EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Abnormal Heart Sound Classification and Model Interpretability: A Transfer Learning Approach with Deep Learning

Milan Marocchi, Leigh Abbott, Yue Rong, Sven Nordholm, Girish Dwivedi

Journal of Vascular Diseases · 04.12.2023 · 2 (4) · 438-459

DOI: 10.3390/jvd2040034 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Vascular Diseases, online erschienen am 04.12.2023. Verfasst von Milan Marocchi und 4 weiteren Autor:innen. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 31 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Physician detection of heart sound abnormality is complicated by the inherent difficulty of detecting critical abnormalities in the presence of noise. Computer-aided heart auscultation provides a promising alternative for more accurate detection, with recent deep learning approaches exceeding expert accuracy. Although combining phonocardiogram (PCG) data with electrocardiogram (ECG) data provides more information to an abnormal heart sound classifier, the scarce presence of labelled datasets with this combination impedes training. This paper explores fine-tuning deep convolutional neural networks such as ResNet, VGG, and inceptionv3, on images of spectrograms, mel-spectrograms, and scalograms. By fine-tuning deep pre-trained models on image representations of ECG and PCG, we achieve 91.25% accuracy on the training-a dataset of the PhysioNet Computing in Cardiology Challenge 2016, compared to a previous result of 81.48%. Interpretation of the model’s learned features is also provided, with the results indicative of clinical significance.

Zitieren

APA

Marocchi, M., Abbott, L., Rong, Y., Nordholm, S., & Dwivedi, G. (2023). Abnormal Heart Sound Classification and Model Interpretability: A Transfer Learning Approach with Deep Learning. Journal of Vascular Diseases, 2(4), 438-459. https://doi.org/10.3390/jvd2040034

Vancouver

Marocchi M, Abbott L, Rong Y, Nordholm S, Dwivedi G. Abnormal Heart Sound Classification and Model Interpretability: A Transfer Learning Approach with Deep Learning. Journal of Vascular Diseases. 2023;2(4):438-459. doi:10.3390/jvd2040034

BibTeX
@article{Marocchi2023,
  author = {Marocchi, Milan and Abbott, Leigh and Rong, Yue and Nordholm, Sven and Dwivedi, Girish},
  title = {Abnormal Heart Sound Classification and Model Interpretability: A Transfer Learning Approach with Deep Learning},
  journal = {Journal of Vascular Diseases},
  year = {2023},
  volume = {2},
  number = {4},
  pages = {438--459},
  doi = {10.3390/jvd2040034}
}
Kostenlos starten →