Low dose threshold for measuring cardiac functional metrics using four‐dimensional CT with deep learning
We demonstrate that on average radiation dose can be reduced by a factor of 5 while introducing minimal changes to global functional metrics (especially EF, GLS, and CS). The robustness to reduced image quality can be further boosted by using emulated low-dose data in the DL training set.
Authors
- Jed D. Pack (ORCID: https://orcid.org/0000-0003-3232-1012)
- Elliot R. McVeigh (ORCID: https://orcid.org/0000-0003-1684-2432)
- Pengwei Wu (ORCID: https://orcid.org/0000-0002-2412-3043)
- Lauren Severance
- Kyle Kim
Institutions
- University of California San Diego (US)
- GE Global Research (United States) (US)
Publication Details
- Journal
- Journal of Applied Clinical Medical Physics
- Published
- 2024-12-03
- DOI
- https://doi.org/10.1002/acm2.14593
- Citations
- 2
- Primary Topic
- Cardiac Imaging and Diagnostics
- Type
- article
- Field-Weighted Citation Impact
- 0.81
Funders
- National Heart, Lung, and Blood Institute