Deep Learning Segmentation and Quantification of the Left Ventricle from the Parasternal Short-Axis View in Echocardiography
Our DL-based measurement pipeline for PSAX achieved performance comparable to expert annotators, positioning it as a possible substitute for tedious manual measurements. DL-derived MWT was able to differentiate hypertensive from non-hypertensive subjects, which indicates the potential clinical utility of fully automated PSAX measurements.
Authors
- Thuy Mi Nguyen (ORCID: https://orcid.org/0000-0003-0540-4787)
- Jahn Frederik Grue (ORCID: https://orcid.org/0000-0003-4950-830X)
- Ragnhild Holden Helland (ORCID: https://orcid.org/0000-0002-9592-4876)
- John Nyberg (ORCID: https://orcid.org/0000-0001-6060-0428)
- Andreas Østvik (ORCID: https://orcid.org/0000-0003-3895-2683)
- Håvard Dalen (ORCID: https://orcid.org/0000-0003-1192-3663)
- Lasse Løvstakken (ORCID: https://orcid.org/0000-0003-2474-9588)
- Daniela Melichova (ORCID: https://orcid.org/0000-0003-0678-2077)
- Harald Brunvand
- Bjørnar Grenne (ORCID: https://orcid.org/0000-0002-2984-6865)
- Thor Edvardsen (ORCID: https://orcid.org/0000-0002-3800-765X)
- Kristina Hermann Haugaa (ORCID: https://orcid.org/0000-0002-4900-0453)
- Ingrid Tveten (ORCID: https://orcid.org/0000-0002-9386-8639)
Institutions
- Oslo University Hospital (NO)
- SINTEF (NO)
- University of Oslo (NO)
- Norwegian University of Science and Technology (NO)
- Levanger Hospital (NO)
- Hospital of Southern Norway (NO)
- St Olav's University Hospital (NO)
Publication Details
- Journal
- Ultrasound in Medicine & Biology
- Published
- 2025-11-04
- DOI
- https://doi.org/10.1016/j.ultrasmedbio.2025.10.005
- Primary Topic
- Cardiovascular Function and Risk Factors
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Norges Forskningsråd