Enhanced classification performance using deep learning based segmentation for pulmonary embolism detection in CT angiography
Our automatic pipeline achieved beyond state-of-the-art diagnostic performance of PE in CTPA using nnU-Net for segmentation and volume- and probability-based post-processing for classification.
Authors
- Tobias Sjöblom (ORCID: https://orcid.org/0000-0001-6668-4140)
- Tomas Fröding (ORCID: https://orcid.org/0000-0002-4053-4301)
- Christian Jamtheim Gustafsson (ORCID: https://orcid.org/0000-0003-2931-5615)
- Dimitrios Toumpanakis (ORCID: https://orcid.org/0000-0002-5221-2721)
- Ali Teymur Kahraman (ORCID: https://orcid.org/0000-0001-7488-6105)
Institutions
- Uppsala University (SE)
- Karolinska University Hospital (SE)
- Lund University (SE)
- Skåne University Hospital (SE)
Publication Details
- Journal
- Heliyon
- Published
- 2024-09-19
- DOI
- https://doi.org/10.1016/j.heliyon.2024.e38118
- Citations
- 7
- Primary Topic
- Venous Thromboembolism Diagnosis and Management
- Type
- article
- Field-Weighted Citation Impact
- 3.85
Funders
- VINNOVA
- Uppsala Universitet