Echocardiogram view classification using low-level features
Lists
Only you see this
Abstract
This paper presents a view classification method for 2D heart ultrasound. Our method uses low-level image features to train a frame-level classifier, which unlike related approaches, does not require an additional pixel-level classification of heart structures. By employing kernel-based classification, our algorithm can classify images from any phase of the heartbeat cycle and efficiently incorporate information from subsequent frames without re-training the model. On real-world data, our algorithm achieves 98.51% accuracy for 8-way classification. While the method can efficiently aggregate multiple frames, in ~94% of the tests, identification only requires a single frame.
BibTeX
@inproceedings{wu2013echocardiogram,
author = {Hui Wu and Dustin M. Bowers and Toan T. Huynh and Richard Souvenir},
title = {{Echocardiogram view classification using low-level features}},
booktitle = {ISBI},
year = {2013},
url = {https://openreview.net/forum?id=AVWS4V63GfBs},
}Loading related content...