DeepHeartBeat: Latent trajectory learning of cardiac cycles using cardiac ultrasounds

Fabian Laumer, Gabriel Fringeli, Alina Dubatovka, Laura Manduchi, Joachim M. Buhmann
Proceedings of the Machine Learning for Health NeurIPS Workshop, PMLR 136:194-212, 2020.

Abstract

Echocardiography monitors the heart movement for noninvasive diagnosis of heart diseases. It proves to be of profound practical importance as it combines low-cost portable instrumentation and rapid image acquisition without the risks of ionizing radiation. However, echocardiograms produce high-dimensional, noisy data which frequently proved difficult to interpret. As a solution, we propose a novel autoencoder-based framework, DeepHeartBeat, to learn human interpretable representations of cardiac cycles from cardiac ultrasound data. Our model encodes high dimensional observations by a cyclic trajectory in a lower dimensional space. We show that the learned parameters describing the latent trajectory are well interpretable and we demonstrate the versatility of our model by successfully applying it to various cardiologically relevant tasks, such as ejection fraction prediction and arrhythmia detection. As a result, DeepHeartBeat promises to serve as a valuable assistant tool for automating therapy decisions and guiding clinical care.

Cite this Paper

BibTeX
@InProceedings{pmlr-v136-laumer20a, title = {DeepHeartBeat: Latent trajectory learning of cardiac cycles using cardiac ultrasounds}, author = {Laumer, Fabian and Fringeli, Gabriel and Dubatovka, Alina and Manduchi, Laura and Buhmann, Joachim M.}, booktitle = {Proceedings of the Machine Learning for Health NeurIPS Workshop}, pages = {194--212}, year = {2020}, editor = {Alsentzer, Emily and McDermott, Matthew B. A. and Falck, Fabian and Sarkar, Suproteem K. and Roy, Subhrajit and Hyland, Stephanie L.}, volume = {136}, series = {Proceedings of Machine Learning Research}, month = {11 Dec}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v136/laumer20a/laumer20a.pdf}, url = {https://proceedings.mlr.press/v136/laumer20a.html}, abstract = {Echocardiography monitors the heart movement for noninvasive diagnosis of heart diseases. It proves to be of profound practical importance as it combines low-cost portable instrumentation and rapid image acquisition without the risks of ionizing radiation. However, echocardiograms produce high-dimensional, noisy data which frequently proved difficult to interpret. As a solution, we propose a novel autoencoder-based framework, DeepHeartBeat, to learn human interpretable representations of cardiac cycles from cardiac ultrasound data. Our model encodes high dimensional observations by a cyclic trajectory in a lower dimensional space. We show that the learned parameters describing the latent trajectory are well interpretable and we demonstrate the versatility of our model by successfully applying it to various cardiologically relevant tasks, such as ejection fraction prediction and arrhythmia detection. As a result, DeepHeartBeat promises to serve as a valuable assistant tool for automating therapy decisions and guiding clinical care.} }
Endnote
%0 Conference Paper %T DeepHeartBeat: Latent trajectory learning of cardiac cycles using cardiac ultrasounds %A Fabian Laumer %A Gabriel Fringeli %A Alina Dubatovka %A Laura Manduchi %A Joachim M. Buhmann %B Proceedings of the Machine Learning for Health NeurIPS Workshop %C Proceedings of Machine Learning Research %D 2020 %E Emily Alsentzer %E Matthew B. A. McDermott %E Fabian Falck %E Suproteem K. Sarkar %E Subhrajit Roy %E Stephanie L. Hyland %F pmlr-v136-laumer20a %I PMLR %P 194--212 %U https://proceedings.mlr.press/v136/laumer20a.html %V 136 %X Echocardiography monitors the heart movement for noninvasive diagnosis of heart diseases. It proves to be of profound practical importance as it combines low-cost portable instrumentation and rapid image acquisition without the risks of ionizing radiation. However, echocardiograms produce high-dimensional, noisy data which frequently proved difficult to interpret. As a solution, we propose a novel autoencoder-based framework, DeepHeartBeat, to learn human interpretable representations of cardiac cycles from cardiac ultrasound data. Our model encodes high dimensional observations by a cyclic trajectory in a lower dimensional space. We show that the learned parameters describing the latent trajectory are well interpretable and we demonstrate the versatility of our model by successfully applying it to various cardiologically relevant tasks, such as ejection fraction prediction and arrhythmia detection. As a result, DeepHeartBeat promises to serve as a valuable assistant tool for automating therapy decisions and guiding clinical care.
APA
Laumer, F., Fringeli, G., Dubatovka, A., Manduchi, L. & Buhmann, J.M.. (2020). DeepHeartBeat: Latent trajectory learning of cardiac cycles using cardiac ultrasounds. Proceedings of the Machine Learning for Health NeurIPS Workshop, in Proceedings of Machine Learning Research 136:194-212 Available from https://proceedings.mlr.press/v136/laumer20a.html.

Related Material