space-time interest points detected by a Cuboid detector. Multiple scales of max pooling features are applied to representat the echocardiogram video. The linear multiclass SVM is employed to classify echocardiogram videos into eight views. Based on the collection of 219 echocardiogram videos, the evaluation is carried out. The preliminary results exhibit 72% Average Accuracy Rate (AAR) for the classification with eight view angles and 90% with three primary view locations. |
Keywords | 3D SIFT; Classification of Echocardiogram Video; Cuboid Detector; Sparse Coding; SVM |
Research Group | Artificial Intelligence group |
Conference | 3rd MICCAI International Workshop on Medical Content-Based Retrieval for Clinical Decision Support |
Proceedings Title | Medical Content-Based Retrieval for Clinical Decision Support Third MICCAI International Workshop, MCBR-CDS 2012, Nice, France, October 1st, 2012, Revised Selected Papers |
Series | Lecture Notes in Computer Science |
Editors | Greenspan, H., Müller, H. and Syeda-Mahmood, T. |
ISSN | 0302-9743 |
Electronic | 1611-3349 |
ISBN | |
Paperback | 9783642366772 |
Electronic | 9783642366789 |
Publisher | Springer |
Place of publication | Berlin, Heidelberg |
Publication process dates | |
Deposited | 01 Apr 2013 |
Output status | Published |
Digital Object Identifier (DOI) | https://doi.org/10.1007/978-3-642-36678-9_7 |
Scopus EID | 2-s2.0-84874424795 |
Language | English |
https://repository.mdx.ac.uk/item/83z76
58
total views0
total downloads0
views this month0
downloads this month