Machine-learning tool for classifying pulmonary hypertension via expert reader-provided CT features: An educational resource for non-dedicated radiologists
This study is the first to develop an ML-driven tool for classifying PH via chest CECT. While performance metrics require improvement, including the need for a larger sample size, the resource can potentially train non-dedicated radiologists in PH classification, supporting multidisciplinary reasoning.
Authors
- Lorenzo Cereser (ORCID: https://orcid.org/0000-0003-4480-8872)
- Andrea Borghesi (ORCID: https://orcid.org/0000-0002-4761-2923)
- Giovanni Agati (ORCID: https://orcid.org/0000-0003-0855-9389)
- Valentino Collini
- Miriam Isola (ORCID: https://orcid.org/0000-0002-6391-1720)
- Tin Nadarević
- R. Girometti
- Chiara Zuiani (ORCID: https://orcid.org/0000-0001-5132-3115)
- Carmelo Cicciò (ORCID: https://orcid.org/0000-0001-9769-8043)
- Vincenzo Della Mea (ORCID: https://orcid.org/0000-0002-0144-3802)
- Massimo Imazio (ORCID: https://orcid.org/0000-0002-5722-0245)
- Vincenzo Patruno (ORCID: https://orcid.org/0000-0001-6984-3936)
- Paola Ciolli (ORCID: https://orcid.org/0000-0002-7846-9162)
- Maria De Martino (ORCID: https://orcid.org/0000-0002-5322-1531)
Institutions
- University of Udine (IT)
- University of Rijeka (HR)
- Ospedale Sacro Cuore Don Calabria (IT)
- Surgical Specialties (Canada) (CA)
- Ospedale Santa Maria della Misericordia di Udine (IT)
- Surgical Specialties (United States) (US)
- University of Brescia (IT)
Publication Details
- Journal
- European Journal of Radiology
- Published
- 2025-02-15
- DOI
- https://doi.org/10.1016/j.ejrad.2025.111998
- Citations
- 1
- Primary Topic
- Pulmonary Hypertension Research and Treatments
- Type
- article
- Field-Weighted Citation Impact
- 1.52