Verity plots: A novel method of visualizing reliability assessments of artificial intelligence methods in quantitative cardiovascular magnetic resonance
Verity plots offer markers for bias, variance, trends and outliers, in addition to deciding AI quantification acceptability. The plots were successfully applied to various AI methods in CMR and decisively communicated AI-expert agreement.
Authors
- Sascha Däuber
- Clemens Ammann (ORCID: https://orcid.org/0000-0002-5962-4008)
- Steffen Lange (ORCID: https://orcid.org/0000-0003-2831-6835)
- Jeanette Schulz‐Menger (ORCID: https://orcid.org/0000-0003-3100-1092)
- Thomas Hadler (ORCID: https://orcid.org/0000-0002-6151-6858)
- Leonhard Grassow
- Hadil Saad (ORCID: https://orcid.org/0000-0001-8574-644X)
- Philine Reisdorf
Institutions
- Darmstadt University of Applied Sciences (DE)
- Max Delbrück Center (DE)
- Humboldt-Universität zu Berlin (DE)
- German Centre for Cardiovascular Research (DE)
- Bracco (Italy) (IT)
- Helios Hospital Berlin-Buch (DE)
- Freie Universität Berlin (DE)
- Charité - Universitätsmedizin Berlin (DE)
Publication Details
- Journal
- PLoS ONE
- Published
- 2025-05-16
- DOI
- https://doi.org/10.1371/journal.pone.0323371
- Primary Topic
- Hemodynamic Monitoring and Therapy
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Deutsche Forschungsgemeinschaft