Accurate fully automated assessment of left ventricle, left atrium, and left atrial appendage function from computed tomography using deep learning
nnU-Net outperformed two different vision transformer architectures for the segmentation and calculation of function parameters for the LV, LA, and LAA. Fully automatic calculation of cardiac function parameters from CT using deep learning is fast and reliable.
Authors
- Anders Persson (ORCID: https://orcid.org/0000-0002-9446-6981)
- Mariana Bustamante (ORCID: https://orcid.org/0000-0002-1958-1672)
- Lilian Henriksson (ORCID: https://orcid.org/0000-0001-5485-6769)
- Lee Jollans (ORCID: https://orcid.org/0000-0003-4254-5159)
- Tino Ebbers (ORCID: https://orcid.org/0000-0003-1395-8296)
Institutions
- Linköping University (SE)
- deCODE Genetics (Iceland) (IS)
- Amgen (Canada) (CA)
Publication Details
- Journal
- European Heart Journal - Imaging Methods and Practice
- Published
- 2024-10-01
- DOI
- https://doi.org/10.1093/ehjimp/qyaf011
- Citations
- 1
- Primary Topic
- Cardiovascular Function and Risk Factors
- Type
- article
- Field-Weighted Citation Impact
- 0.40
Funders
- Hjärt-Lungfonden
- Linköpings Universitet
- Knut och Alice Wallenbergs Stiftelse
- Vetenskapsrådet
- Science for Life Laboratory