Shape-Based Retrieval of Heart Sounds for Disease Similarity Detection

Abstract

Retrieval of similar heart sounds from a sound database has applications in physician training, diagnostic screening, and decision support. In this paper, we exploit a visual rendering of heart sounds and model the morphological variations of audio envelopes through a constrained non-rigid translation transform. Similar heart sounds are then retrieved by recovering the corresponding alignment transform using a variant of shape-based dynamic time warping. Results of similar heart sound retrieval are demonstrated for various diseases on a large database of heart sounds.

Cite

Text

Syeda-Mahmood and Wang. "Shape-Based Retrieval of Heart Sounds for Disease Similarity Detection." European Conference on Computer Vision, 2008. doi:10.1007/978-3-540-88688-4_42

Markdown

[Syeda-Mahmood and Wang. "Shape-Based Retrieval of Heart Sounds for Disease Similarity Detection." European Conference on Computer Vision, 2008.](https://mlanthology.org/eccv/2008/syedamahmood2008eccv-shape/) doi:10.1007/978-3-540-88688-4_42

BibTeX

@inproceedings{syedamahmood2008eccv-shape,
  title     = {{Shape-Based Retrieval of Heart Sounds for Disease Similarity Detection}},
  author    = {Syeda-Mahmood, Tanveer Fathima and Wang, Fei},
  booktitle = {European Conference on Computer Vision},
  year      = {2008},
  pages     = {568-581},
  doi       = {10.1007/978-3-540-88688-4_42},
  url       = {https://mlanthology.org/eccv/2008/syedamahmood2008eccv-shape/}
}