Deep learning-based identification of chronic pulmonary embolism on CTPA: a regional lung analysis using multiplanar MIP images
A convolutional neural network detects chronic thromboembolic pulmonary hypertension and chronic embolism from CTPA MIP projections. CTPA data were divided into four concentric anatomic layers for regional analysis. Central layers were most important for identifying CTEPH features. Network performance improved when more vessel regions were used as input.
Authors
- Teemu Mäkelä (ORCID: https://orcid.org/0000-0003-3777-5283)
- Arttu Ruohola (ORCID: https://orcid.org/0000-0001-5266-8502)
- Marko Kangasniemi (ORCID: https://orcid.org/0000-0001-7501-3373)
- Tuomas Vainio
- Sauli Savolainen
- Anssi Arkko (ORCID: https://orcid.org/0000-0002-7306-7172)
Institutions
- University of Helsinki (FI)
- Helsinki University Hospital (FI)
- Hospital District of Helsinki and Uusimaa (FI)
Publication Details
- Journal
- European Radiology Experimental
- Published
- 2026-03-16
- DOI
- https://doi.org/10.1186/s41747-026-00699-x
- Primary Topic
- Venous Thromboembolism Diagnosis and Management
- Type
- article
- Field-Weighted Citation Impact
- 0.00