Cardiovascular disease diagnosis using cross-domain transfer learning.

Clicks: 306
ID: 87011
2019
Article Quality & Performance Metrics
Overall Quality
Not rated
Combines reader engagement with the AI quality analysis. This article has not been analysed, so there is no overall score — reader engagement is measured and shown alongside.
AI Quality Assessment
Not analyzed
Readership in this journal
Emerging

Ranked #67 of 127 articles by views in conference proceedings : annual international conference of the ieee engineering in medicine and biology society ieee engineering in medicine and biology society annual conference

Most read Least read

Bar heights use a square-root scale. Only the 120 most-read articles are drawn; the journal has 127 in total.

Mint this article as an NFT
Not yet minted

Create a permanent, verifiable on-chain record of this article on the Scimatic Network. The NFT is held in your Journament account, and you can withdraw it to your own wallet at any time.

5 SUSD one-off · no wallet required
Sign in to mint
Abstract
While cardiovascular diseases (CVDs) are commonly diagnosed by cardiologists via inspecting electrocardiogram (ECG) waveforms, these decisions can be supported by a data-driven approach, which may automate this process. An automatic diagnostic approach often employs hand-crafted features extracted from ECG waveforms. These features, however, do not generalise well, challenged by variation in acquisition settings such as sampling rate and mounting points. Existing deep learning (DL) approaches, on the other hand, extract features from ECG automatically but require construction of dedicated networks that require huge data and computational resource if trained from scratch. Here we propose an end-to-end trainable cross-domain transfer learning for CVD classification from ECG waveforms, by utilising existing vision-based CNN frameworks as feature extractors, followed by ECG feature learning layers. Because these frameworks are designed for image inputs, we employ a stacked spectrogram representation of multi-lead ECG waveforms as a preprocessing step. We also proposed a fusion of multiple ECG leads, using plausible stacking arrangements of the spectrograms, to encode their spatial relations. The proposed approach is validated on multiple ECG datasets and competitive performance is achieved.
Reference Key
tadesse2019cardiovascularconference Use this key to autocite in the manuscript while using SciMatic Manuscript Manager or Thesis Manager
Authors Tadesse, Girmaw Abebe;Zhu, Tingting;Liu, Yong;Zhou, Yingling;Chen, Jiyan;Tian, Maoyi;Clifton, David;
Journal conference proceedings : annual international conference of the ieee engineering in medicine and biology society ieee engineering in medicine and biology society annual conference
Year 2019
DOI
10.1109/EMBC.2019.8857737
URL
Keywords
Machine learning automation workflow dicom series categorization

Citations

No citations found. To add a citation, contact the admin at info@scimatic.org

Comments

No comments yet. Be the first to comment on this article.